add support for linux_riscv64 and freestanding_riscv64

10 files changed, 455 insertions, 44 deletions

diff --git a/src/build_settings.cpp b/src/build_settings.cpp
index 82523d736..3d56f4202 100644
--- a/src/build_settings.cpp
+++ b/src/build_settings.cpp
@@ -39,6 +39,7 @@ enum TargetArchKind : u16 {
 	TargetArch_arm64,
 	TargetArch_wasm32,
 	TargetArch_wasm64p32,
+	TargetArch_riscv64,
 
 	TargetArch_COUNT,
 };
@@ -104,6 +105,7 @@ gb_global String target_arch_names[TargetArch_COUNT] = {
 	str_lit("arm64"),
 	str_lit("wasm32"),
 	str_lit("wasm64p32"),
+	str_lit("riscv64"),
 };
 
 #include "build_settings_microarch.cpp"
@@ -555,13 +557,18 @@ gb_global TargetMetrics target_linux_arm64 = {
 	8, 8, 16, 32,
 	str_lit("aarch64-linux-elf"),
 };
-
 gb_global TargetMetrics target_linux_arm32 = {
 	TargetOs_linux,
 	TargetArch_arm32,
 	4, 4, 8, 16,
 	str_lit("arm-unknown-linux-gnueabihf"),
 };
+gb_global TargetMetrics target_linux_riscv64 = {
+	TargetOs_linux,
+	TargetArch_riscv64,
+	8, 8, 16, 32,
+	str_lit("riscv64-linux-gnu"),
+};
 
 gb_global TargetMetrics target_darwin_amd64 = {
 	TargetOs_darwin,
@@ -716,6 +723,12 @@ gb_global TargetMetrics target_freestanding_arm32 = {
 	4, 4, 8, 16,
 	str_lit("arm-unknown-unknown-gnueabihf"),
 };
+gb_global TargetMetrics target_freestanding_riscv64 = {
+	TargetOs_freestanding,
+	TargetArch_riscv64,
+	8, 8, 16, 32,
+	str_lit("riscv64-unknown-gnu"),
+};
 
 
 struct NamedTargetMetrics {
@@ -733,6 +746,7 @@ gb_global NamedTargetMetrics named_targets[] = {
 	{ str_lit("linux_amd64"),         &target_linux_amd64    },
 	{ str_lit("linux_arm64"),         &target_linux_arm64    },
 	{ str_lit("linux_arm32"),         &target_linux_arm32    },
+	{ str_lit("linux_riscv64"),       &target_linux_riscv64  },
 
 	{ str_lit("windows_i386"),        &target_windows_i386   },
 	{ str_lit("windows_amd64"),       &target_windows_amd64  },
@@ -761,6 +775,8 @@ gb_global NamedTargetMetrics named_targets[] = {
 
 	{ str_lit("freestanding_arm64"), &target_freestanding_arm64 },
 	{ str_lit("freestanding_arm32"), &target_freestanding_arm32 },
+
+	{ str_lit("freestanding_riscv64"), &target_freestanding_riscv64 },
 };
 
 gb_global NamedTargetMetrics *selected_target_metrics;
@@ -1631,6 +1647,8 @@ gb_internal void init_build_context(TargetMetrics *cross_target, Subtarget subta
 
 		// Disallow on wasm
 		bc->use_separate_modules = false;
+	} if(bc->metrics.arch == TargetArch_riscv64) {
+		bc->link_flags = str_lit("-target riscv64 ");
 	} else {
 		// NOTE: for targets other than darwin, we don't specify a `-target` link flag.
 		// This is because we don't support cross-linking and clang is better at figuring
diff --git a/src/build_settings_microarch.cpp b/src/build_settings_microarch.cpp
index 02b507031..8f64d4026 100644
--- a/src/build_settings_microarch.cpp
+++ b/src/build_settings_microarch.cpp
@@ -3,17 +3,19 @@ gb_global String target_microarch_list[TargetArch_COUNT] = {
 	// TargetArch_Invalid:
 	str_lit(""),
 	// TargetArch_amd64:
-	str_lit("alderlake,amdfam10,athlon,athlon-4,athlon-fx,athlon-mp,athlon-tbird,athlon-xp,athlon64,athlon64-sse3,atom,atom_sse4_2,atom_sse4_2_movbe,barcelona,bdver1,bdver2,bdver3,bdver4,bonnell,broadwell,btver1,btver2,c3,c3-2,cannonlake,cascadelake,cooperlake,core-avx-i,core-avx2,core2,core_2_duo_sse4_1,core_2_duo_ssse3,core_2nd_gen_avx,core_3rd_gen_avx,core_4th_gen_avx,core_4th_gen_avx_tsx,core_5th_gen_avx,core_5th_gen_avx_tsx,core_aes_pclmulqdq,core_i7_sse4_2,corei7,corei7-avx,emeraldrapids,generic,geode,goldmont,goldmont-plus,goldmont_plus,grandridge,graniterapids,graniterapids-d,graniterapids_d,haswell,i386,i486,i586,i686,icelake-client,icelake-server,icelake_client,icelake_server,ivybridge,k6,k6-2,k6-3,k8,k8-sse3,knl,knm,lakemont,meteorlake,mic_avx512,nehalem,nocona,opteron,opteron-sse3,penryn,pentium,pentium-m,pentium-mmx,pentium2,pentium3,pentium3m,pentium4,pentium4m,pentium_4,pentium_4_sse3,pentium_ii,pentium_iii,pentium_iii_no_xmm_regs,pentium_m,pentium_mmx,pentium_pro,pentiumpro,prescott,raptorlake,rocketlake,sandybridge,sapphirerapids,sierraforest,silvermont,skx,skylake,skylake-avx512,skylake_avx512,slm,tigerlake,tremont,westmere,winchip-c6,winchip2,x86-64,x86-64-v2,x86-64-v3,x86-64-v4,yonah,znver1,znver2,znver3,znver4"),
+	str_lit("alderlake,amdfam10,arrowlake,arrowlake-s,arrowlake_s,athlon,athlon-4,athlon-fx,athlon-mp,athlon-tbird,athlon-xp,athlon64,athlon64-sse3,atom,atom_sse4_2,atom_sse4_2_movbe,barcelona,bdver1,bdver2,bdver3,bdver4,bonnell,broadwell,btver1,btver2,c3,c3-2,cannonlake,cascadelake,clearwaterforest,cooperlake,core-avx-i,core-avx2,core2,core_2_duo_sse4_1,core_2_duo_ssse3,core_2nd_gen_avx,core_3rd_gen_avx,core_4th_gen_avx,core_4th_gen_avx_tsx,core_5th_gen_avx,core_5th_gen_avx_tsx,core_aes_pclmulqdq,core_i7_sse4_2,corei7,corei7-avx,emeraldrapids,generic,geode,goldmont,goldmont-plus,goldmont_plus,gracemont,grandridge,graniterapids,graniterapids-d,graniterapids_d,haswell,i386,i486,i586,i686,icelake-client,icelake-server,icelake_client,icelake_server,ivybridge,k6,k6-2,k6-3,k8,k8-sse3,knl,knm,lakemont,lunarlake,meteorlake,mic_avx512,nehalem,nocona,opteron,opteron-sse3,pantherlake,penryn,pentium,pentium-m,pentium-mmx,pentium2,pentium3,pentium3m,pentium4,pentium4m,pentium_4,pentium_4_sse3,pentium_ii,pentium_iii,pentium_iii_no_xmm_regs,pentium_m,pentium_mmx,pentium_pro,pentiumpro,prescott,raptorlake,rocketlake,sandybridge,sapphirerapids,sierraforest,silvermont,skx,skylake,skylake-avx512,skylake_avx512,slm,tigerlake,tremont,westmere,winchip-c6,winchip2,x86-64,x86-64-v2,x86-64-v3,x86-64-v4,yonah,znver1,znver2,znver3,znver4"),
 	// TargetArch_i386:
-	str_lit("alderlake,amdfam10,athlon,athlon-4,athlon-fx,athlon-mp,athlon-tbird,athlon-xp,athlon64,athlon64-sse3,atom,atom_sse4_2,atom_sse4_2_movbe,barcelona,bdver1,bdver2,bdver3,bdver4,bonnell,broadwell,btver1,btver2,c3,c3-2,cannonlake,cascadelake,cooperlake,core-avx-i,core-avx2,core2,core_2_duo_sse4_1,core_2_duo_ssse3,core_2nd_gen_avx,core_3rd_gen_avx,core_4th_gen_avx,core_4th_gen_avx_tsx,core_5th_gen_avx,core_5th_gen_avx_tsx,core_aes_pclmulqdq,core_i7_sse4_2,corei7,corei7-avx,emeraldrapids,generic,geode,goldmont,goldmont-plus,goldmont_plus,grandridge,graniterapids,graniterapids-d,graniterapids_d,haswell,i386,i486,i586,i686,icelake-client,icelake-server,icelake_client,icelake_server,ivybridge,k6,k6-2,k6-3,k8,k8-sse3,knl,knm,lakemont,meteorlake,mic_avx512,nehalem,nocona,opteron,opteron-sse3,penryn,pentium,pentium-m,pentium-mmx,pentium2,pentium3,pentium3m,pentium4,pentium4m,pentium_4,pentium_4_sse3,pentium_ii,pentium_iii,pentium_iii_no_xmm_regs,pentium_m,pentium_mmx,pentium_pro,pentiumpro,prescott,raptorlake,rocketlake,sandybridge,sapphirerapids,sierraforest,silvermont,skx,skylake,skylake-avx512,skylake_avx512,slm,tigerlake,tremont,westmere,winchip-c6,winchip2,x86-64,x86-64-v2,x86-64-v3,x86-64-v4,yonah,znver1,znver2,znver3,znver4"),
+	str_lit("alderlake,amdfam10,arrowlake,arrowlake-s,arrowlake_s,athlon,athlon-4,athlon-fx,athlon-mp,athlon-tbird,athlon-xp,athlon64,athlon64-sse3,atom,atom_sse4_2,atom_sse4_2_movbe,barcelona,bdver1,bdver2,bdver3,bdver4,bonnell,broadwell,btver1,btver2,c3,c3-2,cannonlake,cascadelake,clearwaterforest,cooperlake,core-avx-i,core-avx2,core2,core_2_duo_sse4_1,core_2_duo_ssse3,core_2nd_gen_avx,core_3rd_gen_avx,core_4th_gen_avx,core_4th_gen_avx_tsx,core_5th_gen_avx,core_5th_gen_avx_tsx,core_aes_pclmulqdq,core_i7_sse4_2,corei7,corei7-avx,emeraldrapids,generic,geode,goldmont,goldmont-plus,goldmont_plus,gracemont,grandridge,graniterapids,graniterapids-d,graniterapids_d,haswell,i386,i486,i586,i686,icelake-client,icelake-server,icelake_client,icelake_server,ivybridge,k6,k6-2,k6-3,k8,k8-sse3,knl,knm,lakemont,lunarlake,meteorlake,mic_avx512,nehalem,nocona,opteron,opteron-sse3,pantherlake,penryn,pentium,pentium-m,pentium-mmx,pentium2,pentium3,pentium3m,pentium4,pentium4m,pentium_4,pentium_4_sse3,pentium_ii,pentium_iii,pentium_iii_no_xmm_regs,pentium_m,pentium_mmx,pentium_pro,pentiumpro,prescott,raptorlake,rocketlake,sandybridge,sapphirerapids,sierraforest,silvermont,skx,skylake,skylake-avx512,skylake_avx512,slm,tigerlake,tremont,westmere,winchip-c6,winchip2,x86-64,x86-64-v2,x86-64-v3,x86-64-v4,yonah,znver1,znver2,znver3,znver4"),
 	// TargetArch_arm32:
-	str_lit("arm1020e,arm1020t,arm1022e,arm10e,arm10tdmi,arm1136j-s,arm1136jf-s,arm1156t2-s,arm1156t2f-s,arm1176jz-s,arm1176jzf-s,arm710t,arm720t,arm7tdmi,arm7tdmi-s,arm8,arm810,arm9,arm920,arm920t,arm922t,arm926ej-s,arm940t,arm946e-s,arm966e-s,arm968e-s,arm9e,arm9tdmi,cortex-a12,cortex-a15,cortex-a17,cortex-a32,cortex-a35,cortex-a5,cortex-a53,cortex-a55,cortex-a57,cortex-a7,cortex-a710,cortex-a72,cortex-a73,cortex-a75,cortex-a76,cortex-a76ae,cortex-a77,cortex-a78,cortex-a78c,cortex-a8,cortex-a9,cortex-m0,cortex-m0plus,cortex-m1,cortex-m23,cortex-m3,cortex-m33,cortex-m35p,cortex-m4,cortex-m55,cortex-m7,cortex-m85,cortex-r4,cortex-r4f,cortex-r5,cortex-r52,cortex-r7,cortex-r8,cortex-x1,cortex-x1c,cyclone,ep9312,exynos-m3,exynos-m4,exynos-m5,generic,iwmmxt,krait,kryo,mpcore,mpcorenovfp,neoverse-n1,neoverse-n2,neoverse-v1,sc000,sc300,strongarm,strongarm110,strongarm1100,strongarm1110,swift,xscale"),
+	str_lit("arm1020e,arm1020t,arm1022e,arm10e,arm10tdmi,arm1136j-s,arm1136jf-s,arm1156t2-s,arm1156t2f-s,arm1176jz-s,arm1176jzf-s,arm710t,arm720t,arm7tdmi,arm7tdmi-s,arm8,arm810,arm9,arm920,arm920t,arm922t,arm926ej-s,arm940t,arm946e-s,arm966e-s,arm968e-s,arm9e,arm9tdmi,cortex-a12,cortex-a15,cortex-a17,cortex-a32,cortex-a35,cortex-a5,cortex-a53,cortex-a55,cortex-a57,cortex-a7,cortex-a710,cortex-a72,cortex-a73,cortex-a75,cortex-a76,cortex-a76ae,cortex-a77,cortex-a78,cortex-a78c,cortex-a8,cortex-a9,cortex-m0,cortex-m0plus,cortex-m1,cortex-m23,cortex-m3,cortex-m33,cortex-m35p,cortex-m4,cortex-m52,cortex-m55,cortex-m7,cortex-m85,cortex-r4,cortex-r4f,cortex-r5,cortex-r52,cortex-r7,cortex-r8,cortex-x1,cortex-x1c,cyclone,ep9312,exynos-m3,exynos-m4,exynos-m5,generic,iwmmxt,krait,kryo,mpcore,mpcorenovfp,neoverse-n1,neoverse-n2,neoverse-v1,sc000,sc300,strongarm,strongarm110,strongarm1100,strongarm1110,swift,xscale"),
 	// TargetArch_arm64:
-	str_lit("a64fx,ampere1,ampere1a,apple-a10,apple-a11,apple-a12,apple-a13,apple-a14,apple-a15,apple-a16,apple-a7,apple-a8,apple-a9,apple-latest,apple-m1,apple-m2,apple-s4,apple-s5,carmel,cortex-a34,cortex-a35,cortex-a510,cortex-a53,cortex-a55,cortex-a57,cortex-a65,cortex-a65ae,cortex-a710,cortex-a715,cortex-a72,cortex-a73,cortex-a75,cortex-a76,cortex-a76ae,cortex-a77,cortex-a78,cortex-a78c,cortex-r82,cortex-x1,cortex-x1c,cortex-x2,cortex-x3,cyclone,exynos-m3,exynos-m4,exynos-m5,falkor,generic,kryo,neoverse-512tvb,neoverse-e1,neoverse-n1,neoverse-n2,neoverse-v1,neoverse-v2,saphira,thunderx,thunderx2t99,thunderx3t110,thunderxt81,thunderxt83,thunderxt88,tsv110"),
+	str_lit("a64fx,ampere1,ampere1a,ampere1b,apple-a10,apple-a11,apple-a12,apple-a13,apple-a14,apple-a15,apple-a16,apple-a17,apple-a7,apple-a8,apple-a9,apple-latest,apple-m1,apple-m2,apple-m3,apple-s4,apple-s5,carmel,cortex-a34,cortex-a35,cortex-a510,cortex-a520,cortex-a53,cortex-a55,cortex-a57,cortex-a65,cortex-a65ae,cortex-a710,cortex-a715,cortex-a72,cortex-a720,cortex-a73,cortex-a75,cortex-a76,cortex-a76ae,cortex-a77,cortex-a78,cortex-a78c,cortex-r82,cortex-x1,cortex-x1c,cortex-x2,cortex-x3,cortex-x4,cyclone,exynos-m3,exynos-m4,exynos-m5,falkor,generic,kryo,neoverse-512tvb,neoverse-e1,neoverse-n1,neoverse-n2,neoverse-v1,neoverse-v2,saphira,thunderx,thunderx2t99,thunderx3t110,thunderxt81,thunderxt83,thunderxt88,tsv110"),
 	// TargetArch_wasm32:
 	str_lit("bleeding-edge,generic,mvp"),
 	// TargetArch_wasm64p32:
 	str_lit("bleeding-edge,generic,mvp"),
+	// TargetArch_riscv64:
+	str_lit("generic,generic-rv32,generic-rv64,rocket,rocket-rv32,rocket-rv64,sifive-7-series,sifive-e20,sifive-e21,sifive-e24,sifive-e31,sifive-e34,sifive-e76,sifive-p450,sifive-p670,sifive-s21,sifive-s51,sifive-s54,sifive-s76,sifive-u54,sifive-u74,sifive-x280,syntacore-scr1-base,syntacore-scr1-max,veyron-v1,xiangshan-nanhu"),
 };
 
