; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; RUN: llc -verify-machineinstrs -mcpu=sapphirerapids -mattr=+false-deps-getmant -mtriple=x86_64-unknown-unknown < %s | FileCheck %s --check-prefixes=ENABLE ; RUN: llc -verify-machineinstrs -mcpu=sapphirerapids -mattr=-false-deps-getmant -mtriple=x86_64-unknown-unknown < %s | FileCheck %s --check-prefixes=DISABLE define <4 x float> @getmantps_mem_128(ptr %p0) { ; ENABLE-LABEL: getmantps_mem_128: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantps $88, (%rdi), %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantps_mem_128: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vgetmantps $88, (%rdi), %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %a0 = load <4 x float>, ptr %p0, align 64 %2 = call <4 x float> @llvm.x86.avx512.mask.getmant.ps.128(<4 x float> %a0, i32 88, <4 x float> undef, i8 -1) ret <4 x float> %2 } define <4 x float> @getmantps_broadcast_128(ptr %p0) { ; ENABLE-LABEL: getmantps_broadcast_128: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantps $88, (%rdi){1to4}, %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantps_broadcast_128: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vgetmantps $88, (%rdi){1to4}, %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %v0 = load float, ptr %p0, align 4 %t0 = insertelement <4 x float> undef, float %v0, i64 0 %a0 = shufflevector <4 x float> %t0, <4 x float> undef, <4 x i32> zeroinitializer %2 = call <4 x float> @llvm.x86.avx512.mask.getmant.ps.128(<4 x float> %a0, i32 88, <4 x float> undef, i8 -1) ret <4 x float> %2 } declare <4 x float> @llvm.x86.avx512.mask.getmant.ps.128(<4 x float>, i32, <4 x float>, i8) define <8 x float> @getmantps_mem_256(ptr %p0) { ; ENABLE-LABEL: getmantps_mem_256: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantps $88, (%rdi), %ymm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantps_mem_256: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vgetmantps $88, (%rdi), %ymm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %a0 = load <8 x float>, ptr %p0, align 64 %2 = call <8 x float> @llvm.x86.avx512.mask.getmant.ps.256(<8 x float> %a0, i32 88, <8 x float> undef, i8 -1) ret <8 x float> %2 } define <8 x float> @getmantps_broadcast_256(ptr %p0) { ; ENABLE-LABEL: getmantps_broadcast_256: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantps $88, (%rdi){1to8}, %ymm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantps_broadcast_256: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vgetmantps $88, (%rdi){1to8}, %ymm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %v0 = load float, ptr %p0, align 4 %t0 = insertelement <8 x float> undef, float %v0, i64 0 %a0 = shufflevector <8 x float> %t0, <8 x float> undef, <8 x i32> zeroinitializer %2 = call <8 x float> @llvm.x86.avx512.mask.getmant.ps.256(<8 x float> %a0, i32 88, <8 x float> undef, i8 -1) ret <8 x float> %2 } declare <8 x float> @llvm.x86.avx512.mask.getmant.ps.256(<8 x float>, i32, <8 x float>, i8) define <16 x float> @getmantps_mem_512(ptr %p0) { ; ENABLE-LABEL: getmantps_mem_512: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vpxor %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantps $88, (%rdi), %zmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantps_mem_512: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vgetmantps $88, (%rdi), %zmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %a0 = load <16 x float>, ptr %p0, align 64 %2 = call <16 x float> @llvm.x86.avx512.mask.getmant.ps.512(<16 x float> %a0, i32 88, <16 x float> undef, i16 -1, i32 4) ret <16 x float> %2 } define <16 x float> @getmantps_broadcast_512(ptr %p0) { ; ENABLE-LABEL: getmantps_broadcast_512: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vpxor %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantps $88, (%rdi){1to16}, %zmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantps_broadcast_512: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vgetmantps $88, (%rdi){1to16}, %zmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %v0 = load float, ptr %p0, align 4 %t0 = insertelement <16 x float> undef, float %v0, i64 0 %a0 = shufflevector <16 x float> %t0, <16 x float> undef, <16 x i32> zeroinitializer %2 = call <16 x float> @llvm.x86.avx512.mask.getmant.ps.512(<16 x float> %a0, i32 88, <16 x float> undef, i16 -1, i32 4) ret <16 x float> %2 } declare <16 x float> @llvm.x86.avx512.mask.getmant.ps.512(<16 x float>, i32, <16 x float>, i16, i32) define <2 x double> @getmantpd_mem_128(ptr %p0) { ; ENABLE-LABEL: getmantpd_mem_128: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantpd $88, (%rdi), %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantpd_mem_128: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vgetmantpd $88, (%rdi), %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %a0 = load <2 x double>, ptr %p0, align 64 %2 = call <2 x double> @llvm.x86.avx512.mask.getmant.pd.128(<2 x double> %a0, i32 88, <2 x double> undef, i8 -1) ret <2 x double> %2 } define <2 x double> @getmantpd_broadcast_128(ptr %p0) { ; ENABLE-LABEL: getmantpd_broadcast_128: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantpd $88, (%rdi){1to2}, %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantpd_broadcast_128: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vgetmantpd $88, (%rdi){1to2}, %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %v0 = load double, ptr %p0, align 4 %t0 = insertelement <2 x double> undef, double %v0, i64 0 %a0 = shufflevector <2 x double> %t0, <2 x double> undef, <2 x i32> zeroinitializer %2 = call <2 x double> @llvm.x86.avx512.mask.getmant.pd.128(<2 x double> %a0, i32 88, <2 x double> undef, i8 -1) ret <2 x double> %2 } declare <2 x double> @llvm.x86.avx512.mask.getmant.pd.128(<2 x double>, i32, <2 x double>, i8) define <4 x double> @getmantpd_mem_256(ptr %p0) { ; ENABLE-LABEL: getmantpd_mem_256: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantpd $88, (%rdi), %ymm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantpd_mem_256: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vgetmantpd $88, (%rdi), %ymm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %a0 = load <4 x double>, ptr %p0, align 64 %2 = call <4 x double> @llvm.x86.avx512.mask.getmant.pd.256(<4 x double> %a0, i32 88, <4 x double> undef, i8 -1) ret <4 x double> %2 } define <4 x double> @getmantpd_broadcast_256(ptr %p0) { ; ENABLE-LABEL: getmantpd_broadcast_256: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantpd $88, (%rdi){1to4}, %ymm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantpd_broadcast_256: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vgetmantpd $88, (%rdi){1to4}, %ymm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %v0 = load double, ptr %p0, align 4 %t0 = insertelement <4 x double> undef, double %v0, i64 0 %a0 = shufflevector <4 x