 // Generated with the featuregen script in `misc/featuregen`
@@ -21,17 +23,19 @@ gb_global String target_features_list[TargetArch_COUNT] = {
 	// TargetArch_Invalid:
 	str_lit(""),
 	// TargetArch_amd64:
-	str_lit("16bit-mode,32bit-mode,3dnow,3dnowa,64bit,64bit-mode,adx,aes,allow-light-256-bit,amx-bf16,amx-complex,amx-fp16,amx-int8,amx-tile,avx,avx2,avx512bf16,avx512bitalg,avx512bw,avx512cd,avx512dq,avx512er,avx512f,avx512fp16,avx512ifma,avx512pf,avx512vbmi,avx512vbmi2,avx512vl,avx512vnni,avx512vp2intersect,avx512vpopcntdq,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,branchfusion,cldemote,clflushopt,clwb,clzero,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,ermsb,f16c,false-deps-getmant,false-deps-lzcnt-tzcnt,false-deps-mulc,false-deps-mullq,false-deps-perm,false-deps-popcnt,false-deps-range,fast-11bytenop,fast-15bytenop,fast-7bytenop,fast-bextr,fast-gather,fast-hops,fast-lzcnt,fast-movbe,fast-scalar-fsqrt,fast-scalar-shift-masks,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fast-vector-shift-masks,faster-shift-than-shuffle,fma,fma4,fsgsbase,fsrm,fxsr,gfni,harden-sls-ijmp,harden-sls-ret,hreset,idivl-to-divb,idivq-to-divl,invpcid,kl,lea-sp,lea-uses-ag,lvi-cfi,lvi-load-hardening,lwp,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,mwaitx,no-bypass-delay,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pad-short-functions,pclmul,pconfig,pku,popcnt,prefer-128-bit,prefer-256-bit,prefer-mask-registers,prefer-movmsk-over-vtest,prefer-no-gather,prefer-no-scatter,prefetchi,prefetchwt1,prfchw,ptwrite,raoint,rdpid,rdpru,rdrnd,rdseed,retpoline,retpoline-external-thunk,retpoline-indirect-branches,retpoline-indirect-calls,rtm,sahf,sbb-dep-breaking,serialize,seses,sgx,sha,sha512,shstk,slow-3ops-lea,slow-incdec,slow-lea,slow-pmaddwd,slow-pmulld,slow-shld,slow-two-mem-ops,slow-unaligned-mem-16,slow-unaligned-mem-32,sm3,sm4,soft-float,sse,sse-unaligned-mem,sse2,sse3,sse4.1,sse4.2,sse4a,ssse3,tagged-globals,tbm,tsxldtrk,tuning-fast-imm-vector-shift,uintr,use-glm-div-sqrt-costs,use-slm-arith-costs,vaes,vpclmulqdq,vzeroupper,waitpkg,wbnoinvd,widekl,x87,xop,xsave,xsavec,xsaveopt,xsaves"),
+	str_lit("16bit-mode,32bit-mode,3dnow,3dnowa,64bit,64bit-mode,adx,aes,allow-light-256-bit,amx-bf16,amx-complex,amx-fp16,amx-int8,amx-tile,avx,avx10.1-256,avx10.1-512,avx2,avx512bf16,avx512bitalg,avx512bw,avx512cd,avx512dq,avx512er,avx512f,avx512fp16,avx512ifma,avx512pf,avx512vbmi,avx512vbmi2,avx512vl,avx512vnni,avx512vp2intersect,avx512vpopcntdq,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,branchfusion,ccmp,cf,cldemote,clflushopt,clwb,clzero,cmov,cmpccxadd,crc32,cx16,cx8,egpr,enqcmd,ermsb,evex512,f16c,false-deps-getmant,false-deps-lzcnt-tzcnt,false-deps-mulc,false-deps-mullq,false-deps-perm,false-deps-popcnt,false-deps-range,fast-11bytenop,fast-15bytenop,fast-7bytenop,fast-bextr,fast-gather,fast-hops,fast-lzcnt,fast-movbe,fast-scalar-fsqrt,fast-scalar-shift-masks,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fast-vector-shift-masks,faster-shift-than-shuffle,fma,fma4,fsgsbase,fsrm,fxsr,gfni,harden-sls-ijmp,harden-sls-ret,hreset,idivl-to-divb,idivq-to-divl,invpcid,kl,lea-sp,lea-uses-ag,lvi-cfi,lvi-load-hardening,lwp,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,mwaitx,ndd,no-bypass-delay,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pad-short-functions,pclmul,pconfig,pku,popcnt,ppx,prefer-128-bit,prefer-256-bit,prefer-mask-registers,prefer-movmsk-over-vtest,prefer-no-gather,prefer-no-scatter,prefetchi,prefetchwt1,prfchw,ptwrite,push2pop2,raoint,rdpid,rdpru,rdrnd,rdseed,retpoline,retpoline-external-thunk,retpoline-indirect-branches,retpoline-indirect-calls,rtm,sahf,sbb-dep-breaking,serialize,seses,sgx,sha,sha512,shstk,slow-3ops-lea,slow-incdec,slow-lea,slow-pmaddwd,slow-pmulld,slow-shld,slow-two-mem-ops,slow-unaligned-mem-16,slow-unaligned-mem-32,sm3,sm4,soft-float,sse,sse-unaligned-mem,sse2,sse3,sse4.1,sse4.2,sse4a,ssse3,tagged-globals,tbm,tsxldtrk,tuning-fast-imm-vector-shift,uintr,use-glm-div-sqrt-costs,use-slm-arith-costs,usermsr,vaes,vpclmulqdq,vzeroupper,waitpkg,wbnoinvd,widekl,x87,xop,xsave,xsavec,xsaveopt,xsaves"),
 	// TargetArch_i386:
-	str_lit("16bit-mode,32bit-mode,3dnow,3dnowa,64bit,64bit-mode,adx,aes,allow-light-256-bit,amx-bf16,amx-complex,amx-fp16,amx-int8,amx-tile,avx,avx2,avx512bf16,avx512bitalg,avx512bw,avx512cd,avx512dq,avx512er,avx512f,avx512fp16,avx512ifma,avx512pf,avx512vbmi,avx512vbmi2,avx512vl,avx512vnni,avx512vp2intersect,avx512vpopcntdq,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,branchfusion,cldemote,clflushopt,clwb,clzero,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,ermsb,f16c,false-deps-getmant,false-deps-lzcnt-tzcnt,false-deps-mulc,false-deps-mullq,false-deps-perm,false-deps-popcnt,false-deps-range,fast-11bytenop,fast-15bytenop,fast-7bytenop,fast-bextr,fast-gather,fast-hops,fast-lzcnt,fast-movbe,fast-scalar-fsqrt,fast-scalar-shift-masks,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fast-vector-shift-masks,faster-shift-than-shuffle,fma,fma4,fsgsbase,fsrm,fxsr,gfni,harden-sls-ijmp,harden-sls-ret,hreset,idivl-to-divb,idivq-to-divl,invpcid,kl,lea-sp,lea-uses-ag,lvi-cfi,lvi-load-hardening,lwp,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,mwaitx,no-bypass-delay,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pad-short-functions,pclmul,pconfig,pku,popcnt,prefer-128-bit,prefer-256-bit,prefer-mask-registers,prefer-movmsk-over-vtest,prefer-no-gather,prefer-no-scatter,prefetchi,prefetchwt1,prfchw,ptwrite,raoint,rdpid,rdpru,rdrnd,rdseed,retpoline,retpoline-external-thunk,retpoline-indirect-branches,retpoline-indirect-calls,rtm,sahf,sbb-dep-breaking,serialize,seses,sgx,sha,sha512,shstk,slow-3ops-lea,slow-incdec,slow-lea,slow-pmaddwd,slow-pmulld,slow-shld,slow-two-mem-ops,slow-unaligned-mem-16,slow-unaligned-mem-32,sm3,sm4,soft-float,sse,sse-unaligned-mem,sse2,sse3,sse4.1,sse4.2,sse4a,ssse3,tagged-globals,tbm,tsxldtrk,tuning-fast-imm-vector-shift,uintr,use-glm-div-sqrt-costs,use-slm-arith-costs,vaes,vpclmulqdq,vzeroupper,waitpkg,wbnoinvd,widekl,x87,xop,xsave,xsavec,xsaveopt,xsaves"),
+	str_lit("16bit-mode,32bit-mode,3dnow,3dnowa,64bit,64bit-mode,adx,aes,allow-light-256-bit,amx-bf16,amx-complex,amx-fp16,amx-int8,amx-tile,avx,avx10.1-256,avx10.1-512,avx2,avx512bf16,avx512bitalg,avx512bw,avx512cd,avx512dq,avx512er,avx512f,avx512fp16,avx512ifma,avx512pf,avx512vbmi,avx512vbmi2,avx512vl,avx512vnni,avx512vp2intersect,avx512vpopcntdq,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,branchfusion,ccmp,cf,cldemote,clflushopt,clwb,clzero,cmov,cmpccxadd,crc32,cx16,cx8,egpr,enqcmd,ermsb,evex512,f16c,false-deps-getmant,false-deps-lzcnt-tzcnt,false-deps-mulc,false-deps-mullq,false-deps-perm,false-deps-popcnt,false-deps-range,fast-11bytenop,fast-15bytenop,fast-7bytenop,fast-bextr,fast-gather,fast-hops,fast-lzcnt,fast-movbe,fast-scalar-fsqrt,fast-scalar-shift-masks,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fast-vector-shift-masks,faster-shift-than-shuffle,fma,fma4,fsgsbase,fsrm,fxsr,gfni,harden-sls-ijmp,harden-sls-ret,hreset,idivl-to-divb,idivq-to-divl,invpcid,kl,lea-sp,lea-uses-ag,lvi-cfi,lvi-load-hardening,lwp,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,mwaitx,ndd,no-bypass-delay,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pad-short-functions,pclmul,pconfig,pku,popcnt,ppx,prefer-128-bit,prefer-256-bit,prefer-mask-registers,prefer-movmsk-over-vtest,prefer-no-gather,prefer-no-scatter,prefetchi,prefetchwt1,prfchw,ptwrite,push2pop2,raoint,rdpid,rdpru,rdrnd,rdseed,retpoline,retpoline-external-thunk,retpoline-indirect-branches,retpoline-indirect-calls,rtm,sahf,sbb-dep-breaking,serialize,seses,sgx,sha,sha512,shstk,slow-3ops-lea,slow-incdec,slow-lea,slow-pmaddwd,slow-pmulld,slow-shld,slow-two-mem-ops,slow-unaligned-mem-16,slow-unaligned-mem-32,sm3,sm4,soft-float,sse,sse-unaligned-mem,sse2,sse3,sse4.1,sse4.2,sse4a,ssse3,tagged-globals,tbm,tsxldtrk,tuning-fast-imm-vector-shift,uintr,use-glm-div-sqrt-costs,use-slm-arith-costs,usermsr,vaes,vpclmulqdq,vzeroupper,waitpkg,wbnoinvd,widekl,x87,xop,xsave,xsavec,xsaveopt,xsaves"),
 	// TargetArch_arm32:
-	str_lit("32bit,8msecext,a12,a15,a17,a32,a35,a5,a53,a55,a57,a7,a72,a73,a75,a76,a77,a78c,a8,a9,aapcs-frame-chain,aapcs-frame-chain-leaf,aclass,acquire-release,aes,armv4,armv4t,armv5t,armv5te,armv5tej,armv6,armv6-m,armv6j,armv6k,armv6kz,armv6s-m,armv6t2,armv7-a,armv7-m,armv7-r,armv7e-m,armv7k,armv7s,armv7ve,armv8-a,armv8-m.base,armv8-m.main,armv8-r,armv8.1-a,armv8.1-m.main,armv8.2-a,armv8.3-a,armv8.4-a,armv8.5-a,armv8.6-a,armv8.7-a,armv8.8-a,armv8.9-a,armv9-a,armv9.1-a,armv9.2-a,armv9.3-a,armv9.4-a,atomics-32,avoid-movs-shop,avoid-partial-cpsr,bf16,big-endian-instructions,cde,cdecp0,cdecp1,cdecp2,cdecp3,cdecp4,cdecp5,cdecp6,cdecp7,cheap-predicable-cpsr,clrbhb,cortex-a710,cortex-a78,cortex-x1,cortex-x1c,crc,crypto,d32,db,dfb,disable-postra-scheduler,dont-widen-vmovs,dotprod,dsp,execute-only,expand-fp-mlx,exynos,fix-cmse-cve-2021-35465,fix-cortex-a57-aes-1742098,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp16fml,fp64,fpao,fpregs,fpregs16,fpregs64,fullfp16,fuse-aes,fuse-literals,harden-sls-blr,harden-sls-nocomdat,harden-sls-retbr,hwdiv,hwdiv-arm,i8mm,iwmmxt,iwmmxt2,krait,kryo,lob,long-calls,loop-align,m3,m7,mclass,mp,muxed-units,mve,mve.fp,mve1beat,mve2beat,mve4beat,nacl-trap,neon,neon-fpmovs,neonfp,neoverse-v1,no-branch-predictor,no-bti-at-return-twice,no-movt,no-neg-immediates,noarm,nonpipelined-vfp,pacbti,perfmon,prefer-ishst,prefer-vmovsr,prof-unpr,r4,r5,r52,r7,ras,rclass,read-tp-tpidrprw,read-tp-tpidruro,read-tp-tpidrurw,reserve-r9,ret-addr-stack,sb,sha2,slow-fp-brcc,slow-load-D-subreg,slow-odd-reg,slow-vdup32,slow-vgetlni32,slowfpvfmx,slowfpvmlx,soft-float,splat-vfp-neon,strict-align,swift,thumb-mode,thumb2,trustzone,use-mipipeliner,use-misched,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8.1a,v8.1m.main,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8.7a,v8.8a,v8.9a,v8m,v8m.main,v9.1a,v9.2a,v9.3a,v9.4a,v9a,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization,vldn-align,vmlx-forwarding,vmlx-hazards,wide-stride-vfp,xscale,zcz"),
+	str_lit("32bit,8msecext,a12,a15,a17,a32,a35,a5,a53,a55,a57,a7,a72,a73,a75,a76,a77,a78c,a8,a9,aapcs-frame-chain,aapcs-frame-chain-leaf,aclass,acquire-release,aes,armv4,armv4t,armv5t,armv5te,armv5tej,armv6,armv6-m,armv6j,armv6k,armv6kz,armv6s-m,armv6t2,armv7-a,armv7-m,armv7-r,armv7e-m,armv7k,armv7s,armv7ve,armv8-a,armv8-m.base,armv8-m.main,armv8-r,armv8.1-a,armv8.1-m.main,armv8.2-a,armv8.3-a,armv8.4-a,armv8.5-a,armv8.6-a,armv8.7-a,armv8.8-a,armv8.9-a,armv9-a,armv9.1-a,armv9.2-a,armv9.3-a,armv9.4-a,armv9.5-a,atomics-32,avoid-movs-shop,avoid-partial-cpsr,bf16,big-endian-instructions,cde,cdecp0,cdecp1,cdecp2,cdecp3,cdecp4,cdecp5,cdecp6,cdecp7,cheap-predicable-cpsr,clrbhb,cortex-a710,cortex-a78,cortex-x1,cortex-x1c,crc,crypto,d32,db,dfb,disable-postra-scheduler,dont-widen-vmovs,dotprod,dsp,execute-only,expand-fp-mlx,exynos,fix-cmse-cve-2021-35465,fix-cortex-a57-aes-1742098,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp16fml,fp64,fpao,fpregs,fpregs16,fpregs64,fullfp16,fuse-aes,fuse-literals,harden-sls-blr,harden-sls-nocomdat,harden-sls-retbr,hwdiv,hwdiv-arm,i8mm,iwmmxt,iwmmxt2,krait,kryo,lob,long-calls,loop-align,m3,m7,mclass,mp,muxed-units,mve,mve.fp,mve1beat,mve2beat,mve4beat,nacl-trap,neon,neon-fpmovs,neonfp,neoverse-v1,no-branch-predictor,no-bti-at-return-twice,no-movt,no-neg-immediates,noarm,nonpipelined-vfp,pacbti,perfmon,prefer-ishst,prefer-vmovsr,prof-unpr,r4,r5,r52,r7,ras,rclass,read-tp-tpidrprw,read-tp-tpidruro,read-tp-tpidrurw,reserve-r9,ret-addr-stack,sb,sha2,slow-fp-brcc,slow-load-D-subreg,slow-odd-reg,slow-vdup32,slow-vgetlni32,slowfpvfmx,slowfpvmlx,soft-float,splat-vfp-neon,strict-align,swift,thumb-mode,thumb2,trustzone,use-mipipeliner,use-misched,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8.1a,v8.1m.main,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8.7a,v8.8a,v8.9a,v8m,v8m.main,v9.1a,v9.2a,v9.3a,v9.4a,v9.5a,v9a,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization,vldn-align,vmlx-forwarding,vmlx-hazards,wide-stride-vfp,xscale,zcz"),
 	// TargetArch_arm64:
-	str_lit("CONTEXTIDREL2,a35,a510,a53,a55,a57,a64fx,a65,a710,a715,a72,a73,a75,a76,a77,a78,a78c,aes,aggressive-fma,all,alternate-sextload-cvt-f32-pattern,altnzcv,am,ampere1,ampere1a,amvs,apple-a10,apple-a11,apple-a12,apple-a13,apple-a14,apple-a15,apple-a16,apple-a7,apple-a7-sysreg,arith-bcc-fusion,arith-cbz-fusion,ascend-store-address,b16b16,balance-fp-ops,bf16,brbe,bti,call-saved-x10,call-saved-x11,call-saved-x12,call-saved-x13,call-saved-x14,call-saved-x15,call-saved-x18,call-saved-x8,call-saved-x9,carmel,ccdp,ccidx,ccpp,chk,clrbhb,cmp-bcc-fusion,complxnum,cortex-r82,cortex-x1,cortex-x2,cortex-x3,crc,crypto,cssc,custom-cheap-as-move,d128,disable-latency-sched-heuristic,dit,dotprod,ecv,el2vmsa,el3,enable-select-opt,ete,exynos-cheap-as-move,exynosm3,exynosm4,f32mm,f64mm,falkor,fgt,fix-cortex-a53-835769,flagm,fmv,force-32bit-jump-tables,fp-armv8,fp16fml,fptoint,fullfp16,fuse-address,fuse-addsub-2reg-const1,fuse-adrp-add,fuse-aes,fuse-arith-logic,fuse-crypto-eor,fuse-csel,fuse-literals,gcs,harden-sls-blr,harden-sls-nocomdat,harden-sls-retbr,hbc,hcx,i8mm,ite,jsconv,kryo,lor,ls64,lse,lse128,lse2,lsl-fast,mec,mops,mpam,mte,neon,neoverse512tvb,neoversee1,neoversen1,neoversen2,neoversev1,neoversev2,nmi,no-bti-at-return-twice,no-neg-immediates,no-sve-fp-ld1r,no-zcz-fp,nv,outline-atomics,pan,pan-rwv,pauth,perfmon,predictable-select-expensive,predres,prfm-slc-target,rand,ras,rasv2,rcpc,rcpc-immo,rcpc3,rdm,reserve-x1,reserve-x10,reserve-x11,reserve-x12,reserve-x13,reserve-x14,reserve-x15,reserve-x18,reserve-x2,reserve-x20,reserve-x21,reserve-x22,reserve-x23,reserve-x24,reserve-x25,reserve-x26,reserve-x27,reserve-x28,reserve-x3,reserve-x30,reserve-x4,reserve-x5,reserve-x6,reserve-x7,reserve-x9,rme,saphira,sb,sel2,sha2,sha3,slow-misaligned-128store,slow-paired-128,slow-strqro-store,sm4,sme,sme-f16f16,sme-f64f64,sme-i16i64,sme2,sme2p1,spe,spe-eef,specres2,specrestrict,ssbs,strict-align,sve,sve2,sve2-aes,sve2-bitperm,sve2-sha3,sve2-sm4,sve2p1,tagged-globals,the,thunderx,thunderx2t99,thunderx3t110,thunderxt81,thunderxt83,thunderxt88,tlb-rmi,tme,tpidr-el1,tpidr-el2,tpidr-el3,tpidrro-el0,tracev8.4,trbe,tsv110,uaops,use-experimental-zeroing-pseudos,use-postra-scheduler,use-reciprocal-square-root,use-scalar-inc-vl,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8.7a,v8.8a,v8.9a,v8a,v8r,v9.1a,v9.2a,v9.3a,v9.4a,v9a,vh,wfxt,xs,zcm,zcz,zcz-fp-workaround,zcz-gp"),
+	str_lit("CONTEXTIDREL2,a35,a510,a520,a53,a55,a57,a64fx,a65,a710,a715,a72,a720,a73,a75,a76,a77,a78,a78c,addr-lsl-fast,aes,aggressive-fma,all,alternate-sextload-cvt-f32-pattern,altnzcv,alu-lsl-fast,am,ampere1,ampere1a,ampere1b,amvs,apple-a10,apple-a11,apple-a12,apple-a13,apple-a14,apple-a15,apple-a16,apple-a17,apple-a7,apple-a7-sysreg,arith-bcc-fusion,arith-cbz-fusion,ascend-store-address,b16b16,balance-fp-ops,bf16,brbe,bti,call-saved-x10,call-saved-x11,call-saved-x12,call-saved-x13,call-saved-x14,call-saved-x15,call-saved-x18,call-saved-x8,call-saved-x9,carmel,ccdp,ccidx,ccpp,chk,clrbhb,cmp-bcc-fusion,complxnum,cortex-r82,cortex-x1,cortex-x2,cortex-x3,cortex-x4,cpa,crc,crypto,cssc,d128,disable-latency-sched-heuristic,disable-ldp,disable-stp,dit,dotprod,ecv,el2vmsa,el3,enable-select-opt,ete,exynos-cheap-as-move,exynosm3,exynosm4,f32mm,f64mm,falkor,faminmax,fgt,fix-cortex-a53-835769,flagm,fmv,force-32bit-jump-tables,fp-armv8,fp16fml,fp8,fp8dot2,fp8dot4,fp8fma,fpmr,fptoint,fullfp16,fuse-address,fuse-addsub-2reg-const1,fuse-adrp-add,fuse-aes,fuse-arith-logic,fuse-crypto-eor,fuse-csel,fuse-literals,gcs,harden-sls-blr,harden-sls-nocomdat,harden-sls-retbr,hbc,hcx,i8mm,ite,jsconv,kryo,ldp-aligned-only,lor,ls64,lse,lse128,lse2,lut,mec,mops,mpam,mte,neon,neoverse512tvb,neoversee1,neoversen1,neoversen2,neoversev1,neoversev2,nmi,no-bti-at-return-twice,no-neg-immediates,no-sve-fp-ld1r,no-zcz-fp,nv,outline-atomics,pan,pan-rwv,pauth,pauth-lr,perfmon,predictable-select-expensive,predres,prfm-slc-target,rand,ras,rasv2,rcpc,rcpc-immo,rcpc3,rdm,reserve-x1,reserve-x10,reserve-x11,reserve-x12,reserve-x13,reserve-x14,reserve-x15,reserve-x18,reserve-x2,reserve-x20,reserve-x21,reserve-x22,reserve-x23,reserve-x24,reserve-x25,reserve-x26,reserve-x27,reserve-x28,reserve-x3,reserve-x30,reserve-x4,reserve-x5,reserve-x6,reserve-x7,reserve-x9,rme,saphira,sb,sel2,sha2,sha3,slow-misaligned-128store,slow-paired-128,slow-strqro-store,sm4,sme,sme-f16f16,sme-f64f64,sme-f8f16,sme-f8f32,sme-fa64,sme-i16i64,sme-lutv2,sme2,sme2p1,spe,spe-eef,specres2,specrestrict,ssbs,ssve-fp8dot2,ssve-fp8dot4,ssve-fp8fma,store-pair-suppress,stp-aligned-only,strict-align,sve,sve2,sve2-aes,sve2-bitperm,sve2-sha3,sve2-sm4,sve2p1,tagged-globals,the,thunderx,thunderx2t99,thunderx3t110,thunderxt81,thunderxt83,thunderxt88,tlb-rmi,tlbiw,tme,tpidr-el1,tpidr-el2,tpidr-el3,tpidrro-el0,tracev8.4,trbe,tsv110,uaops,use-experimental-zeroing-pseudos,use-postra-scheduler,use-reciprocal-square-root,use-scalar-inc-vl,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8.7a,v8.8a,v8.9a,v8a,v8r,v9.1a,v9.2a,v9.3a,v9.4a,v9.5a,v9a,vh,wfxt,xs,zcm,zcz,zcz-fp-workaround,zcz-gp"),
 	// TargetArch_wasm32:
-	str_lit("atomics,bulk-memory,exception-handling,extended-const,multivalue,mutable-globals,nontrapping-fptoint,reference-types,relaxed-simd,sign-ext,simd128,tail-call"),
+	str_lit("atomics,bulk-memory,exception-handling,extended-const,multimemory,multivalue,mutable-globals,nontrapping-fptoint,reference-types,relaxed-simd,sign-ext,simd128,tail-call"),
 	// TargetArch_wasm64p32:
-	str_lit("atomics,bulk-memory,exception-handling,extended-const,multivalue,mutable-globals,nontrapping-fptoint,reference-types,relaxed-simd,sign-ext,simd128,tail-call"),
+	str_lit("atomics,bulk-memory,exception-handling,extended-const,multimemory,multivalue,mutable-globals,nontrapping-fptoint,reference-types,relaxed-simd,sign-ext,simd128,tail-call"),
+	// TargetArch_riscv64:
+	str_lit("32bit,64bit,a,auipc-addi-fusion,c,conditional-cmv-fusion,d,dlen-factor-2,e,experimental,experimental-zacas,experimental-zcmop,experimental-zfbfmin,experimental-zicfilp,experimental-zicfiss,experimental-zimop,experimental-ztso,experimental-zvfbfmin,experimental-zvfbfwma,f,fast-unaligned-access,forced-atomics,h,i,ld-add-fusion,lui-addi-fusion,m,no-default-unroll,no-optimized-zero-stride-load,no-rvc-hints,relax,reserve-x1,reserve-x10,reserve-x11,reserve-x12,reserve-x13,reserve-x14,reserve-x15,reserve-x16,reserve-x17,reserve-x18,reserve-x19,reserve-x2,reserve-x20,reserve-x21,reserve-x22,reserve-x23,reserve-x24,reserve-x25,reserve-x26,reserve-x27,reserve-x28,reserve-x29,reserve-x3,reserve-x30,reserve-x31,reserve-x4,reserve-x5,reserve-x6,reserve-x7,reserve-x8,reserve-x9,save-restore,seq-cst-trailing-fence,shifted-zextw-fusion,short-forward-branch-opt,sifive7,smaia,smepmp,ssaia,svinval,svnapot,svpbmt,tagged-globals,unaligned-scalar-mem,use-postra-scheduler,v,ventana-veyron,xcvalu,xcvbi,xcvbitmanip,xcvelw,xcvmac,xcvmem,xcvsimd,xsfvcp,xsfvfnrclipxfqf,xsfvfwmaccqqq,xsfvqmaccdod,xsfvqmaccqoq,xtheadba,xtheadbb,xtheadbs,xtheadcmo,xtheadcondmov,xtheadfmemidx,xtheadmac,xtheadmemidx,xtheadmempair,xtheadsync,xtheadvdot,xventanacondops,za128rs,za64rs,zawrs,zba,zbb,zbc,zbkb,zbkc,zbkx,zbs,zca,zcb,zcd,zce,zcf,zcmp,zcmt,zdinx,zexth-fusion,zextw-fusion,zfa,zfh,zfhmin,zfinx,zhinx,zhinxmin,zic64b,zicbom,zicbop,zicboz,ziccamoa,ziccif,zicclsm,ziccrse,zicntr,zicond,zicsr,zifencei,zihintntl,zihintpause,zihpm,zk,zkn,zknd,zkne,zknh,zkr,zks,zksed,zksh,zkt,zmmul,zvbb,zvbc,zve32f,zve32x,zve64d,zve64f,zve64x,zvfh,zvfhmin,zvkb,zvkg,zvkn,zvknc,zvkned,zvkng,zvknha,zvknhb,zvks,zvksc,zvksed,zvksg,zvksh,zvkt,zvl1024b,zvl128b,zvl16384b,zvl2048b,zvl256b,zvl32768b,zvl32b,zvl4096b,zvl512b,zvl64b,zvl65536b,zvl8192b"),
 };
 
 // Generated with the featuregen script in `misc/featuregen`
@@ -39,17 +43,19 @@ gb_global int target_microarch_counts[TargetArch_COUNT] = {
 	// TargetArch_Invalid:
 	0,
 	// TargetArch_amd64:
-	120,
+	127,
 	// TargetArch_i386:
-	120,
+	127,
 	// TargetArch_arm32:
-	90,
+	91,
 	// TargetArch_arm64:
-	63,
+	69,
 	// TargetArch_wasm32:
 	3,
 	// TargetArch_wasm64p32:
 	3,
+	// TargetArch_riscv64:
+	26,
 };
 
 // Generated with the featuregen script in `misc/featuregen`
@@ -57,6 +63,9 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	// TargetArch_amd64:
 	{ str_lit("alderlake"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,avx,avx2,avxvnni,bmi,bmi2,cldemote,clflushopt,clwb,cmov,crc32,cx16,cx8,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("amdfam10"), str_lit("3dnow,3dnowa,64bit,64bit-mode,cmov,cx16,cx8,fast-scalar-shift-masks,fxsr,lzcnt,mmx,nopl,popcnt,prfchw,sahf,sbb-dep-breaking,slow-shld,sse,sse2,sse3,sse4a,vzeroupper,x87") },
+	{ str_lit("arrowlake"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
+	{ str_lit("arrowlake-s"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,sha512,shstk,slow-3ops-lea,sm3,sm4,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
+	{ str_lit("arrowlake_s"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,sha512,shstk,slow-3ops-lea,sm3,sm4,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("athlon"), str_lit("3dnow,3dnowa,64bit-mode,cmov,cx8,mmx,nopl,slow-shld,slow-unaligned-mem-16,sse,sse2,vzeroupper,x87") },
 	{ str_lit("athlon-4"), str_lit("3dnow,3dnowa,64bit-mode,cmov,cx8,fxsr,mmx,nopl,slow-shld,slow-unaligned-mem-16,sse,sse2,vzeroupper,x87") },
 	{ str_lit("athlon-fx"), str_lit("3dnow,3dnowa,64bit,64bit-mode,cmov,cx8,fast-scalar-shift-masks,fxsr,mmx,nopl,sbb-dep-breaking,slow-shld,slow-unaligned-mem-16,sse,sse2,vzeroupper,x87") },
@@ -81,6 +90,7 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("c3-2"), str_lit("64bit-mode,cmov,cx8,fxsr,mmx,slow-unaligned-mem-16,sse,sse2,vzeroupper,x87") },
 	{ str_lit("cannonlake"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,avx,avx2,avx512bw,avx512cd,avx512dq,avx512f,avx512ifma,avx512vbmi,avx512vl,bmi,bmi2,clflushopt,cmov,crc32,cx16,cx8,ermsb,evex512,f16c,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,idivq-to-divl,invpcid,lzcnt,macrofusion,mmx,movbe,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pku,popcnt,prefer-256-bit,prfchw,rdrnd,rdseed,sahf,sha,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,vzeroupper,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("cascadelake"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,avx,avx2,avx512bw,avx512cd,avx512dq,avx512f,avx512vl,avx512vnni,bmi,bmi2,clflushopt,clwb,cmov,crc32,cx16,cx8,ermsb,evex512,f16c,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,faster-shift-than-shuffle,fma,fsgsbase,fxsr,idivq-to-divl,invpcid,lzcnt,macrofusion,mmx,movbe,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pku,popcnt,prefer-256-bit,prfchw,rdrnd,rdseed,sahf,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,vzeroupper,x87,xsave,xsavec,xsaveopt,xsaves") },
+	{ str_lit("clearwaterforest"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prefetchi,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,sha512,shstk,slow-3ops-lea,sm3,sm4,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,uintr,usermsr,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("cooperlake"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,avx,avx2,avx512bf16,avx512bw,avx512cd,avx512dq,avx512f,avx512vl,avx512vnni,bmi,bmi2,clflushopt,clwb,cmov,crc32,cx16,cx8,ermsb,evex512,f16c,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,faster-shift-than-shuffle,fma,fsgsbase,fxsr,idivq-to-divl,invpcid,lzcnt,macrofusion,mmx,movbe,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pku,popcnt,prefer-256-bit,prfchw,rdrnd,rdseed,sahf,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,vzeroupper,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("core-avx-i"), str_lit("64bit,64bit-mode,avx,cmov,crc32,cx16,cx8,f16c,false-deps-popcnt,fast-15bytenop,fast-scalar-fsqrt,fast-shld-rotate,fsgsbase,fxsr,idivq-to-divl,macrofusion,mmx,no-bypass-delay-mov,nopl,pclmul,popcnt,rdrnd,sahf,slow-3ops-lea,slow-unaligned-mem-32,sse,sse2,sse3,sse4.1,sse4.2,ssse3,vzeroupper,x87,xsave,xsaveopt") },
 	{ str_lit("core-avx2"), str_lit("64bit,64bit-mode,allow-light-256-bit,avx,avx2,bmi,bmi2,cmov,crc32,cx16,cx8,ermsb,f16c,false-deps-lzcnt-tzcnt,false-deps-popcnt,fast-15bytenop,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fma,fsgsbase,fxsr,idivq-to-divl,invpcid,lzcnt,macrofusion,mmx,movbe,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,popcnt,rdrnd,sahf,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,vzeroupper,x87,xsave,xsaveopt") },
@@ -103,6 +113,7 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("goldmont"), str_lit("64bit,64bit-mode,aes,clflushopt,cmov,crc32,cx16,cx8,false-deps-popcnt,fast-movbe,fsgsbase,fxsr,mmx,movbe,no-bypass-delay,nopl,pclmul,popcnt,prfchw,rdrnd,rdseed,sahf,sha,slow-incdec,slow-lea,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,use-glm-div-sqrt-costs,vzeroupper,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("goldmont-plus"), str_lit("64bit,64bit-mode,aes,clflushopt,cmov,crc32,cx16,cx8,fast-movbe,fsgsbase,fxsr,mmx,movbe,no-bypass-delay,nopl,pclmul,popcnt,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,sha,slow-incdec,slow-lea,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,use-glm-div-sqrt-costs,vzeroupper,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("goldmont_plus"), str_lit("64bit,64bit-mode,aes,clflushopt,cmov,crc32,cx16,cx8,fast-movbe,fsgsbase,fxsr,mmx,movbe,no-bypass-delay,nopl,pclmul,popcnt,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,sha,slow-incdec,slow-lea,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,use-glm-div-sqrt-costs,vzeroupper,x87,xsave,xsavec,xsaveopt,xsaves") },
+	{ str_lit("gracemont"), str_lit("64bit,64bit-mode,adx,aes,avx,avx2,avxvnni,bmi,bmi2,cldemote,clflushopt,clwb,cmov,crc32,cx16,cx8,f16c,false-deps-popcnt,fast-15bytenop,fast-scalar-fsqrt,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivl-to-divb,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,nopl,pclmul,pconfig,pku,popcnt,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("grandridge"), str_lit("64bit,64bit-mode,adx,aes,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,fast-movbe,fma,fsgsbase,fxsr,gfni,hreset,invpcid,kl,lzcnt,mmx,movbe,movdir64b,movdiri,no-bypass-delay,nopl,pclmul,pconfig,pku,popcnt,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,slow-incdec,slow-lea,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,uintr,use-glm-div-sqrt-costs,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("graniterapids"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,amx-bf16,amx-fp16,amx-int8,amx-tile,avx,avx2,avx512bf16,avx512bitalg,avx512bw,avx512cd,avx512dq,avx512f,avx512fp16,avx512ifma,avx512vbmi,avx512vbmi2,avx512vl,avx512vnni,avx512vpopcntdq,avxvnni,bmi,bmi2,cldemote,clflushopt,clwb,cmov,crc32,cx16,cx8,enqcmd,ermsb,evex512,f16c,false-deps-getmant,false-deps-mulc,false-deps-mullq,false-deps-perm,false-deps-range,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fsrm,fxsr,gfni,idivq-to-divl,invpcid,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-256-bit,prefetchi,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tsxldtrk,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,wbnoinvd,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("graniterapids-d"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,amx-bf16,amx-complex,amx-fp16,amx-int8,amx-tile,avx,avx2,avx512bf16,avx512bitalg,avx512bw,avx512cd,avx512dq,avx512f,avx512fp16,avx512ifma,avx512vbmi,avx512vbmi2,avx512vl,avx512vnni,avx512vpopcntdq,avxvnni,bmi,bmi2,cldemote,clflushopt,clwb,cmov,crc32,cx16,cx8,enqcmd,ermsb,evex512,f16c,false-deps-getmant,false-deps-mulc,false-deps-mullq,false-deps-perm,false-deps-range,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fsrm,fxsr,gfni,idivq-to-divl,invpcid,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-256-bit,prefetchi,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tsxldtrk,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,wbnoinvd,x87,xsave,xsavec,xsaveopt,xsaves") },
@@ -125,12 +136,14 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("knl"), str_lit("64bit,64bit-mode,adx,aes,avx,avx2,avx512cd,avx512er,avx512f,avx512pf,bmi,bmi2,cmov,crc32,cx16,cx8,evex512,f16c,fast-gather,fast-movbe,fma,fsgsbase,fxsr,idivq-to-divl,lzcnt,mmx,movbe,nopl,pclmul,popcnt,prefer-mask-registers,prefetchwt1,prfchw,rdrnd,rdseed,sahf,slow-3ops-lea,slow-incdec,slow-pmaddwd,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,x87,xsave,xsaveopt") },
 	{ str_lit("knm"), str_lit("64bit,64bit-mode,adx,aes,avx,avx2,avx512cd,avx512er,avx512f,avx512pf,avx512vpopcntdq,bmi,bmi2,cmov,crc32,cx16,cx8,evex512,f16c,fast-gather,fast-movbe,fma,fsgsbase,fxsr,idivq-to-divl,lzcnt,mmx,movbe,nopl,pclmul,popcnt,prefer-mask-registers,prefetchwt1,prfchw,rdrnd,rdseed,sahf,slow-3ops-lea,slow-incdec,slow-pmaddwd,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,x87,xsave,xsaveopt") },
 	{ str_lit("lakemont"), str_lit("64bit-mode,cx8,slow-unaligned-mem-16,sse,sse2,vzeroupper") },
+	{ str_lit("lunarlake"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,sha512,shstk,slow-3ops-lea,sm3,sm4,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("meteorlake"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,avx,avx2,avxvnni,bmi,bmi2,cldemote,clflushopt,clwb,cmov,crc32,cx16,cx8,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("mic_avx512"), str_lit("64bit,64bit-mode,adx,aes,avx,avx2,avx512cd,avx512er,avx512f,avx512pf,bmi,bmi2,cmov,crc32,cx16,cx8,evex512,f16c,fast-gather,fast-movbe,fma,fsgsbase,fxsr,idivq-to-divl,lzcnt,mmx,movbe,nopl,pclmul,popcnt,prefer-mask-registers,prefetchwt1,prfchw,rdrnd,rdseed,sahf,slow-3ops-lea,slow-incdec,slow-pmaddwd,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,x87,xsave,xsaveopt") },
 	{ str_lit("nehalem"), str_lit("64bit,64bit-mode,cmov,crc32,cx16,cx8,fxsr,macrofusion,mmx,no-bypass-delay-mov,nopl,popcnt,sahf,sse,sse2,sse3,sse4.1,sse4.2,ssse3,vzeroupper,x87") },
 	{ str_lit("nocona"), str_lit("64bit,64bit-mode,cmov,cx16,cx8,fxsr,mmx,nopl,slow-unaligned-mem-16,sse,sse2,sse3,vzeroupper,x87") },
 	{ str_lit("opteron"), str_lit("3dnow,3dnowa,64bit,64bit-mode,cmov,cx8,fast-scalar-shift-masks,fxsr,mmx,nopl,sbb-dep-breaking,slow-shld,slow-unaligned-mem-16,sse,sse2,vzeroupper,x87") },
 	{ str_lit("opteron-sse3"), str_lit("3dnow,3dnowa,64bit,64bit-mode,cmov,cx16,cx8,fast-scalar-shift-masks,fxsr,mmx,nopl,sbb-dep-breaking,slow-shld,slow-unaligned-mem-16,sse,sse2,sse3,vzeroupper,x87") },
+	{ str_lit("pantherlake"), str_lit("64bit,64bit-mode,adx,aes,allow-light-256-bit,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prefetchi,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,sha512,shstk,slow-3ops-lea,sm3,sm4,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("penryn"), str_lit("64bit,64bit-mode,cmov,cx16,cx8,fxsr,macrofusion,mmx,nopl,sahf,slow-unaligned-mem-16,sse,sse2,sse3,sse4.1,ssse3,vzeroupper,x87") },
 	{ str_lit("pentium"), str_lit("64bit-mode,cx8,slow-unaligned-mem-16,sse,sse2,vzeroupper,x87") },
 	{ str_lit("pentium-m"), str_lit("64bit-mode,cmov,cx8,fxsr,mmx,nopl,slow-unaligned-mem-16,sse,sse2,vzeroupper,x87") },
@@ -178,6 +191,9 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	// TargetArch_i386:
 	{ str_lit("alderlake"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,avx,avx2,avxvnni,bmi,bmi2,cldemote,clflushopt,clwb,cmov,crc32,cx16,cx8,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("amdfam10"), str_lit("32bit-mode,3dnow,3dnowa,64bit,cmov,cx16,cx8,fast-scalar-shift-masks,fxsr,lzcnt,mmx,nopl,popcnt,prfchw,sahf,sbb-dep-breaking,slow-shld,sse,sse2,sse3,sse4a,vzeroupper,x87") },
+	{ str_lit("arrowlake"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
+	{ str_lit("arrowlake-s"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,sha512,shstk,slow-3ops-lea,sm3,sm4,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
+	{ str_lit("arrowlake_s"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,sha512,shstk,slow-3ops-lea,sm3,sm4,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("athlon"), str_lit("32bit-mode,3dnow,3dnowa,cmov,cx8,mmx,nopl,slow-shld,slow-unaligned-mem-16,vzeroupper,x87") },
 	{ str_lit("athlon-4"), str_lit("32bit-mode,3dnow,3dnowa,cmov,cx8,fxsr,mmx,nopl,slow-shld,slow-unaligned-mem-16,sse,vzeroupper,x87") },
 	{ str_lit("athlon-fx"), str_lit("32bit-mode,3dnow,3dnowa,64bit,cmov,cx8,fast-scalar-shift-masks,fxsr,mmx,nopl,sbb-dep-breaking,slow-shld,slow-unaligned-mem-16,sse,sse2,vzeroupper,x87") },
@@ -202,6 +218,7 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("c3-2"), str_lit("32bit-mode,cmov,cx8,fxsr,mmx,slow-unaligned-mem-16,sse,vzeroupper,x87") },
 	{ str_lit("cannonlake"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,avx,avx2,avx512bw,avx512cd,avx512dq,avx512f,avx512ifma,avx512vbmi,avx512vl,bmi,bmi2,clflushopt,cmov,crc32,cx16,cx8,ermsb,evex512,f16c,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,idivq-to-divl,invpcid,lzcnt,macrofusion,mmx,movbe,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pku,popcnt,prefer-256-bit,prfchw,rdrnd,rdseed,sahf,sha,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,vzeroupper,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("cascadelake"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,avx,avx2,avx512bw,avx512cd,avx512dq,avx512f,avx512vl,avx512vnni,bmi,bmi2,clflushopt,clwb,cmov,crc32,cx16,cx8,ermsb,evex512,f16c,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,faster-shift-than-shuffle,fma,fsgsbase,fxsr,idivq-to-divl,invpcid,lzcnt,macrofusion,mmx,movbe,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pku,popcnt,prefer-256-bit,prfchw,rdrnd,rdseed,sahf,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,vzeroupper,x87,xsave,xsavec,xsaveopt,xsaves") },
+	{ str_lit("clearwaterforest"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prefetchi,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,sha512,shstk,slow-3ops-lea,sm3,sm4,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,uintr,usermsr,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("cooperlake"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,avx,avx2,avx512bf16,avx512bw,avx512cd,avx512dq,avx512f,avx512vl,avx512vnni,bmi,bmi2,clflushopt,clwb,cmov,crc32,cx16,cx8,ermsb,evex512,f16c,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,faster-shift-than-shuffle,fma,fsgsbase,fxsr,idivq-to-divl,invpcid,lzcnt,macrofusion,mmx,movbe,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pku,popcnt,prefer-256-bit,prfchw,rdrnd,rdseed,sahf,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,vzeroupper,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("core-avx-i"), str_lit("32bit-mode,64bit,avx,cmov,crc32,cx16,cx8,f16c,false-deps-popcnt,fast-15bytenop,fast-scalar-fsqrt,fast-shld-rotate,fsgsbase,fxsr,idivq-to-divl,macrofusion,mmx,no-bypass-delay-mov,nopl,pclmul,popcnt,rdrnd,sahf,slow-3ops-lea,slow-unaligned-mem-32,sse,sse2,sse3,sse4.1,sse4.2,ssse3,vzeroupper,x87,xsave,xsaveopt") },
 	{ str_lit("core-avx2"), str_lit("32bit-mode,64bit,allow-light-256-bit,avx,avx2,bmi,bmi2,cmov,crc32,cx16,cx8,ermsb,f16c,false-deps-lzcnt-tzcnt,false-deps-popcnt,fast-15bytenop,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fma,fsgsbase,fxsr,idivq-to-divl,invpcid,lzcnt,macrofusion,mmx,movbe,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,popcnt,rdrnd,sahf,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,vzeroupper,x87,xsave,xsaveopt") },
@@ -224,6 +241,7 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("goldmont"), str_lit("32bit-mode,64bit,aes,clflushopt,cmov,crc32,cx16,cx8,false-deps-popcnt,fast-movbe,fsgsbase,fxsr,mmx,movbe,no-bypass-delay,nopl,pclmul,popcnt,prfchw,rdrnd,rdseed,sahf,sha,slow-incdec,slow-lea,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,use-glm-div-sqrt-costs,vzeroupper,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("goldmont-plus"), str_lit("32bit-mode,64bit,aes,clflushopt,cmov,crc32,cx16,cx8,fast-movbe,fsgsbase,fxsr,mmx,movbe,no-bypass-delay,nopl,pclmul,popcnt,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,sha,slow-incdec,slow-lea,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,use-glm-div-sqrt-costs,vzeroupper,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("goldmont_plus"), str_lit("32bit-mode,64bit,aes,clflushopt,cmov,crc32,cx16,cx8,fast-movbe,fsgsbase,fxsr,mmx,movbe,no-bypass-delay,nopl,pclmul,popcnt,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,sha,slow-incdec,slow-lea,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,use-glm-div-sqrt-costs,vzeroupper,x87,xsave,xsavec,xsaveopt,xsaves") },
+	{ str_lit("gracemont"), str_lit("32bit-mode,64bit,adx,aes,avx,avx2,avxvnni,bmi,bmi2,cldemote,clflushopt,clwb,cmov,crc32,cx16,cx8,f16c,false-deps-popcnt,fast-15bytenop,fast-scalar-fsqrt,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivl-to-divb,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,nopl,pclmul,pconfig,pku,popcnt,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("grandridge"), str_lit("32bit-mode,64bit,adx,aes,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,fast-movbe,fma,fsgsbase,fxsr,gfni,hreset,invpcid,kl,lzcnt,mmx,movbe,movdir64b,movdiri,no-bypass-delay,nopl,pclmul,pconfig,pku,popcnt,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,slow-incdec,slow-lea,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,uintr,use-glm-div-sqrt-costs,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("graniterapids"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,amx-bf16,amx-fp16,amx-int8,amx-tile,avx,avx2,avx512bf16,avx512bitalg,avx512bw,avx512cd,avx512dq,avx512f,avx512fp16,avx512ifma,avx512vbmi,avx512vbmi2,avx512vl,avx512vnni,avx512vpopcntdq,avxvnni,bmi,bmi2,cldemote,clflushopt,clwb,cmov,crc32,cx16,cx8,enqcmd,ermsb,evex512,f16c,false-deps-getmant,false-deps-mulc,false-deps-mullq,false-deps-perm,false-deps-range,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fsrm,fxsr,gfni,idivq-to-divl,invpcid,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-256-bit,prefetchi,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tsxldtrk,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,wbnoinvd,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("graniterapids-d"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,amx-bf16,amx-complex,amx-fp16,amx-int8,amx-tile,avx,avx2,avx512bf16,avx512bitalg,avx512bw,avx512cd,avx512dq,avx512f,avx512fp16,avx512ifma,avx512vbmi,avx512vbmi2,avx512vl,avx512vnni,avx512vpopcntdq,avxvnni,bmi,bmi2,cldemote,clflushopt,clwb,cmov,crc32,cx16,cx8,enqcmd,ermsb,evex512,f16c,false-deps-getmant,false-deps-mulc,false-deps-mullq,false-deps-perm,false-deps-range,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fsrm,fxsr,gfni,idivq-to-divl,invpcid,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-256-bit,prefetchi,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tsxldtrk,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,wbnoinvd,x87,xsave,xsavec,xsaveopt,xsaves") },