double> %t0, <4 x double> undef, <4 x i32> zeroinitializer %2 = call <4 x double> @llvm.x86.avx512.mask.getmant.pd.256(<4 x double> %a0, i32 88, <4 x double> undef, i8 -1) ret <4 x double> %2 } declare <4 x double> @llvm.x86.avx512.mask.getmant.pd.256(<4 x double>, i32, <4 x double>, i8) define <8 x double> @getmantpd_mem_512(ptr %p0) { ; ENABLE-LABEL: getmantpd_mem_512: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vpxor %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantpd $88, (%rdi), %zmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantpd_mem_512: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vgetmantpd $88, (%rdi), %zmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %a0 = load <8 x double>, ptr %p0, align 64 %2 = call <8 x double> @llvm.x86.avx512.mask.getmant.pd.512(<8 x double> %a0, i32 88, <8 x double> undef, i8 -1, i32 4) ret <8 x double> %2 } define <8 x double> @getmantpd_broadcast_512(ptr %p0) { ; ENABLE-LABEL: getmantpd_broadcast_512: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vpxor %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantpd $88, (%rdi){1to8}, %zmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantpd_broadcast_512: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vgetmantpd $88, (%rdi){1to8}, %zmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %v0 = load double, ptr %p0, align 4 %t0 = insertelement <8 x double> undef, double %v0, i64 0 %a0 = shufflevector <8 x double> %t0, <8 x double> undef, <8 x i32> zeroinitializer %2 = call <8 x double> @llvm.x86.avx512.mask.getmant.pd.512(<8 x double> %a0, i32 88, <8 x double> undef, i8 -1, i32 4) ret <8 x double> %2 } declare <8 x double> @llvm.x86.avx512.mask.getmant.pd.512(<8 x double>, i32, <8 x double>, i8, i32) define <8 x half> @getmantsh(<8 x half> %a0, <8 x half> %a1) { ; ENABLE-LABEL: getmantsh: ; ENABLE: # %bb.0: ; ENABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload ; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1 ; ENABLE-NEXT: vgetmantsh $11, %xmm2, %xmm0, %xmm1 ; ENABLE-NEXT: vaddph %xmm2, %xmm0, %xmm0 ; ENABLE-NEXT: vaddph %xmm0, %xmm1, %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantsh: ; DISABLE: # %bb.0: ; DISABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload ; DISABLE-NEXT: vgetmantsh $11, %xmm2, %xmm0, %xmm1 ; DISABLE-NEXT: vaddph %xmm2, %xmm0, %xmm0 ; DISABLE-NEXT: vaddph %xmm0, %xmm1, %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %2 = call <8 x half> @llvm.x86.avx512fp16.mask.getmant.sh(<8 x half> %a0, <8 x half> %a1, i32 11, <8 x half> undef, i8 -1, i32 4) %t = fadd <8 x half> %a0, %a1 %res = fadd <8 x half> %2, %t ret <8 x half> %res } define <8 x half> @getmantsh_mem(<8 x half> %a0, ptr %p1) { ; ENABLE-LABEL: getmantsh_mem: ; ENABLE: # %bb.0: ; ENABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload ; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantsh $11, (%rdi), %xmm1, %xmm0 ; ENABLE-NEXT: vaddph %xmm1, %xmm0, %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantsh_mem: ; DISABLE: # %bb.0: ; DISABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload ; DISABLE-NEXT: vgetmantsh $11, (%rdi), %xmm1, %xmm0 ; DISABLE-NEXT: vaddph %xmm1, %xmm0, %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %a1 = load <8 x half>, ptr %p1, align 64 %2 = call <8 x half> @llvm.x86.avx512fp16.mask.getmant.sh(<8 x half> %a0, <8 x half> %a1, i32 11, <8 x half> undef, i8 -1, i32 