@@ -246,12 +264,14 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("knl"), str_lit("32bit-mode,64bit,adx,aes,avx,avx2,avx512cd,avx512er,avx512f,avx512pf,bmi,bmi2,cmov,crc32,cx16,cx8,evex512,f16c,fast-gather,fast-movbe,fma,fsgsbase,fxsr,idivq-to-divl,lzcnt,mmx,movbe,nopl,pclmul,popcnt,prefer-mask-registers,prefetchwt1,prfchw,rdrnd,rdseed,sahf,slow-3ops-lea,slow-incdec,slow-pmaddwd,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,x87,xsave,xsaveopt") },
 	{ str_lit("knm"), str_lit("32bit-mode,64bit,adx,aes,avx,avx2,avx512cd,avx512er,avx512f,avx512pf,avx512vpopcntdq,bmi,bmi2,cmov,crc32,cx16,cx8,evex512,f16c,fast-gather,fast-movbe,fma,fsgsbase,fxsr,idivq-to-divl,lzcnt,mmx,movbe,nopl,pclmul,popcnt,prefer-mask-registers,prefetchwt1,prfchw,rdrnd,rdseed,sahf,slow-3ops-lea,slow-incdec,slow-pmaddwd,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,x87,xsave,xsaveopt") },
 	{ str_lit("lakemont"), str_lit("32bit-mode,cx8,slow-unaligned-mem-16,vzeroupper") },
+	{ str_lit("lunarlake"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,sha512,shstk,slow-3ops-lea,sm3,sm4,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("meteorlake"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,avx,avx2,avxvnni,bmi,bmi2,cldemote,clflushopt,clwb,cmov,crc32,cx16,cx8,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,shstk,slow-3ops-lea,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("mic_avx512"), str_lit("32bit-mode,64bit,adx,aes,avx,avx2,avx512cd,avx512er,avx512f,avx512pf,bmi,bmi2,cmov,crc32,cx16,cx8,evex512,f16c,fast-gather,fast-movbe,fma,fsgsbase,fxsr,idivq-to-divl,lzcnt,mmx,movbe,nopl,pclmul,popcnt,prefer-mask-registers,prefetchwt1,prfchw,rdrnd,rdseed,sahf,slow-3ops-lea,slow-incdec,slow-pmaddwd,slow-two-mem-ops,sse,sse2,sse3,sse4.1,sse4.2,ssse3,x87,xsave,xsaveopt") },
 	{ str_lit("nehalem"), str_lit("32bit-mode,64bit,cmov,crc32,cx16,cx8,fxsr,macrofusion,mmx,no-bypass-delay-mov,nopl,popcnt,sahf,sse,sse2,sse3,sse4.1,sse4.2,ssse3,vzeroupper,x87") },
 	{ str_lit("nocona"), str_lit("32bit-mode,64bit,cmov,cx16,cx8,fxsr,mmx,nopl,slow-unaligned-mem-16,sse,sse2,sse3,vzeroupper,x87") },
 	{ str_lit("opteron"), str_lit("32bit-mode,3dnow,3dnowa,64bit,cmov,cx8,fast-scalar-shift-masks,fxsr,mmx,nopl,sbb-dep-breaking,slow-shld,slow-unaligned-mem-16,sse,sse2,vzeroupper,x87") },
 	{ str_lit("opteron-sse3"), str_lit("32bit-mode,3dnow,3dnowa,64bit,cmov,cx16,cx8,fast-scalar-shift-masks,fxsr,mmx,nopl,sbb-dep-breaking,slow-shld,slow-unaligned-mem-16,sse,sse2,sse3,vzeroupper,x87") },
+	{ str_lit("pantherlake"), str_lit("32bit-mode,64bit,adx,aes,allow-light-256-bit,avx,avx2,avxifma,avxneconvert,avxvnni,avxvnniint16,avxvnniint8,bmi,bmi2,cldemote,clflushopt,clwb,cmov,cmpccxadd,crc32,cx16,cx8,enqcmd,f16c,false-deps-perm,false-deps-popcnt,fast-15bytenop,fast-gather,fast-scalar-fsqrt,fast-shld-rotate,fast-variable-crosslane-shuffle,fast-variable-perlane-shuffle,fast-vector-fsqrt,fma,fsgsbase,fxsr,gfni,hreset,idivq-to-divl,invpcid,kl,lzcnt,macrofusion,mmx,movbe,movdir64b,movdiri,no-bypass-delay-blend,no-bypass-delay-mov,no-bypass-delay-shuffle,nopl,pclmul,pconfig,pku,popcnt,prefer-movmsk-over-vtest,prefetchi,prfchw,ptwrite,rdpid,rdrnd,rdseed,sahf,serialize,sha,sha512,shstk,slow-3ops-lea,sm3,sm4,sse,sse2,sse3,sse4.1,sse4.2,ssse3,tuning-fast-imm-vector-shift,uintr,vaes,vpclmulqdq,vzeroupper,waitpkg,widekl,x87,xsave,xsavec,xsaveopt,xsaves") },
 	{ str_lit("penryn"), str_lit("32bit-mode,64bit,cmov,cx16,cx8,fxsr,macrofusion,mmx,nopl,sahf,slow-unaligned-mem-16,sse,sse2,sse3,sse4.1,ssse3,vzeroupper,x87") },
 	{ str_lit("pentium"), str_lit("32bit-mode,cx8,slow-unaligned-mem-16,vzeroupper,x87") },
 	{ str_lit("pentium-m"), str_lit("32bit-mode,cmov,cx8,fxsr,mmx,nopl,slow-unaligned-mem-16,sse,sse2,vzeroupper,x87") },
@@ -325,16 +345,16 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("arm968e-s"), str_lit("armv5te,v4t,v5t,v5te") },
 	{ str_lit("arm9e"), str_lit("armv5te,v4t,v5t,v5te") },
 	{ str_lit("arm9tdmi"), str_lit("armv4t,v4t") },
-	{ str_lit("cortex-a12"), str_lit("a12,aclass,armv7-a,avoid-partial-cpsr,d32,db,dsp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,neon,perfmon,ret-addr-stack,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization,vmlx-forwarding") },
-	{ str_lit("cortex-a15"), str_lit("a15,aclass,armv7-a,avoid-partial-cpsr,d32,db,dont-widen-vmovs,dsp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,muxed-units,neon,perfmon,ret-addr-stack,splat-vfp-neon,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization,vldn-align") },
-	{ str_lit("cortex-a17"), str_lit("a17,aclass,armv7-a,avoid-partial-cpsr,d32,db,dsp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,neon,perfmon,ret-addr-stack,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization,vmlx-forwarding") },
+	{ str_lit("cortex-a12"), str_lit("a12,aclass,armv7-a,avoid-partial-cpsr,d32,db,dsp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,perfmon,ret-addr-stack,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization,vmlx-forwarding") },
+	{ str_lit("cortex-a15"), str_lit("a15,aclass,armv7-a,avoid-partial-cpsr,d32,db,dont-widen-vmovs,dsp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,muxed-units,perfmon,ret-addr-stack,splat-vfp-neon,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization,vldn-align") },
+	{ str_lit("cortex-a17"), str_lit("a17,aclass,armv7-a,avoid-partial-cpsr,d32,db,dsp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,perfmon,ret-addr-stack,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization,vmlx-forwarding") },
 	{ str_lit("cortex-a32"), str_lit("aclass,acquire-release,aes,armv8-a,crc,crypto,d32,db,dsp,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,neon,perfmon,sha2,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization") },
 	{ str_lit("cortex-a35"), str_lit("a35,aclass,acquire-release,aes,armv8-a,crc,crypto,d32,db,dsp,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,neon,perfmon,sha2,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization") },
-	{ str_lit("cortex-a5"), str_lit("a5,aclass,armv7-a,d32,db,dsp,fp16,fp64,fpregs,fpregs64,mp,neon,perfmon,ret-addr-stack,slow-fp-brcc,slowfpvfmx,slowfpvmlx,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,vmlx-forwarding") },
+	{ str_lit("cortex-a5"), str_lit("a5,aclass,armv7-a,d32,db,dsp,fp16,fp64,fpregs,fpregs64,mp,perfmon,ret-addr-stack,slow-fp-brcc,slowfpvfmx,slowfpvmlx,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,vmlx-forwarding") },
 	{ str_lit("cortex-a53"), str_lit("a53,aclass,acquire-release,aes,armv8-a,crc,crypto,d32,db,dsp,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp64,fpao,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,neon,perfmon,sha2,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization") },
 	{ str_lit("cortex-a55"), str_lit("a55,aclass,acquire-release,aes,armv8.2-a,crc,crypto,d32,db,dotprod,dsp,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,neon,perfmon,ras,sha2,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8.1a,v8.2a,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization") },
 	{ str_lit("cortex-a57"), str_lit("a57,aclass,acquire-release,aes,armv8-a,avoid-partial-cpsr,cheap-predicable-cpsr,crc,crypto,d32,db,dsp,fix-cortex-a57-aes-1742098,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp64,fpao,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,neon,perfmon,sha2,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization") },
-	{ str_lit("cortex-a7"), str_lit("a7,aclass,armv7-a,d32,db,dsp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,neon,perfmon,ret-addr-stack,slow-fp-brcc,slowfpvfmx,slowfpvmlx,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization,vmlx-forwarding,vmlx-hazards") },
+	{ str_lit("cortex-a7"), str_lit("a7,aclass,armv7-a,d32,db,dsp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,perfmon,ret-addr-stack,slow-fp-brcc,slowfpvfmx,slowfpvmlx,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization,vmlx-forwarding,vmlx-hazards") },
 	{ str_lit("cortex-a710"), str_lit("aclass,acquire-release,armv9-a,bf16,cortex-a710,crc,d32,db,dotprod,dsp,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp16fml,fp64,fpregs,fpregs16,fpregs64,fullfp16,hwdiv,hwdiv-arm,i8mm,mp,neon,perfmon,ras,sb,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8m,v9a,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization") },
 	{ str_lit("cortex-a72"), str_lit("a72,aclass,acquire-release,aes,armv8-a,crc,crypto,d32,db,dsp,fix-cortex-a57-aes-1742098,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,neon,perfmon,sha2,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization") },
 	{ str_lit("cortex-a73"), str_lit("a73,aclass,acquire-release,aes,armv8-a,crc,crypto,d32,db,dsp,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,neon,perfmon,sha2,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization") },
@@ -344,8 +364,8 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("cortex-a77"), str_lit("a77,aclass,acquire-release,aes,armv8.2-a,crc,crypto,d32,db,dotprod,dsp,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp64,fpregs,fpregs16,fpregs64,fullfp16,hwdiv,hwdiv-arm,mp,neon,perfmon,ras,sha2,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8.1a,v8.2a,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization") },
 	{ str_lit("cortex-a78"), str_lit("aclass,acquire-release,aes,armv8.2-a,cortex-a78,crc,crypto,d32,db,dotprod,dsp,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp64,fpregs,fpregs16,fpregs64,fullfp16,hwdiv,hwdiv-arm,mp,neon,perfmon,ras,sha2,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8.1a,v8.2a,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization") },
 	{ str_lit("cortex-a78c"), str_lit("a78c,aclass,acquire-release,aes,armv8.2-a,crc,crypto,d32,db,dotprod,dsp,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp64,fpregs,fpregs16,fpregs64,fullfp16,hwdiv,hwdiv-arm,mp,neon,perfmon,ras,sha2,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8.1a,v8.2a,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization") },
-	{ str_lit("cortex-a8"), str_lit("a8,aclass,armv7-a,d32,db,dsp,fp64,fpregs,fpregs64,neon,nonpipelined-vfp,perfmon,ret-addr-stack,slow-fp-brcc,slowfpvfmx,slowfpvmlx,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vmlx-forwarding,vmlx-hazards") },
-	{ str_lit("cortex-a9"), str_lit("a9,aclass,armv7-a,avoid-partial-cpsr,d32,db,dsp,expand-fp-mlx,fp16,fp64,fpregs,fpregs64,mp,muxed-units,neon,neon-fpmovs,perfmon,prefer-vmovsr,ret-addr-stack,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vldn-align,vmlx-forwarding,vmlx-hazards") },
+	{ str_lit("cortex-a8"), str_lit("a8,aclass,armv7-a,d32,db,dsp,fp64,fpregs,fpregs64,nonpipelined-vfp,perfmon,ret-addr-stack,slow-fp-brcc,slowfpvfmx,slowfpvmlx,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vmlx-forwarding,vmlx-hazards") },
+	{ str_lit("cortex-a9"), str_lit("a9,aclass,armv7-a,avoid-partial-cpsr,d32,db,dsp,expand-fp-mlx,fp16,fp64,fpregs,fpregs64,mp,muxed-units,neon-fpmovs,perfmon,prefer-vmovsr,ret-addr-stack,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vldn-align,vmlx-forwarding,vmlx-hazards") },
 	{ str_lit("cortex-m0"), str_lit("armv6-m,db,mclass,no-branch-predictor,noarm,strict-align,thumb-mode,v4t,v5t,v5te,v6,v6m") },
 	{ str_lit("cortex-m0plus"), str_lit("armv6-m,db,mclass,no-branch-predictor,noarm,strict-align,thumb-mode,v4t,v5t,v5te,v6,v6m") },
 	{ str_lit("cortex-m1"), str_lit("armv6-m,db,mclass,no-branch-predictor,noarm,strict-align,thumb-mode,v4t,v5t,v5te,v6,v6m") },
@@ -354,6 +374,7 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("cortex-m33"), str_lit("8msecext,acquire-release,armv8-m.main,db,dsp,fix-cmse-cve-2021-35465,fp-armv8d16sp,fp16,fpregs,hwdiv,loop-align,mclass,no-branch-predictor,noarm,slowfpvfmx,slowfpvmlx,thumb-mode,thumb2,use-misched,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,v8m.main,vfp2sp,vfp3d16sp,vfp4d16sp") },
 	{ str_lit("cortex-m35p"), str_lit("8msecext,acquire-release,armv8-m.main,db,dsp,fix-cmse-cve-2021-35465,fp-armv8d16sp,fp16,fpregs,hwdiv,loop-align,mclass,no-branch-predictor,noarm,slowfpvfmx,slowfpvmlx,thumb-mode,thumb2,use-misched,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,v8m.main,vfp2sp,vfp3d16sp,vfp4d16sp") },
 	{ str_lit("cortex-m4"), str_lit("armv7e-m,db,dsp,fp16,fpregs,hwdiv,loop-align,mclass,no-branch-predictor,noarm,slowfpvfmx,slowfpvmlx,thumb-mode,thumb2,use-misched,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2sp,vfp3d16sp,vfp4d16sp") },
+	{ str_lit("cortex-m52"), str_lit("8msecext,acquire-release,armv8.1-m.main,db,dsp,fp-armv8d16,fp-armv8d16sp,fp16,fp64,fpregs,fpregs16,fpregs64,fullfp16,hwdiv,lob,loop-align,mclass,mve,mve.fp,mve1beat,no-branch-predictor,noarm,pacbti,ras,slowfpvmlx,thumb-mode,thumb2,use-misched,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8.1m.main,v8m,v8m.main,vfp2,vfp2sp,vfp3d16,vfp3d16sp,vfp4d16,vfp4d16sp") },
 	{ str_lit("cortex-m55"), str_lit("8msecext,acquire-release,armv8.1-m.main,db,dsp,fix-cmse-cve-2021-35465,fp-armv8d16,fp-armv8d16sp,fp16,fp64,fpregs,fpregs16,fpregs64,fullfp16,hwdiv,lob,loop-align,mclass,mve,mve.fp,no-branch-predictor,noarm,ras,slowfpvmlx,thumb-mode,thumb2,use-misched,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8.1m.main,v8m,v8m.main,vfp2,vfp2sp,vfp3d16,vfp3d16sp,vfp4d16,vfp4d16sp") },
 	{ str_lit("cortex-m7"), str_lit("armv7e-m,db,dsp,fp-armv8d16,fp-armv8d16sp,fp16,fp64,fpregs,fpregs64,hwdiv,m7,mclass,noarm,thumb-mode,thumb2,use-mipipeliner,use-misched,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3d16,vfp3d16sp,vfp4d16,vfp4d16sp") },
 	{ str_lit("cortex-m85"), str_lit("8msecext,acquire-release,armv8.1-m.main,db,dsp,fp-armv8d16,fp-armv8d16sp,fp16,fp64,fpregs,fpregs16,fpregs64,fullfp16,hwdiv,lob,mclass,mve,mve.fp,noarm,pacbti,ras,thumb-mode,thumb2,use-misched,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8.1m.main,v8m,v8m.main,vfp2,vfp2sp,vfp3d16,vfp3d16sp,vfp4d16,vfp4d16sp") },
@@ -372,7 +393,7 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("exynos-m5"), str_lit("aclass,acquire-release,aes,armv8.2-a,crc,crypto,d32,db,dont-widen-vmovs,dotprod,dsp,expand-fp-mlx,exynos,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp64,fpregs,fpregs16,fpregs64,fullfp16,fuse-aes,fuse-literals,hwdiv,hwdiv-arm,mp,neon,perfmon,prof-unpr,ras,ret-addr-stack,sha2,slow-fp-brcc,slow-vdup32,slow-vgetlni32,slowfpvfmx,slowfpvmlx,splat-vfp-neon,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8.1a,v8.2a,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization,wide-stride-vfp,zcz") },
 	{ str_lit("generic"), str_lit("") },
 	{ str_lit("iwmmxt"), str_lit("armv5te,v4t,v5t,v5te") },
-	{ str_lit("krait"), str_lit("aclass,armv7-a,avoid-partial-cpsr,d32,db,dsp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,krait,muxed-units,neon,perfmon,ret-addr-stack,thumb2,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,vldn-align,vmlx-forwarding") },
+	{ str_lit("krait"), str_lit("aclass,armv7-a,avoid-partial-cpsr,d32,db,dsp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,krait,muxed-units,perfmon,ret-addr-stack,thumb2,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,vldn-align,vmlx-forwarding") },
 	{ str_lit("kryo"), str_lit("aclass,acquire-release,aes,armv8-a,crc,crypto,d32,db,dsp,fp-armv8,fp-armv8d16,fp-armv8d16sp,fp-armv8sp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,kryo,mp,neon,perfmon,sha2,thumb2,trustzone,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,virtualization") },
 	{ str_lit("mpcore"), str_lit("armv6k,fp64,fpregs,fpregs64,slowfpvmlx,v4t,v5t,v5te,v6,v6k,vfp2,vfp2sp") },
 	{ str_lit("mpcorenovfp"), str_lit("armv6k,v4t,v5t,v5te,v6,v6k") },
@@ -385,12 +406,13 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("strongarm110"), str_lit("armv4") },
 	{ str_lit("strongarm1100"), str_lit("armv4") },
 	{ str_lit("strongarm1110"), str_lit("armv4") },
-	{ str_lit("swift"), str_lit("aclass,armv7-a,avoid-movs-shop,avoid-partial-cpsr,d32,db,disable-postra-scheduler,dsp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,neon,neonfp,perfmon,prefer-ishst,prof-unpr,ret-addr-stack,slow-load-D-subreg,slow-odd-reg,slow-vdup32,slow-vgetlni32,slowfpvfmx,slowfpvmlx,swift,thumb2,use-misched,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,vmlx-hazards,wide-stride-vfp") },
+	{ str_lit("swift"), str_lit("aclass,armv7-a,avoid-movs-shop,avoid-partial-cpsr,d32,db,disable-postra-scheduler,dsp,fp16,fp64,fpregs,fpregs64,hwdiv,hwdiv-arm,mp,neonfp,perfmon,prefer-ishst,prof-unpr,ret-addr-stack,slow-load-D-subreg,slow-odd-reg,slow-vdup32,slow-vgetlni32,slowfpvfmx,slowfpvmlx,swift,thumb2,use-misched,v4t,v5t,v5te,v6,v6k,v6m,v6t2,v7,v7clrex,v8m,vfp2,vfp2sp,vfp3,vfp3d16,vfp3d16sp,vfp3sp,vfp4,vfp4d16,vfp4d16sp,vfp4sp,vmlx-hazards,wide-stride-vfp") },
 	{ str_lit("xscale"), str_lit("armv5te,v4t,v5t,v5te") },
 	// TargetArch_arm64:
 	{ str_lit("a64fx"), str_lit("CONTEXTIDREL2,a64fx,aggressive-fma,arith-bcc-fusion,ccpp,complxnum,crc,el2vmsa,el3,fp-armv8,fullfp16,lor,lse,neon,pan,pan-rwv,perfmon,predictable-select-expensive,ras,rdm,sha2,store-pair-suppress,sve,uaops,use-postra-scheduler,v8.1a,v8.2a,v8a,vh") },
 	{ str_lit("ampere1"), str_lit("CONTEXTIDREL2,addr-lsl-fast,aes,aggressive-fma,altnzcv,alu-lsl-fast,am,ampere1,amvs,arith-bcc-fusion,bf16,bti,ccdp,ccidx,ccpp,cmp-bcc-fusion,complxnum,crc,dit,dotprod,ecv,el2vmsa,el3,fgt,flagm,fp-armv8,fptoint,fuse-address,fuse-aes,fuse-literals,i8mm,jsconv,ldp-aligned-only,lor,lse,lse2,mpam,neon,nv,pan,pan-rwv,pauth,perfmon,predres,rand,ras,rcpc,rcpc-immo,rdm,sb,sel2,sha2,sha3,specrestrict,ssbs,store-pair-suppress,stp-aligned-only,tlb-rmi,tracev8.4,uaops,use-postra-scheduler,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8a,vh") },
 	{ str_lit("ampere1a"), str_lit("CONTEXTIDREL2,addr-lsl-fast,aes,aggressive-fma,altnzcv,alu-lsl-fast,am,ampere1a,amvs,arith-bcc-fusion,bf16,bti,ccdp,ccidx,ccpp,cmp-bcc-fusion,complxnum,crc,dit,dotprod,ecv,el2vmsa,el3,fgt,flagm,fp-armv8,fptoint,fuse-address,fuse-aes,fuse-literals,i8mm,jsconv,ldp-aligned-only,lor,lse,lse2,mpam,mte,neon,nv,pan,pan-rwv,pauth,perfmon,predres,rand,ras,rcpc,rcpc-immo,rdm,sb,sel2,sha2,sha3,sm4,specrestrict,ssbs,store-pair-suppress,stp-aligned-only,tlb-rmi,tracev8.4,uaops,use-postra-scheduler,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8a,vh") },
+	{ str_lit("ampere1b"), str_lit("CONTEXTIDREL2,addr-lsl-fast,aes,aggressive-fma,altnzcv,alu-lsl-fast,am,ampere1b,amvs,arith-bcc-fusion,bf16,bti,ccdp,ccidx,ccpp,cmp-bcc-fusion,complxnum,crc,cssc,dit,dotprod,ecv,el2vmsa,el3,enable-select-opt,fgt,flagm,fp-armv8,fptoint,fullfp16,fuse-address,fuse-adrp-add,fuse-aes,fuse-literals,hcx,i8mm,jsconv,ldp-aligned-only,lor,lse,lse2,mpam,mte,neon,nv,pan,pan-rwv,pauth,perfmon,predictable-select-expensive,predres,rand,ras,rcpc,rcpc-immo,rdm,sb,sel2,sha2,sha3,sm4,specrestrict,ssbs,store-pair-suppress,stp-aligned-only,tlb-rmi,tracev8.4,uaops,use-postra-scheduler,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8.7a,v8a,vh,wfxt,xs") },
 	{ str_lit("apple-a10"), str_lit("CONTEXTIDREL2,aes,alternate-sextload-cvt-f32-pattern,apple-a10,arith-bcc-fusion,arith-cbz-fusion,crc,crypto,disable-latency-sched-heuristic,el2vmsa,el3,fp-armv8,fuse-aes,fuse-crypto-eor,lor,neon,pan,perfmon,rdm,sha2,store-pair-suppress,v8a,vh,zcm,zcz,zcz-gp") },
 	{ str_lit("apple-a11"), str_lit("CONTEXTIDREL2,aes,alternate-sextload-cvt-f32-pattern,apple-a11,arith-bcc-fusion,arith-cbz-fusion,ccpp,crc,crypto,disable-latency-sched-heuristic,el2vmsa,el3,fp-armv8,fullfp16,fuse-aes,fuse-crypto-eor,lor,lse,neon,pan,pan-rwv,perfmon,ras,rdm,sha2,store-pair-suppress,uaops,v8.1a,v8.2a,v8a,vh,zcm,zcz,zcz-gp") },
 	{ str_lit("apple-a12"), str_lit("CONTEXTIDREL2,aes,alternate-sextload-cvt-f32-pattern,apple-a12,arith-bcc-fusion,arith-cbz-fusion,ccidx,ccpp,complxnum,crc,crypto,disable-latency-sched-heuristic,el2vmsa,el3,fp-armv8,fullfp16,fuse-aes,fuse-crypto-eor,jsconv,lor,lse,neon,pan,pan-rwv,pauth,perfmon,ras,rcpc,rdm,sha2,store-pair-suppress,uaops,v8.1a,v8.2a,v8.3a,v8a,vh,zcm,zcz,zcz-gp") },
@@ -398,18 +420,21 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("apple-a14"), str_lit("CONTEXTIDREL2,aes,aggressive-fma,alternate-sextload-cvt-f32-pattern,altnzcv,am,apple-a14,arith-bcc-fusion,arith-cbz-fusion,ccdp,ccidx,ccpp,complxnum,crc,crypto,disable-latency-sched-heuristic,dit,dotprod,el2vmsa,el3,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-address,fuse-adrp-add,fuse-aes,fuse-arith-logic,fuse-crypto-eor,fuse-csel,fuse-literals,jsconv,lor,lse,lse2,mpam,neon,nv,pan,pan-rwv,pauth,perfmon,predres,ras,rcpc,rcpc-immo,rdm,sb,sel2,sha2,sha3,specrestrict,ssbs,store-pair-suppress,tlb-rmi,tracev8.4,uaops,v8.1a,v8.2a,v8.3a,v8.4a,v8a,vh,zcm,zcz,zcz-gp") },
 	{ str_lit("apple-a15"), str_lit("CONTEXTIDREL2,aes,alternate-sextload-cvt-f32-pattern,altnzcv,am,amvs,apple-a15,arith-bcc-fusion,arith-cbz-fusion,bf16,bti,ccdp,ccidx,ccpp,complxnum,crc,crypto,disable-latency-sched-heuristic,dit,dotprod,ecv,el2vmsa,el3,fgt,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-address,fuse-aes,fuse-arith-logic,fuse-crypto-eor,fuse-csel,fuse-literals,i8mm,jsconv,lor,lse,lse2,mpam,neon,nv,pan,pan-rwv,pauth,perfmon,predres,ras,rcpc,rcpc-immo,rdm,sb,sel2,sha2,sha3,specrestrict,ssbs,store-pair-suppress,tlb-rmi,tracev8.4,uaops,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8a,vh,zcm,zcz,zcz-gp") },
 	{ str_lit("apple-a16"), str_lit("CONTEXTIDREL2,aes,alternate-sextload-cvt-f32-pattern,altnzcv,am,amvs,apple-a16,arith-bcc-fusion,arith-cbz-fusion,bf16,bti,ccdp,ccidx,ccpp,complxnum,crc,crypto,disable-latency-sched-heuristic,dit,dotprod,ecv,el2vmsa,el3,fgt,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-address,fuse-aes,fuse-arith-logic,fuse-crypto-eor,fuse-csel,fuse-literals,hcx,i8mm,jsconv,lor,lse,lse2,mpam,neon,nv,pan,pan-rwv,pauth,perfmon,predres,ras,rcpc,rcpc-immo,rdm,sb,sel2,sha2,sha3,specrestrict,ssbs,store-pair-suppress,tlb-rmi,tracev8.4,uaops,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8a,vh,zcm,zcz,zcz-gp") },
+	{ str_lit("apple-a17"), str_lit("CONTEXTIDREL2,aes,alternate-sextload-cvt-f32-pattern,altnzcv,am,amvs,apple-a17,arith-bcc-fusion,arith-cbz-fusion,bf16,bti,ccdp,ccidx,ccpp,complxnum,crc,crypto,disable-latency-sched-heuristic,dit,dotprod,ecv,el2vmsa,el3,fgt,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-address,fuse-aes,fuse-arith-logic,fuse-crypto-eor,fuse-csel,fuse-literals,hcx,i8mm,jsconv,lor,lse,lse2,mpam,neon,nv,pan,pan-rwv,pauth,perfmon,predres,ras,rcpc,rcpc-immo,rdm,sb,sel2,sha2,sha3,specrestrict,ssbs,store-pair-suppress,tlb-rmi,tracev8.4,uaops,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8a,vh,zcm,zcz,zcz-gp") },
 	{ str_lit("apple-a7"), str_lit("aes,alternate-sextload-cvt-f32-pattern,apple-a7,apple-a7-sysreg,arith-bcc-fusion,arith-cbz-fusion,crypto,disable-latency-sched-heuristic,el2vmsa,el3,fp-armv8,fuse-aes,fuse-crypto-eor,neon,perfmon,sha2,store-pair-suppress,v8a,zcm,zcz,zcz-fp-workaround,zcz-gp") },
 	{ str_lit("apple-a8"), str_lit("aes,alternate-sextload-cvt-f32-pattern,apple-a7,apple-a7-sysreg,arith-bcc-fusion,arith-cbz-fusion,crypto,disable-latency-sched-heuristic,el2vmsa,el3,fp-armv8,fuse-aes,fuse-crypto-eor,neon,perfmon,sha2,store-pair-suppress,v8a,zcm,zcz,zcz-fp-workaround,zcz-gp") },
 	{ str_lit("apple-a9"), str_lit("aes,alternate-sextload-cvt-f32-pattern,apple-a7,apple-a7-sysreg,arith-bcc-fusion,arith-cbz-fusion,crypto,disable-latency-sched-heuristic,el2vmsa,el3,fp-armv8,fuse-aes,fuse-crypto-eor,neon,perfmon,sha2,store-pair-suppress,v8a,zcm,zcz,zcz-fp-workaround,zcz-gp") },
 	{ str_lit("apple-latest"), str_lit("CONTEXTIDREL2,aes,alternate-sextload-cvt-f32-pattern,altnzcv,am,amvs,apple-a16,arith-bcc-fusion,arith-cbz-fusion,bf16,bti,ccdp,ccidx,ccpp,complxnum,crc,crypto,disable-latency-sched-heuristic,dit,dotprod,ecv,el2vmsa,el3,fgt,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-address,fuse-aes,fuse-arith-logic,fuse-crypto-eor,fuse-csel,fuse-literals,hcx,i8mm,jsconv,lor,lse,lse2,mpam,neon,nv,pan,pan-rwv,pauth,perfmon,predres,ras,rcpc,rcpc-immo,rdm,sb,sel2,sha2,sha3,specrestrict,ssbs,store-pair-suppress,tlb-rmi,tracev8.4,uaops,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8a,vh,zcm,zcz,zcz-gp") },
 	{ str_lit("apple-m1"), str_lit("CONTEXTIDREL2,aes,aggressive-fma,alternate-sextload-cvt-f32-pattern,altnzcv,am,apple-a14,arith-bcc-fusion,arith-cbz-fusion,ccdp,ccidx,ccpp,complxnum,crc,crypto,disable-latency-sched-heuristic,dit,dotprod,el2vmsa,el3,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-address,fuse-adrp-add,fuse-aes,fuse-arith-logic,fuse-crypto-eor,fuse-csel,fuse-literals,jsconv,lor,lse,lse2,mpam,neon,nv,pan,pan-rwv,pauth,perfmon,predres,ras,rcpc,rcpc-immo,rdm,sb,sel2,sha2,sha3,specrestrict,ssbs,store-pair-suppress,tlb-rmi,tracev8.4,uaops,v8.1a,v8.2a,v8.3a,v8.4a,v8a,vh,zcm,zcz,zcz-gp") },
 	{ str_lit("apple-m2"), str_lit("CONTEXTIDREL2,aes,alternate-sextload-cvt-f32-pattern,altnzcv,am,amvs,apple-a15,arith-bcc-fusion,arith-cbz-fusion,bf16,bti,ccdp,ccidx,ccpp,complxnum,crc,crypto,disable-latency-sched-heuristic,dit,dotprod,ecv,el2vmsa,el3,fgt,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-address,fuse-aes,fuse-arith-logic,fuse-crypto-eor,fuse-csel,fuse-literals,i8mm,jsconv,lor,lse,lse2,mpam,neon,nv,pan,pan-rwv,pauth,perfmon,predres,ras,rcpc,rcpc-immo,rdm,sb,sel2,sha2,sha3,specrestrict,ssbs,store-pair-suppress,tlb-rmi,tracev8.4,uaops,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8a,vh,zcm,zcz,zcz-gp") },
+	{ str_lit("apple-m3"), str_lit("CONTEXTIDREL2,aes,alternate-sextload-cvt-f32-pattern,altnzcv,am,amvs,apple-a16,arith-bcc-fusion,arith-cbz-fusion,bf16,bti,ccdp,ccidx,ccpp,complxnum,crc,crypto,disable-latency-sched-heuristic,dit,dotprod,ecv,el2vmsa,el3,fgt,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-address,fuse-aes,fuse-arith-logic,fuse-crypto-eor,fuse-csel,fuse-literals,hcx,i8mm,jsconv,lor,lse,lse2,mpam,neon,nv,pan,pan-rwv,pauth,perfmon,predres,ras,rcpc,rcpc-immo,rdm,sb,sel2,sha2,sha3,specrestrict,ssbs,store-pair-suppress,tlb-rmi,tracev8.4,uaops,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8a,vh,zcm,zcz,zcz-gp") },
 	{ str_lit("apple-s4"), str_lit("CONTEXTIDREL2,aes,alternate-sextload-cvt-f32-pattern,apple-a12,arith-bcc-fusion,arith-cbz-fusion,ccidx,ccpp,complxnum,crc,crypto,disable-latency-sched-heuristic,el2vmsa,el3,fp-armv8,fullfp16,fuse-aes,fuse-crypto-eor,jsconv,lor,lse,neon,pan,pan-rwv,pauth,perfmon,ras,rcpc,rdm,sha2,store-pair-suppress,uaops,v8.1a,v8.2a,v8.3a,v8a,vh,zcm,zcz,zcz-gp") },
 	{ str_lit("apple-s5"), str_lit("CONTEXTIDREL2,aes,alternate-sextload-cvt-f32-pattern,apple-a12,arith-bcc-fusion,arith-cbz-fusion,ccidx,ccpp,complxnum,crc,crypto,disable-latency-sched-heuristic,el2vmsa,el3,fp-armv8,fullfp16,fuse-aes,fuse-crypto-eor,jsconv,lor,lse,neon,pan,pan-rwv,pauth,perfmon,ras,rcpc,rdm,sha2,store-pair-suppress,uaops,v8.1a,v8.2a,v8.3a,v8a,vh,zcm,zcz,zcz-gp") },
 	{ str_lit("carmel"), str_lit("CONTEXTIDREL2,aes,carmel,ccpp,crc,crypto,el2vmsa,el3,fp-armv8,fullfp16,lor,lse,neon,pan,pan-rwv,ras,rdm,sha2,uaops,v8.1a,v8.2a,v8a,vh") },
 	{ str_lit("cortex-a34"), str_lit("a35,aes,crc,crypto,el2vmsa,el3,fp-armv8,neon,perfmon,sha2,v8a") },
 	{ str_lit("cortex-a35"), str_lit("a35,aes,crc,crypto,el2vmsa,el3,fp-armv8,neon,perfmon,sha2,v8a") },
 	{ str_lit("cortex-a510"), str_lit("CONTEXTIDREL2,a510,altnzcv,am,bf16,bti,ccdp,ccidx,ccpp,complxnum,crc,dit,dotprod,el2vmsa,el3,ete,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-adrp-add,fuse-aes,i8mm,jsconv,lor,lse,lse2,mec,mpam,mte,neon,nv,pan,pan-rwv,pauth,perfmon,predres,ras,rcpc,rcpc-immo,rdm,rme,sb,sel2,specrestrict,ssbs,sve,sve2,sve2-bitperm,tlb-rmi,tracev8.4,trbe,uaops,use-postra-scheduler,use-scalar-inc-vl,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8a,v9a,vh") },
+	{ str_lit("cortex-a520"), str_lit("CONTEXTIDREL2,a520,altnzcv,am,amvs,bf16,bti,ccdp,ccidx,ccpp,complxnum,crc,dit,dotprod,ecv,el2vmsa,el3,ete,fgt,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-adrp-add,fuse-aes,hcx,i8mm,jsconv,lor,lse,lse2,mec,mpam,mte,neon,nv,pan,pan-rwv,pauth,perfmon,predres,ras,rcpc,rcpc-immo,rdm,rme,sb,sel2,specrestrict,ssbs,sve,sve2,sve2-bitperm,tlb-rmi,tracev8.4,trbe,uaops,use-postra-scheduler,use-scalar-inc-vl,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8.7a,v8a,v9.1a,v9.2a,v9a,vh,wfxt,xs") },
 	{ str_lit("cortex-a53"), str_lit("a53,aes,balance-fp-ops,crc,crypto,el2vmsa,el3,fp-armv8,fuse-adrp-add,fuse-aes,neon,perfmon,sha2,use-postra-scheduler,v8a") },
 	{ str_lit("cortex-a55"), str_lit("CONTEXTIDREL2,a55,aes,ccpp,crc,crypto,dotprod,el2vmsa,el3,fp-armv8,fullfp16,fuse-address,fuse-adrp-add,fuse-aes,lor,lse,neon,pan,pan-rwv,perfmon,ras,rcpc,rdm,sha2,uaops,use-postra-scheduler,v8.1a,v8.2a,v8a,vh") },
 	{ str_lit("cortex-a57"), str_lit("a57,aes,balance-fp-ops,crc,crypto,el2vmsa,el3,enable-select-opt,fp-armv8,fuse-adrp-add,fuse-aes,fuse-literals,neon,perfmon,predictable-select-expensive,sha2,use-postra-scheduler,v8a") },
@@ -418,6 +443,7 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("cortex-a710"), str_lit("CONTEXTIDREL2,a710,addr-lsl-fast,altnzcv,alu-lsl-fast,am,bf16,bti,ccdp,ccidx,ccpp,cmp-bcc-fusion,complxnum,crc,dit,dotprod,el2vmsa,el3,enable-select-opt,ete,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-adrp-add,fuse-aes,i8mm,jsconv,lor,lse,lse2,mec,mpam,mte,neon,nv,pan,pan-rwv,pauth,perfmon,predictable-select-expensive,predres,ras,rcpc,rcpc-immo,rdm,rme,sb,sel2,specrestrict,ssbs,sve,sve2,sve2-bitperm,tlb-rmi,tracev8.4,trbe,uaops,use-postra-scheduler,use-scalar-inc-vl,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8a,v9a,vh") },
 	{ str_lit("cortex-a715"), str_lit("CONTEXTIDREL2,a715,addr-lsl-fast,altnzcv,alu-lsl-fast,am,bf16,bti,ccdp,ccidx,ccpp,cmp-bcc-fusion,complxnum,crc,dit,dotprod,el2vmsa,el3,enable-select-opt,ete,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-adrp-add,fuse-aes,i8mm,jsconv,lor,lse,lse2,mec,mpam,mte,neon,nv,pan,pan-rwv,pauth,perfmon,predictable-select-expensive,predres,ras,rcpc,rcpc-immo,rdm,rme,sb,sel2,spe,specrestrict,ssbs,sve,sve2,sve2-bitperm,tlb-rmi,tracev8.4,trbe,uaops,use-postra-scheduler,use-scalar-inc-vl,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8a,v9a,vh") },
 	{ str_lit("cortex-a72"), str_lit("a72,aes,crc,crypto,el2vmsa,el3,enable-select-opt,fp-armv8,fuse-adrp-add,fuse-aes,fuse-literals,neon,perfmon,predictable-select-expensive,sha2,v8a") },
+	{ str_lit("cortex-a720"), str_lit("CONTEXTIDREL2,a720,addr-lsl-fast,altnzcv,alu-lsl-fast,am,amvs,bf16,bti,ccdp,ccidx,ccpp,cmp-bcc-fusion,complxnum,crc,dit,dotprod,ecv,el2vmsa,el3,enable-select-opt,ete,fgt,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-adrp-add,fuse-aes,hcx,i8mm,jsconv,lor,lse,lse2,mec,mpam,mte,neon,nv,pan,pan-rwv,pauth,perfmon,predictable-select-expensive,predres,ras,rcpc,rcpc-immo,rdm,rme,sb,sel2,spe,spe-eef,specrestrict,ssbs,sve,sve2,sve2-bitperm,tlb-rmi,tracev8.4,trbe,uaops,use-postra-scheduler,use-scalar-inc-vl,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8.7a,v8a,v9.1a,v9.2a,v9a,vh,wfxt,xs") },
 	{ str_lit("cortex-a73"), str_lit("a73,aes,crc,crypto,el2vmsa,el3,enable-select-opt,fp-armv8,fuse-adrp-add,fuse-aes,neon,perfmon,predictable-select-expensive,sha2,v8a") },
 	{ str_lit("cortex-a75"), str_lit("CONTEXTIDREL2,a75,aes,ccpp,crc,crypto,dotprod,el2vmsa,el3,enable-select-opt,fp-armv8,fullfp16,fuse-adrp-add,fuse-aes,lor,lse,neon,pan,pan-rwv,perfmon,predictable-select-expensive,ras,rcpc,rdm,sha2,uaops,v8.1a,v8.2a,v8a,vh") },
 	{ str_lit("cortex-a76"), str_lit("CONTEXTIDREL2,a76,addr-lsl-fast,aes,alu-lsl-fast,ccpp,crc,crypto,dotprod,el2vmsa,el3,enable-select-opt,fp-armv8,fullfp16,fuse-adrp-add,fuse-aes,lor,lse,neon,pan,pan-rwv,perfmon,predictable-select-expensive,ras,rcpc,rdm,sha2,ssbs,uaops,v8.1a,v8.2a,v8a,vh") },
@@ -430,6 +456,7 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("cortex-x1c"), str_lit("CONTEXTIDREL2,addr-lsl-fast,aes,alu-lsl-fast,ccpp,cmp-bcc-fusion,cortex-x1,crc,crypto,dotprod,el2vmsa,el3,enable-select-opt,flagm,fp-armv8,fullfp16,fuse-adrp-add,fuse-aes,lor,lse,lse2,neon,pan,pan-rwv,pauth,perfmon,predictable-select-expensive,ras,rcpc,rcpc-immo,rdm,sha2,spe,ssbs,uaops,use-postra-scheduler,v8.1a,v8.2a,v8a,vh") },
 	{ str_lit("cortex-x2"), str_lit("CONTEXTIDREL2,addr-lsl-fast,altnzcv,alu-lsl-fast,am,bf16,bti,ccdp,ccidx,ccpp,cmp-bcc-fusion,complxnum,cortex-x2,crc,dit,dotprod,el2vmsa,el3,enable-select-opt,ete,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-adrp-add,fuse-aes,i8mm,jsconv,lor,lse,lse2,mec,mpam,mte,neon,nv,pan,pan-rwv,pauth,perfmon,predictable-select-expensive,predres,ras,rcpc,rcpc-immo,rdm,rme,sb,sel2,specrestrict,ssbs,sve,sve2,sve2-bitperm,tlb-rmi,tracev8.4,trbe,uaops,use-postra-scheduler,use-scalar-inc-vl,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8a,v9a,vh") },
 	{ str_lit("cortex-x3"), str_lit("CONTEXTIDREL2,addr-lsl-fast,altnzcv,alu-lsl-fast,am,bf16,bti,ccdp,ccidx,ccpp,complxnum,cortex-x3,crc,dit,dotprod,el2vmsa,el3,enable-select-opt,ete,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-adrp-add,fuse-aes,i8mm,jsconv,lor,lse,lse2,mec,mpam,mte,neon,nv,pan,pan-rwv,pauth,perfmon,predictable-select-expensive,predres,ras,rcpc,rcpc-immo,rdm,rme,sb,sel2,spe,specrestrict,ssbs,sve,sve2,sve2-bitperm,tlb-rmi,tracev8.4,trbe,uaops,use-postra-scheduler,use-scalar-inc-vl,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8a,v9a,vh") },
+	{ str_lit("cortex-x4"), str_lit("CONTEXTIDREL2,addr-lsl-fast,altnzcv,alu-lsl-fast,am,amvs,bf16,bti,ccdp,ccidx,ccpp,complxnum,cortex-x4,crc,dit,dotprod,ecv,el2vmsa,el3,enable-select-opt,ete,fgt,flagm,fp-armv8,fp16fml,fptoint,fullfp16,fuse-adrp-add,fuse-aes,hcx,i8mm,jsconv,lor,lse,lse2,mec,mpam,mte,neon,nv,pan,pan-rwv,pauth,perfmon,predictable-select-expensive,predres,ras,rcpc,rcpc-immo,rdm,rme,sb,sel2,spe,spe-eef,specrestrict,ssbs,sve,sve2,sve2-bitperm,tlb-rmi,tracev8.4,trbe,uaops,use-postra-scheduler,use-scalar-inc-vl,v8.1a,v8.2a,v8.3a,v8.4a,v8.5a,v8.6a,v8.7a,v8a,v9.1a,v9.2a,v9a,vh,wfxt,xs") },
 	{ str_lit("cyclone"), str_lit("aes,alternate-sextload-cvt-f32-pattern,apple-a7,apple-a7-sysreg,arith-bcc-fusion,arith-cbz-fusion,crypto,disable-latency-sched-heuristic,el2vmsa,el3,fp-armv8,fuse-aes,fuse-crypto-eor,neon,perfmon,sha2,store-pair-suppress,v8a,zcm,zcz,zcz-fp-workaround,zcz-gp") },
 	{ str_lit("exynos-m3"), str_lit("addr-lsl-fast,aes,alu-lsl-fast,crc,crypto,el2vmsa,el3,exynos-cheap-as-move,exynosm3,force-32bit-jump-tables,fp-armv8,fuse-address,fuse-adrp-add,fuse-aes,fuse-csel,fuse-literals,neon,perfmon,predictable-select-expensive,sha2,store-pair-suppress,use-postra-scheduler,v8a") },
 	{ str_lit("exynos-m4"), str_lit("CONTEXTIDREL2,addr-lsl-fast,aes,alu-lsl-fast,arith-bcc-fusion,arith-cbz-fusion,ccpp,crc,crypto,dotprod,el2vmsa,el3,exynos-cheap-as-move,exynosm4,force-32bit-jump-tables,fp-armv8,fullfp16,fuse-address,fuse-adrp-add,fuse-aes,fuse-arith-logic,fuse-csel,fuse-literals,lor,lse,neon,pan,pan-rwv,perfmon,ras,rdm,sha2,store-pair-suppress,uaops,use-postra-scheduler,v8.1a,v8.2a,v8a,vh,zcz,zcz-gp") },
@@ -459,4 +486,31 @@ gb_global MicroarchFeatureList microarch_features_list[] = {
 	{ str_lit("bleeding-edge"), str_lit("atomics,bulk-memory,mutable-globals,nontrapping-fptoint,sign-ext,simd128,tail-call") },
 	{ str_lit("generic"), str_lit("mutable-globals,sign-ext") },
 	{ str_lit("mvp"), str_lit("") },
-};
\ No newline at end of file
+	// TargetArch_riscv64:
+	{ str_lit("generic"), str_lit("64bit") },
+	{ str_lit("generic-rv32"), str_lit("32bit") },
+	{ str_lit("generic-rv64"), str_lit("64bit") },
+	{ str_lit("rocket"), str_lit("") },
+	{ str_lit("rocket-rv32"), str_lit("32bit,zicsr,zifencei") },
+	{ str_lit("rocket-rv64"), str_lit("64bit,zicsr,zifencei") },
+	{ str_lit("sifive-7-series"), str_lit("no-default-unroll,short-forward-branch-opt,sifive7") },
+	{ str_lit("sifive-e20"), str_lit("32bit,c,m,zicsr,zifencei") },
+	{ str_lit("sifive-e21"), str_lit("32bit,a,c,m,zicsr,zifencei") },
+	{ str_lit("sifive-e24"), str_lit("32bit,a,c,f,m,zicsr,zifencei") },
+	{ str_lit("sifive-e31"), str_lit("32bit,a,c,m,zicsr,zifencei") },
+	{ str_lit("sifive-e34"), str_lit("32bit,a,c,f,m,zicsr,zifencei") },
+	{ str_lit("sifive-e76"), str_lit("32bit,a,c,f,m,no-default-unroll,short-forward-branch-opt,sifive7,zicsr,zifencei") },
+	{ str_lit("sifive-p450"), str_lit("64bit,a,auipc-addi-fusion,c,conditional-cmv-fusion,d,f,fast-unaligned-access,lui-addi-fusion,m,no-default-unroll,za64rs,zba,zbb,zbs,zfhmin,zic64b,zicbom,zicbop,zicboz,ziccamoa,ziccif,zicclsm,ziccrse,zicsr,zifencei,zihintntl,zihintpause,zihpm") },
+	{ str_lit("sifive-p670"), str_lit("64bit,a,auipc-addi-fusion,c,conditional-cmv-fusion,d,f,fast-unaligned-access,lui-addi-fusion,m,no-default-unroll,v,za64rs,zba,zbb,zbs,zfhmin,zic64b,zicbom,zicbop,zicboz,ziccamoa,ziccif,zicclsm,ziccrse,zicsr,zifencei,zihintntl,zihintpause,zihpm,zvbb,zvbc,zve32f,zve32x,zve64d,zve64f,zve64x,zvkb,zvkg,zvkn,zvknc,zvkned,zvkng,zvknhb,zvks,zvksc,zvksed,zvksg,zvksh,zvkt,zvl128b,zvl32b,zvl64b") },
+	{ str_lit("sifive-s21"), str_lit("64bit,a,c,m,zicsr,zifencei") },
+	{ str_lit("sifive-s51"), str_lit("64bit,a,c,m,zicsr,zifencei") },
+	{ str_lit("sifive-s54"), str_lit("64bit,a,c,d,f,m,zicsr,zifencei") },
+	{ str_lit("sifive-s76"), str_lit("64bit,a,c,d,f,m,no-default-unroll,short-forward-branch-opt,sifive7,zicsr,zifencei,zihintpause") },
+	{ str_lit("sifive-u54"), str_lit("64bit,a,c,d,f,m,zicsr,zifencei") },
+	{ str_lit("sifive-u74"), str_lit("64bit,a,c,d,f,m,no-default-unroll,short-forward-branch-opt,sifive7,zicsr,zifencei") },
+	{ str_lit("sifive-x280"), str_lit("64bit,a,c,d,dlen-factor-2,f,m,no-default-unroll,short-forward-branch-opt,sifive7,v,zba,zbb,zfh,zfhmin,zicsr,zifencei,zve32f,zve32x,zve64d,zve64f,zve64x,zvfh,zvfhmin,zvl128b,zvl256b,zvl32b,zvl512b,zvl64b") },
+	{ str_lit("syntacore-scr1-base"), str_lit("32bit,c,no-default-unroll,zicsr,zifencei") },
+	{ str_lit("syntacore-scr1-max"), str_lit("32bit,c,m,no-default-unroll,zicsr,zifencei") },
+	{ str_lit("veyron-v1"), str_lit("64bit,a,auipc-addi-fusion,c,d,f,ld-add-fusion,lui-addi-fusion,m,shifted-zextw-fusion,ventana-veyron,xventanacondops,zba,zbb,zbc,zbs,zexth-fusion,zextw-fusion,zicbom,zicbop,zicboz,zicntr,zicsr,zifencei,zihintpause,zihpm") },
+	{ str_lit("xiangshan-nanhu"), str_lit("64bit,a,c,d,f,m,svinval,zba,zbb,zbc,zbkb,zbkc,zbkx,zbs,zicbom,zicboz,zicsr,zifencei,zkn,zknd,zkne,zknh,zksed,zksh") },
+};
diff --git a/src/check_builtin.cpp b/src/check_builtin.cpp
index e5282f63e..1c4b88101 100644
--- a/src/check_builtin.cpp
+++ b/src/check_builtin.cpp
@@ -155,6 +155,11 @@ gb_internal bool does_require_msgSend_stret(Type *return_type) {
 		return false;
 	}
 