4) %res = fadd <8 x half> %2, %a0 ret <8 x half> %res } define <8 x half> @getmantsh_maskz(<8 x half> %a0, <8 x half> %a1, ptr %mask) { ; ENABLE-LABEL: getmantsh_maskz: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: kmovb (%rdi), %k1 ; ENABLE-NEXT: vxorps %xmm2, %xmm2, %xmm2 ; ENABLE-NEXT: vgetmantsh $11, %xmm1, %xmm0, %xmm2 {%k1} {z} ; ENABLE-NEXT: vaddph %xmm1, %xmm0, %xmm0 ; ENABLE-NEXT: vaddph %xmm0, %xmm2, %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantsh_maskz: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: kmovb (%rdi), %k1 ; DISABLE-NEXT: vgetmantsh $11, %xmm1, %xmm0, %xmm2 {%k1} {z} ; DISABLE-NEXT: vaddph %xmm1, %xmm0, %xmm0 ; DISABLE-NEXT: vaddph %xmm0, %xmm2, %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %2 = load i8, ptr %mask %3 = call <8 x half> @llvm.x86.avx512fp16.mask.getmant.sh(<8 x half> %a0, <8 x half> %a1, i32 11, <8 x half> zeroinitializer, i8 %2, i32 4) %t = fadd <8 x half> %a0, %a1 %res = fadd <8 x half> %3, %t ret <8 x half> %res } declare <8 x half> @llvm.x86.avx512fp16.mask.getmant.sh(<8 x half>, <8 x half>, i32, <8 x half>, i8, i32) define <4 x float> @getmantss(<4 x float> %a0, <4 x float> %a1) { ; ENABLE-LABEL: getmantss: ; ENABLE: # %bb.0: ; ENABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload ; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1 ; ENABLE-NEXT: vgetmantss $11, %xmm2, %xmm0, %xmm1 ; ENABLE-NEXT: vaddps %xmm2, %xmm0, %xmm0 ; ENABLE-NEXT: vaddps %xmm0, %xmm1, %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantss: ; DISABLE: # %bb.0: ; DISABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload ; DISABLE-NEXT: vgetmantss $11, %xmm2, %xmm0, %xmm1 ; DISABLE-NEXT: vaddps %xmm2, %xmm0, %xmm0 ; DISABLE-NEXT: vaddps %xmm0, %xmm1, %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %2 = call <4 x float> @llvm.x86.avx512.mask.getmant.ss(<4 x float> %a0, <4 x float> %a1, i32 11, <4 x float> undef, i8 -1, i32 4) %t = fadd <4 x float> %a0, %a1 %res = fadd <4 x float> %2, %t ret <4 x float> %res } define <4 x float> @getmantss_mem(<4 x float> %a0, ptr %p1) { ; ENABLE-LABEL: getmantss_mem: ; ENABLE: # %bb.0: ; ENABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload ; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantss $11, (%rdi), %xmm1, %xmm0 ; ENABLE-NEXT: vaddps %xmm1, %xmm0, %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantss_mem: ; DISABLE: # %bb.0: ; DISABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload ; DISABLE-NEXT: vgetmantss $11, (%rdi), %xmm1, %xmm0 ; DISABLE-NEXT: vaddps %xmm1, %xmm0, %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %a1 = load <4 x float>, ptr %p1, align 64 %2 = call <4 x float> @llvm.x86.avx512.mask.getmant.ss(<4 x float> %a0, <4 x float> %a1, i32 11, <4 x float> undef, i8 -1, i32 4) %res = fadd <4 x float> %2, %a0 ret <4 x float> %res } define <4 x float> @getmantss_maskz(<4 x float> %a0, <4 x float> %a1, ptr %mask) { ; ENABLE-LABEL: getmantss_maskz: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: kmovb (%rdi), %k1 ; ENABLE-NEXT: vxorps %xmm2, %xmm2, %xmm2 ; ENABLE-NEXT: vgetmantss $11, %xmm1, %xmm0, %xmm2 {%k1} {z} ; ENABLE-NEXT: vaddps %xmm1, %xmm0, %xmm0 ; ENABLE-NEXT: vaddps %xmm0, %xmm2, %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantss_maskz: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: kmovb (%rdi), %k1 ; DISABLE-NEXT: vgetmantss $11, %xmm1, %xmm0, %xmm2 {%k1} {z} ; DISABLE-NEXT: vaddps %xmm1, %xmm0, %xmm0 ; DISABLE-NEXT: vaddps %xmm0, %xmm2, %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %2 = load i8, ptr %mask %3 = call <4 x float> @llvm.x86.avx512.mask.getmant.ss(<4 x float> %a0, <4 x float> %a1, i32 11, <4 x float> zeroinitializer, i8 %2, i32 4) %t = fadd <4 x float> %a0, %a1 %res = fadd <4 x float> %3, %t ret <4 x float> %res } declare <4 x float> @llvm.x86.avx512.mask.getmant.ss(<4 x float>, <4 x float>, i32, <4 x float>, i8, i32) define <2 x double> @getmantsd(<2 x double> %a0, <2 x double> %a1) { ; ENABLE-LABEL: getmantsd: ; ENABLE: # %bb.0: ; ENABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload ; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1 ; ENABLE-NEXT: vgetmantsd $11, %xmm2, %xmm0, %xmm1 ; ENABLE-NEXT: vaddpd %xmm2, %xmm0, %xmm0 ; ENABLE-NEXT: vaddpd %xmm0, %xmm1, %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantsd: ; DISABLE: # %bb.0: ; DISABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload ; DISABLE-NEXT: vgetmantsd $11, %xmm2, %xmm0, %xmm1 ; DISABLE-NEXT: vaddpd %xmm2, %xmm0, %xmm0 ; DISABLE-NEXT: vaddpd %xmm0, %xmm1, %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %2 = call <2 x double> @llvm.x86.avx512.mask.getmant.sd(<2 x double> %a0, <2 x double> %a1, i32 11, <2 x double> undef, i8 -1, i32 4) %t = fadd <2 x double> %a0, %a1 %res = fadd <2 x double> %2, %t ret <2 x double> %res } define <2 x double> @getmantsd_mem(<2 x double> %a0, ptr %p1) { ; ENABLE-LABEL: getmantsd_mem: ; ENABLE: # %bb.0: ; ENABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload ; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0 ; ENABLE-NEXT: vgetmantsd $11, (%rdi), %xmm1, %xmm0 ; ENABLE-NEXT: vaddpd %xmm1, %xmm0, %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantsd_mem: ; DISABLE: # %bb.0: ; DISABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload ; DISABLE-NEXT: vgetmantsd $11, (%rdi), %xmm1, %xmm0 ; DISABLE-NEXT: vaddpd %xmm1, %xmm0, %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %a1 = load <2 x double>, ptr %p1, align 64 %2 = call <2 x double> @llvm.x86.avx512.mask.getmant.sd(<2 x double> %a0, <2 x double> %a1, i32 11, <2 x double> undef, i8 -1, i32 4) %res = fadd <2 x double> %2, %a0 ret <2 x double> %res } define <2 x double> @getmantsd_maskz(<2 x double> %a0, <2 x double> %a1, ptr %mask) { ; ENABLE-LABEL: getmantsd_maskz: ; ENABLE: # %bb.0: ; ENABLE-NEXT: #APP ; ENABLE-NEXT: nop ; ENABLE-NEXT: #NO_APP ; ENABLE-NEXT: kmovb (%rdi), %k1 ; ENABLE-NEXT: vxorps %xmm2, %xmm2, %xmm2 ; ENABLE-NEXT: vgetmantsd $11, %xmm1, %xmm0, %xmm2 {%k1} {z} ; ENABLE-NEXT: vaddpd %xmm1, %xmm0, %xmm0 ; ENABLE-NEXT: vaddpd %xmm0, %xmm2, %xmm0 ; ENABLE-NEXT: retq ; ; DISABLE-LABEL: getmantsd_maskz: ; DISABLE: # %bb.0: ; DISABLE-NEXT: #APP ; DISABLE-NEXT: nop ; DISABLE-NEXT: #NO_APP ; DISABLE-NEXT: kmovb (%rdi), %k1 ; DISABLE-NEXT: vgetmantsd $11, %xmm1, %xmm0, %xmm2 {%k1} {z} ; DISABLE-NEXT: vaddpd %xmm1, %xmm0, %xmm0 ; DISABLE-NEXT: vaddpd %xmm0, %xmm2, %xmm0 ; DISABLE-NEXT: retq %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"() %2 = load i8, ptr %mask %3 = call <2 x double> @llvm.x86.avx512.mask.getmant.sd(<2 x double> %a0, <2 x double> %a1, i32 11, <2 x double> zeroinitializer, i8 %2, i32 4) %t = fadd <2 x double> %a0, %a1 %res = fadd <2 x double> %3, %t ret <2 x double> %res } declare <2 x double> @llvm.x86.avx512.mask.getmant.sd(<2 x double>, <2 x double>, i32, <2 x double>, i8, i32)