+	// No objc here so this doesn't matter, right?
+	if (build_context.metrics.arch == TargetArch_riscv64) {
+		return false;
+	}
+
 	// if (build_context.metrics.arch == TargetArch_arm32) {
 	// 	i64 struct_limit = type_size_of(t_uintptr);
 	// 	// NOTE(bill): This is technically wrong
diff --git a/src/checker.cpp b/src/checker.cpp
index c8eaf0acc..b24a7afdb 100644
--- a/src/checker.cpp
+++ b/src/checker.cpp
@@ -1039,6 +1039,7 @@ gb_internal void init_universal(void) {
 			{"arm64",     TargetArch_arm64},
 			{"wasm32",    TargetArch_wasm32},
 			{"wasm64p32", TargetArch_wasm64p32},
+			{"riscv64",   TargetArch_riscv64},
 		};
 
 		auto fields = add_global_enum_type(str_lit("Odin_Arch_Type"), values, gb_count_of(values));
diff --git a/src/linker.cpp b/src/linker.cpp
index 046e72d0e..faca28932 100644
--- a/src/linker.cpp
+++ b/src/linker.cpp
@@ -388,6 +388,12 @@ gb_internal i32 linker_stage(LinkerData *gen) {
 		} else {
 			timings_start_section(timings, str_lit("ld-link"));
 
+			// Link using `clang`, unless overridden by `ODIN_CLANG_PATH` environment variable.
+			const char* clang_path = gb_get_env("ODIN_CLANG_PATH", permanent_allocator());
+			if (clang_path == NULL) {
+				clang_path = "clang";
+			}
+
 			// NOTE(vassvik): get cwd, for used for local shared libs linking, since those have to be relative to the exe
 			char cwd[256];
 			#if !defined(GB_SYSTEM_WINDOWS)
@@ -458,7 +464,20 @@ gb_internal i32 linker_stage(LinkerData *gen) {
 						}
 					#endif // GB_ARCH_*_BIT
 
-						if (is_osx) {
+						if (build_context.metrics.arch == TargetArch_riscv64) {
+							result = system_exec_command_line_app("clang",
+								"%s \"%.*s\" "
+								"-c -o \"%.*s\" "
+								"-target %.*s -march=rv64gc "
+								"%.*s "
+								"",
+								clang_path,
+								LIT(asm_file),
+								LIT(obj_file),
+								LIT(build_context.metrics.target_triplet),
+								LIT(build_context.extra_assembler_flags)
+							);
+						} else if (is_osx) {
 							// `as` comes with MacOS.
 							result = system_exec_command_line_app("as",
 								"as \"%.*s\" "
@@ -592,7 +611,7 @@ gb_internal i32 linker_stage(LinkerData *gen) {
 					link_settings = gb_string_appendc(link_settings, "-Wl,-fini,'_odin_exit_point' ");
 				}
 
-			} else if (build_context.metrics.os != TargetOs_openbsd && build_context.metrics.os != TargetOs_haiku) {
+			} else if (build_context.metrics.os != TargetOs_openbsd && build_context.metrics.os != TargetOs_haiku && build_context.metrics.arch != TargetArch_riscv64) {
 				// OpenBSD and Haiku default to PIE executable. do not pass -no-pie for it.
 				link_settings = gb_string_appendc(link_settings, "-no-pie ");
 			}
@@ -635,12 +654,6 @@ gb_internal i32 linker_stage(LinkerData *gen) {
 				}
 			}
 
-			// Link using `clang`, unless overridden by `ODIN_CLANG_PATH` environment variable.
-			const char* clang_path = gb_get_env("ODIN_CLANG_PATH", permanent_allocator());
-			if (clang_path == NULL) {
-				clang_path = "clang";
-			}
-
 			gbString link_command_line = gb_string_make(heap_allocator(), clang_path);
 			defer (gb_string_free(link_command_line));
 
diff --git a/src/llvm_abi.cpp b/src/llvm_abi.cpp
index c21cd0a46..0837e40bf 100644
--- a/src/llvm_abi.cpp
+++ b/src/llvm_abi.cpp
@@ -332,7 +332,8 @@ gb_internal i64 lb_alignof(LLVMTypeRef type) {
 }
 
 
-#define LB_ABI_INFO(name) lbFunctionType *name(LLVMContextRef c, LLVMTypeRef *arg_types, unsigned arg_count, LLVMTypeRef return_type, bool return_is_defined, bool return_is_tuple, ProcCallingConvention calling_convention, Type *original_type)
+#define LB_ABI_INFO(name) lbFunctionType *name(lbModule *m, LLVMTypeRef *arg_types, unsigned arg_count, LLVMTypeRef return_type, bool return_is_defined, bool return_is_tuple, ProcCallingConvention calling_convention, Type *original_type)
+#define LB_ABI_INFO_CTX(name) lbFunctionType *name(LLVMContextRef c, LLVMTypeRef *arg_types, unsigned arg_count, LLVMTypeRef return_type, bool return_is_defined, bool return_is_tuple, ProcCallingConvention calling_convention, Type *original_type)
 typedef LB_ABI_INFO(lbAbiInfoType);
 
 #define LB_ABI_COMPUTE_RETURN_TYPE(name) lbArgType name(lbFunctionType *ft, LLVMContextRef c, LLVMTypeRef return_type, bool return_is_defined, bool return_is_tuple)
@@ -379,7 +380,7 @@ namespace lbAbi386 {
 	gb_internal Array<lbArgType> compute_arg_types(LLVMContextRef c, LLVMTypeRef *arg_types, unsigned arg_count);
 	gb_internal LB_ABI_COMPUTE_RETURN_TYPE(compute_return_type);
 
-	gb_internal LB_ABI_INFO(abi_info) {
+	gb_internal LB_ABI_INFO_CTX(abi_info) {
 		lbFunctionType *ft = gb_alloc_item(permanent_allocator(), lbFunctionType);
 		ft->ctx = c;
 		ft->args = compute_arg_types(c, arg_types, arg_count);
@@ -460,7 +461,7 @@ namespace lbAbiAmd64Win64 {
 	gb_internal Array<lbArgType> compute_arg_types(LLVMContextRef c, LLVMTypeRef *arg_types, unsigned arg_count);
 	gb_internal LB_ABI_COMPUTE_RETURN_TYPE(compute_return_type);
 
-	gb_internal LB_ABI_INFO(abi_info) {
+	gb_internal LB_ABI_INFO_CTX(abi_info) {
 		lbFunctionType *ft = gb_alloc_item(permanent_allocator(), lbFunctionType);
 		ft->ctx = c;
 		ft->args = compute_arg_types(c, arg_types, arg_count);
@@ -570,7 +571,7 @@ namespace lbAbiAmd64SysV {
 	gb_internal Array<RegClass> classify(LLVMTypeRef t);
 	gb_internal LLVMTypeRef llreg(LLVMContextRef c, Array<RegClass> const &reg_classes, LLVMTypeRef type);
 
-	gb_internal LB_ABI_INFO(abi_info) {
+	gb_internal LB_ABI_INFO_CTX(abi_info) {
 		lbFunctionType *ft = gb_alloc_item(permanent_allocator(), lbFunctionType);
 		ft->ctx = c;
 		ft->calling_convention = calling_convention;
@@ -1008,7 +1009,7 @@ namespace lbAbiArm64 {
 	gb_internal LB_ABI_COMPUTE_RETURN_TYPE(compute_return_type);
 	gb_internal bool is_homogenous_aggregate(LLVMContextRef c, LLVMTypeRef type, LLVMTypeRef *base_type_, unsigned *member_count_);
 
-	gb_internal LB_ABI_INFO(abi_info) {
+	gb_internal LB_ABI_INFO_CTX(abi_info) {
 		lbFunctionType *ft = gb_alloc_item(permanent_allocator(), lbFunctionType);
 		ft->ctx = c;
 		ft->args = compute_arg_types(c, arg_types, arg_count);
@@ -1242,7 +1243,7 @@ namespace lbAbiWasm {
 
 	enum {MAX_DIRECT_STRUCT_SIZE = 32};
 
-	gb_internal LB_ABI_INFO(abi_info) {
+	gb_internal LB_ABI_INFO_CTX(abi_info) {
 		lbFunctionType *ft = gb_alloc_item(permanent_allocator(), lbFunctionType);
 		ft->ctx = c;
 		ft->calling_convention = calling_convention;
@@ -1407,7 +1408,7 @@ namespace lbAbiArm32 {
 	gb_internal Array<lbArgType> compute_arg_types(LLVMContextRef c, LLVMTypeRef *arg_types, unsigned arg_count, ProcCallingConvention calling_convention);
 	gb_internal lbArgType compute_return_type(LLVMContextRef c, LLVMTypeRef return_type, bool return_is_defined);
 
-	gb_internal LB_ABI_INFO(abi_info) {
+	gb_internal LB_ABI_INFO_CTX(abi_info) {
 		lbFunctionType *ft = gb_alloc_item(permanent_allocator(), lbFunctionType);
 		ft->ctx = c;
 		ft->args = compute_arg_types(c, arg_types, arg_count, calling_convention);
@@ -1485,8 +1486,256 @@ namespace lbAbiArm32 {
 	}
 };
 
+namespace lbAbiRiscv64 {
+
+	gb_internal bool is_register(LLVMTypeRef type) {
+		LLVMTypeKind kind = LLVMGetTypeKind(type);
+		switch (kind) {
+		case LLVMIntegerTypeKind:
+		case LLVMHalfTypeKind:
+		case LLVMFloatTypeKind:
+		case LLVMDoubleTypeKind:
+		case LLVMPointerTypeKind:
+			return true;
+		}
+		return false;
+	}
+
+	gb_internal bool is_float(LLVMTypeRef type) {
+		LLVMTypeKind kind = LLVMGetTypeKind(type);
+		switch (kind) {
+		case LLVMHalfTypeKind:
+		case LLVMFloatTypeKind:
+		case LLVMDoubleTypeKind:
+			return true;
+		default:
+			return false;
+		}
+	}
+
+	gb_internal lbArgType non_struct(LLVMContextRef c, LLVMTypeRef type) {
+		LLVMAttributeRef attr = nullptr;
+		LLVMTypeRef i1 = LLVMInt1TypeInContext(c);
+		if (type == i1) {
+			attr = lb_create_enum_attribute(c, "zeroext");
+		}
+		return lb_arg_type_direct(type, nullptr, nullptr, attr);
+	}
+
+	gb_internal void flatten(lbModule *m, Array<LLVMTypeRef> *fields, LLVMTypeRef type, bool with_padding) {
+		LLVMTypeKind kind = LLVMGetTypeKind(type);
+		switch (kind) {
+		case LLVMStructTypeKind: {
+			if (LLVMIsPackedStruct(type)) {
+				array_add(fields, type);
+				break;
+			}
+
+			if (!with_padding) {
+				auto field_remapping = map_get(&m->struct_field_remapping, cast(void *)type);
+				if (field_remapping) {
+					auto remap = *field_remapping;
+					for_array(i, remap) {
+						flatten(m, fields, LLVMStructGetTypeAtIndex(type, remap[i]), with_padding);
+					}
+					break;
+				} else {
+					debugf("no field mapping for type: %s\n", LLVMPrintTypeToString(type));
+				}
+			}
+
+			unsigned elem_count = LLVMCountStructElementTypes(type);
+			for (unsigned i = 0; i < elem_count; i += 1) {
+				flatten(m, fields, LLVMStructGetTypeAtIndex(type, i), with_padding);
+			}
+			break;
+		}
+		case LLVMArrayTypeKind: {
+			unsigned len     = LLVMGetArrayLength(type);
+			LLVMTypeRef elem = OdinLLVMGetArrayElementType(type);
+			for (unsigned i = 0; i < len; i += 1) {
+				flatten(m, fields, elem, with_padding);
+			}
+			break;
+		}
+		default:
+			array_add(fields, type);
+		}
+	}
+
+	gb_internal lbArgType compute_arg_type(lbModule *m, LLVMTypeRef type, int *gprs_left, int *fprs_left, Type *odin_type) {
+		LLVMContextRef c = m->ctx;
+
+		int xlen = 8; // 8 byte int register size for riscv64.
+
+		// NOTE: we are requiring both of these to be enabled so we can just hard-code 8.
+		// int flen = 0;
+		// if (check_target_feature_is_enabled(str_lit("d"), nullptr)) {
+		// 	flen = 8; // Double precision floats are enabled.
+		// } else if (check_target_feature_is_enabled(str_lit("f"), nullptr)) {
+		// 	flen = 4; // Single precision floats are enabled.
+		// }
+		int flen = 8;
+
+		LLVMTypeKind kind = LLVMGetTypeKind(type);
+		i64 size = lb_sizeof(type);
+
+		if (size == 0) {
+			return lb_arg_type_direct(type, LLVMStructTypeInContext(c, nullptr, 0, false), nullptr, nullptr);
+		}
+
+		LLVMTypeRef orig_type = type;
+
+		// Flatten down the type so it is easier to check all the ABI conditions.
+		// Note that we also need to remove all implicit padding fields Odin adds so we keep ABI
+		// compatibility for struct declarations.
+		if (kind == LLVMStructTypeKind && size <= gb_max(2*xlen, 2*flen)) {
+			Array<LLVMTypeRef> fields = array_make<LLVMTypeRef>(temporary_allocator(), 0, LLVMCountStructElementTypes(type));
+			flatten(m, &fields, type, false);
+
+			if (fields.count == 1) {
+				type = fields[0];
+			} else {
+				type = LLVMStructTypeInContext(c, fields.data, cast(unsigned)fields.count, false);
+			}
+
+			kind = LLVMGetTypeKind(type);
+			size = lb_sizeof(type);
+			GB_ASSERT_MSG(size == lb_sizeof(orig_type), "flattened: %s of size %d, original: %s of size %d", LLVMPrintTypeToString(type), size, LLVMPrintTypeToString(orig_type), lb_sizeof(orig_type));
+		}
+
+		if (is_float(type) && size <= flen && *fprs_left >= 1) {
+			*fprs_left -= 1;
+			return non_struct(c, orig_type);
+		}
+
+		if (kind == LLVMStructTypeKind && size <= 2*flen) {
+			unsigned elem_count = LLVMCountStructElementTypes(type);
+			if (elem_count == 2) {
+				LLVMTypeRef ty1 = LLVMStructGetTypeAtIndex(type, 0);
+				i64 ty1s = lb_sizeof(ty1);
+				LLVMTypeRef ty2 = LLVMStructGetTypeAtIndex(type, 1);
+				i64 ty2s = lb_sizeof(ty2);
+
+				if (is_float(ty1) && is_float(ty2) && ty1s <= flen && ty2s <= flen && *fprs_left >= 2) {
+					*fprs_left -= 2;
+					return lb_arg_type_direct(orig_type, type, nullptr, nullptr);
+				}
+
+				if (is_float(ty1) && is_register(ty2) && ty1s <= flen && ty2s <= xlen && *fprs_left >= 1 && *gprs_left >= 1) {
+					*fprs_left -= 1;
+					*gprs_left -= 1;
+					return lb_arg_type_direct(orig_type, type, nullptr, nullptr);
+				}
+
+				if (is_register(ty1) && is_float(ty2) && ty1s <= xlen && ty2s <= flen && *gprs_left >= 1 && *fprs_left >= 1) {
+					*fprs_left -= 1;
+					*gprs_left -= 1;
+					return lb_arg_type_direct(orig_type, type, nullptr, nullptr);
+				}
+			}
+		}
+
+		// At this point all the cases for floating point registers are exhausted, fit it into
+		// integer registers or the stack.
+		// LLVM automatically handles putting args on the stack so we don't check the amount of registers that are left here.
+
+		if (size <= xlen) {
+			*gprs_left -= 1;
+			if (is_register(type)) {
+				return non_struct(c, orig_type);
+			} else {
+				return lb_arg_type_direct(orig_type, LLVMIntTypeInContext(c, cast(unsigned)(size*8)), nullptr, nullptr);
+			}
+		} else if (size <= 2*xlen) {
+			LLVMTypeRef *fields = gb_alloc_array(temporary_allocator(), LLVMTypeRef, 2);
+			fields[0] = LLVMIntTypeInContext(c, cast(unsigned)(xlen*8));
+			fields[1] = LLVMIntTypeInContext(c, cast(unsigned)((size-xlen)*8));
+
+			*gprs_left -= 2;
+			return lb_arg_type_direct(orig_type, LLVMStructTypeInContext(c, fields, 2, false), nullptr, nullptr);
+		} else {
+			return lb_arg_type_indirect(orig_type, nullptr);
+		}
+	}
+
+	gb_internal Array<lbArgType> compute_arg_types(lbModule *m, LLVMTypeRef *arg_types, unsigned arg_count, ProcCallingConvention calling_convention, Type *odin_type, int *gprs, int *fprs) {
+		auto args = array_make<lbArgType>(lb_function_type_args_allocator(), arg_count);
+
+		for (unsigned i = 0; i < arg_count; i++) {
+			LLVMTypeRef type = arg_types[i];
+			args[i] = compute_arg_type(m, type, gprs, fprs, odin_type);
+		}
+
+		return args;
+	}
+
+	gb_internal lbArgType compute_return_type(lbFunctionType *ft, lbModule *m, LLVMTypeRef return_type, bool return_is_defined, bool return_is_tuple, Type *odin_type, int *agprs) {
+		LLVMContextRef c = m->ctx;
+
+		if (!return_is_defined) {
+			return lb_arg_type_direct(LLVMVoidTypeInContext(c));
+		}
+
+		// There are two registers for return types.
+		int gprs = 2;
+		int fprs = 2;
+		lbArgType ret = compute_arg_type(m, return_type, &gprs, &fprs, odin_type);
+
+		// Return didn't fit into the return registers, so caller allocates and it is returned via
+		// an out-pointer.
+		if (ret.kind == lbArg_Indirect) {
+
+			// Transform multiple return into out pointers if possible.
+			if (return_is_tuple) {
+				if (lb_is_type_kind(return_type, LLVMStructTypeKind)) {
+					int field_count = cast(int)LLVMCountStructElementTypes(return_type);
+					if (field_count > 1 && field_count <= *agprs) {
+						ft->original_arg_count = ft->args.count;
+						ft->multiple_return_original_type = return_type;
+
+						for (int i = 0; i < field_count-1; i++) {
+							LLVMTypeRef field_type = LLVMStructGetTypeAtIndex(return_type, i);
+							LLVMTypeRef field_pointer_type = LLVMPointerType(field_type, 0);
+							lbArgType ret_partial = lb_arg_type_direct(field_pointer_type);
+							array_add(&ft->args, ret_partial);
+							*agprs -= 1;
+						}
+						GB_ASSERT(*agprs >= 0);
+
+						// override the return type for the last field
+						LLVMTypeRef new_return_type = LLVMStructGetTypeAtIndex(return_type, field_count-1);
+						return compute_return_type(ft, m, new_return_type, true, false, odin_type, agprs);
+					}
+				}
+			}
+
+			LLVMAttributeRef attr = lb_create_enum_attribute_with_type(c, "sret", ret.type);
+			return lb_arg_type_indirect(ret.type, attr);
+		}
+
+		return ret;
+	}
+
+	gb_internal LB_ABI_INFO(abi_info) {
+		lbFunctionType *ft = gb_alloc_item(permanent_allocator(), lbFunctionType);
+		ft->ctx = m->ctx;
+		ft->calling_convention = calling_convention;
+
+		int gprs = 8;
+		int fprs = 8;
+
+		ft->args = compute_arg_types(m, arg_types, arg_count, calling_convention, original_type, &gprs, &fprs);
+		ft->ret = compute_return_type(ft, m, return_type, return_is_defined, return_is_tuple, original_type, &gprs);
+
+		return ft;
+	}
+}
+
 
 gb_internal LB_ABI_INFO(lb_get_abi_info_internal) {
+	LLVMContextRef c = m->ctx;
+
 	switch (calling_convention) {
 	case ProcCC_None:
 	case ProcCC_InlineAsm:
@@ -1534,6 +1783,8 @@ gb_internal LB_ABI_INFO(lb_get_abi_info_internal) {
 		return lbAbiWasm::abi_info(c, arg_types, arg_count, return_type, return_is_defined, return_is_tuple, calling_convention, original_type);
 	case TargetArch_wasm64p32:
 		return lbAbiWasm::abi_info(c, arg_types, arg_count, return_type, return_is_defined, return_is_tuple, calling_convention, original_type);
+	case TargetArch_riscv64:
+		return lbAbiRiscv64::abi_info(m, arg_types, arg_count, return_type, return_is_defined, return_is_tuple, calling_convention, original_type);
 	}
 
 	GB_PANIC("Unsupported ABI");
@@ -1543,7 +1794,7 @@ gb_internal LB_ABI_INFO(lb_get_abi_info_internal) {
 
 gb_internal LB_ABI_INFO(lb_get_abi_info) {
 	lbFunctionType *ft = lb_get_abi_info_internal(
-		c,
+		m,
 		arg_types, arg_count,
 		return_type, return_is_defined,
 		ALLOW_SPLIT_MULTI_RETURNS && return_is_tuple && is_calling_convention_odin(calling_convention),
@@ -1555,7 +1806,7 @@ gb_internal LB_ABI_INFO(lb_get_abi_info) {
 	// This is to make it consistent when and how it is handled
 	if (calling_convention == ProcCC_Odin) {
 		// append the `context` pointer
-		lbArgType context_param = lb_arg_type_direct(LLVMPointerType(LLVMInt8TypeInContext(c), 0));
+		lbArgType context_param = lb_arg_type_direct(LLVMPointerType(LLVMInt8TypeInContext(m->ctx), 0));
 		array_add(&ft->args, context_param);
 	}
 
diff --git a/src/llvm_backend.cpp b/src/llvm_backend.cpp
index 72ba12516..f852636a6 100644
--- a/src/llvm_backend.cpp
+++ b/src/llvm_backend.cpp
@@ -40,7 +40,10 @@ String get_default_microarchitecture() {
 				default_march = str_lit("x86-64-v2");
 			}
 		}
+	} else if (build_context.metrics.arch == TargetArch_riscv64) {
+		default_march = str_lit("generic-rv64");
 	}
+
 	return default_march;
 }
 
@@ -65,13 +68,33 @@ gb_internal String get_default_features() {
 	}
 
 	String microarch = get_final_microarchitecture();
+
+	// NOTE(laytan): for riscv64 to work properly with Odin, we need to enforce some features.
+	// and we also overwrite the generic target to include more features so we don't default to
+	// a potato feature set.
+	if (bc->metrics.arch == TargetArch_riscv64) {
+		if (microarch == str_lit("generic-rv64")) {
+			// This is what clang does by default (on -march=rv64gc for General Computing), seems good to also default to.
+			String features = str_lit("64bit,a,c,d,f,m,relax,zicsr,zifencei");
+
+			// Update the features string so LLVM uses it later.
+			if (bc->target_features_string.len > 0) {
+				bc->target_features_string = concatenate3_strings(permanent_allocator(), features, str_lit(","), bc->target_features_string);
+			} else {
+				bc->target_features_string = features;
+			}
+
+			return features;
+		}
+	}
+
 	for (int i = off; i < off+target_microarch_counts[bc->metrics.arch]; i += 1) {
 		if (microarch_features_list[i].microarch == microarch) {
 			return microarch_features_list[i].features;
 		}
 	}
 
-	GB_PANIC("unknown microarch");
+	GB_PANIC("unknown microarch: %.*s", LIT(microarch));
 	return {};
 }
 
@@ -3030,6 +3053,12 @@ gb_internal bool lb_generate_code(lbGenerator *gen) {
 			// Always use PIC for OpenBSD and Haiku: they default to PIE
 			reloc_mode = LLVMRelocPIC;
 		}
+
+		if (build_context.metrics.arch == TargetArch_riscv64) {
+			// NOTE(laytan): didn't seem to work without this.
+			reloc_mode = LLVMRelocPIC;
+		}
+
 		break;
 	case RelocMode_Static:
 		reloc_mode = LLVMRelocStatic;
diff --git a/src/llvm_backend_general.cpp b/src/llvm_backend_general.cpp
index b5338297e..842a1cbc8 100644
--- a/src/llvm_backend_general.cpp
+++ b/src/llvm_backend_general.cpp
@@ -1787,7 +1787,7 @@ gb_internal LLVMTypeRef lb_type_internal_for_procedures_raw(lbModule *m, Type *t
 		}
 	}
 	GB_ASSERT(param_index == param_count);
-	lbFunctionType *ft = lb_get_abi_info(m->ctx, params, param_count, ret, ret != nullptr, return_is_tuple, type->Proc.calling_convention, type);
+	lbFunctionType *ft = lb_get_abi_info(m, params, param_count, ret, ret != nullptr, return_is_tuple, type->Proc.calling_convention, type);
 	{
 		for_array(j, ft->args) {
 			auto arg = ft->args[j];
@@ -2114,6 +2114,12 @@ gb_internal LLVMTypeRef lb_type_internal(lbModule *m, Type *type) {
 					llvm_type = LLVMStructCreateNamed(ctx, name);
 					map_set(&m->types, type, llvm_type);
 					lb_clone_struct_type(llvm_type, lb_type(m, base));
+
+					if (base->kind == Type_Struct) {
+						map_set(&m->struct_field_remapping, cast(void *)llvm_type, lb_get_struct_remapping(m, base));
+						map_set(&m->struct_field_remapping, cast(void *)type, lb_get_struct_remapping(m, base));
+					}
+
 					return llvm_type;
 				}
 			}
diff --git a/src/llvm_backend_proc.cpp b/src/llvm_backend_proc.cpp
index 3326b4041..e850d3364 100644
--- a/src/llvm_backend_proc.cpp
+++ b/src/llvm_backend_proc.cpp
@@ -2877,6 +2877,31 @@ gb_internal lbValue lb_build_builtin_proc(lbProcedure *p, Ast *expr, TypeAndValu
 			LLVMValueRef inline_asm = nullptr;
 
 			switch (build_context.metrics.arch) {
+			case TargetArch_riscv64:
+				{
+					GB_ASSERT(arg_count <= 7);
+
+					char asm_string[] = "ecall";
+					gbString constraints = gb_string_make(heap_allocator(), "={a0}");
+					for (unsigned i = 0; i < arg_count; i++) {
+						constraints = gb_string_appendc(constraints, ",{");
+						static char const *regs[] = {
+							"a7",
+							"a0",
+							"a1",
+							"a2",
+							"a3",
+							"a4",
+							"a5",
+							"a6"
+						};
+						constraints = gb_string_appendc(constraints, regs[i]);
+						constraints = gb_string_appendc(constraints, "}");
+					}
+
+					inline_asm = llvm_get_inline_asm(func_type, make_string_c(asm_string), make_string_c(constraints));
+				}
+				break;
 			case TargetArch_amd64:
 				{
 					GB_ASSERT(arg_count <= 7);
diff --git a/src/main.cpp b/src/main.cpp
index 77758b929..5131bdc21 100644
--- a/src/main.cpp
+++ b/src/main.cpp
@@ -3245,6 +3245,15 @@ int main(int arg_count, char const **arg_ptr) {
 		}
 	}
 
+	// NOTE(laytan): on riscv64 we want to enforce some features.
+	if (build_context.metrics.arch == TargetArch_riscv64) {
+		String disabled;
+		if (!check_target_feature_is_enabled(str_lit("64bit,f,d,m"), &disabled)) { // 64bit, floats, doubles, integer multiplication.
+			gb_printf_err("missing required target feature: \"%.*s\", enable it by setting a different -microarch or explicitly adding it through -target-features\n", LIT(disabled));
+			gb_exit(1);
+		}
+	}
+
 	if (build_context.show_debug_messages) {
 		debugf("Selected microarch: %.*s\n", LIT(march));
 		debugf("Default microarch features: %.*s\n", LIT(default_features));