diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp index 99866c811eb6fa..7915edfff680da 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.cpp +++ b/llvm/lib/Target/X86/X86ISelLowering.cpp @@ -1970,20 +1970,24 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM, } if (Subtarget.hasVBMI2()) { - for (auto VT : { MVT::v8i16, MVT::v4i32, MVT::v2i64, - MVT::v16i16, MVT::v8i32, MVT::v4i64, - MVT::v32i16, MVT::v16i32, MVT::v8i64 }) { + for (auto VT : {MVT::v32i16, MVT::v16i32, MVT::v8i64}) { setOperationAction(ISD::FSHL, VT, Custom); setOperationAction(ISD::FSHR, VT, Custom); } setOperationAction(ISD::ROTL, MVT::v32i16, Custom); - setOperationAction(ISD::ROTR, MVT::v8i16, Custom); - setOperationAction(ISD::ROTR, MVT::v16i16, Custom); setOperationAction(ISD::ROTR, MVT::v32i16, Custom); } }// useAVX512Regs + if (Subtarget.hasVBMI2()) { + for (auto VT : {MVT::v8i16, MVT::v4i32, MVT::v2i64, MVT::v16i16, MVT::v8i32, + MVT::v4i64}) { + setOperationAction(ISD::FSHL, VT, Custom); + setOperationAction(ISD::FSHR, VT, Custom); + } + } + // This block controls legalization for operations that don't have // pre-AVX512 equivalents. Without VLX we use 512-bit operations for // narrower widths. diff --git a/llvm/test/CodeGen/X86/vector-fshl-128.ll b/llvm/test/CodeGen/X86/vector-fshl-128.ll index 2b97280113bb63..2d0e92a54846b0 100644 --- a/llvm/test/CodeGen/X86/vector-fshl-128.ll +++ b/llvm/test/CodeGen/X86/vector-fshl-128.ll @@ -9,6 +9,8 @@ ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi,+avx512vbmi2 | FileCheck %s --check-prefixes=AVX512VBMI2 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=AVX512VLBW ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi,+avx512vbmi2,+avx512vl | FileCheck %s --check-prefixes=AVX512VLVBMI2 +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx10.1-256 | FileCheck %s --check-prefixes=AVX512VLVBMI2 +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx10.1-512 | FileCheck %s --check-prefixes=AVX512VLVBMI2 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx | FileCheck %s --check-prefixes=XOP,XOPAVX1 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx2 | FileCheck %s --check-prefixes=XOP,XOPAVX2 diff --git a/llvm/test/CodeGen/X86/vector-fshl-256.ll b/llvm/test/CodeGen/X86/vector-fshl-256.ll index 1720193e1f04bd..f5da1bb7fb9d2c 100644 --- a/llvm/test/CodeGen/X86/vector-fshl-256.ll +++ b/llvm/test/CodeGen/X86/vector-fshl-256.ll @@ -6,7 +6,9 @@ ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=AVX512BW ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi,+avx512vbmi2 | FileCheck %s --check-prefixes=AVX512VBMI2 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=AVX512VLBW -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi,+avx512vbmi2,+avx512vl | FileCheck %s --check-prefixes=AVX512VLVBMI2 +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi,+avx512vbmi2,+avx512vl | FileCheck %s --check-prefixes=AVX10,AVX512VLVBMI2 +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx10.1-256 | FileCheck %s --check-prefixes=AVX10,AVX10_256 +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx10.1-512 | FileCheck %s --check-prefixes=AVX10,AVX512VLVBMI2 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx | FileCheck %s --check-prefixes=XOPAVX1 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx2 | FileCheck %s --check-prefixes=XOPAVX2 @@ -116,10 +118,10 @@ define <4 x i64> @var_funnnel_v4i64(<4 x i64> %x, <4 x i64> %y, <4 x i64> %amt) ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: var_funnnel_v4i64: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshldvq %ymm2, %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: var_funnnel_v4i64: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshldvq %ymm2, %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: var_funnnel_v4i64: ; XOPAVX1: # %bb.0: @@ -271,10 +273,10 @@ define <8 x i32> @var_funnnel_v8i32(<8 x i32> %x, <8 x i32> %y, <8 x i32> %amt) ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: var_funnnel_v8i32: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshldvd %ymm2, %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: var_funnnel_v8i32: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshldvd %ymm2, %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: var_funnnel_v8i32: ; XOPAVX1: # %bb.0: @@ -424,10 +426,10 @@ define <16 x i16> @var_funnnel_v16i16(<16 x i16> %x, <16 x i16> %y, <16 x i16> % ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: var_funnnel_v16i16: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshldvw %ymm2, %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: var_funnnel_v16i16: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshldvw %ymm2, %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: var_funnnel_v16i16: ; XOPAVX1: # %bb.0: @@ -691,6 +693,21 @@ define <32 x i8> @var_funnnel_v32i8(<32 x i8> %x, <32 x i8> %y, <32 x i8> %amt) ; AVX512VLVBMI2-NEXT: vpmovwb %zmm0, %ymm0 ; AVX512VLVBMI2-NEXT: retq ; +; AVX10_256-LABEL: var_funnnel_v32i8: +; AVX10_256: # %bb.0: +; AVX10_256-NEXT: vpunpckhbw {{.*#+}} ymm3 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31] +; AVX10_256-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to8}, %ymm2, %ymm2 +; AVX10_256-NEXT: vpxor %xmm4, %xmm4, %xmm4 +; AVX10_256-NEXT: vpunpckhbw {{.*#+}} ymm5 = ymm2[8],ymm4[8],ymm2[9],ymm4[9],ymm2[10],ymm4[10],ymm2[11],ymm4[11],ymm2[12],ymm4[12],ymm2[13],ymm4[13],ymm2[14],ymm4[14],ymm2[15],ymm4[15],ymm2[24],ymm4[24],ymm2[25],ymm4[25],ymm2[26],ymm4[26],ymm2[27],ymm4[27],ymm2[28],ymm4[28],ymm2[29],ymm4[29],ymm2[30],ymm4[30],ymm2[31],ymm4[31] +; AVX10_256-NEXT: vpsllvw %ymm5, %ymm3, %ymm3 +; AVX10_256-NEXT: vpsrlw $8, %ymm3, %ymm3 +; AVX10_256-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23] +; AVX10_256-NEXT: vpunpcklbw {{.*#+}} ymm1 = ymm2[0],ymm4[0],ymm2[1],ymm4[1],ymm2[2],ymm4[2],ymm2[3],ymm4[3],ymm2[4],ymm4[4],ymm2[5],ymm4[5],ymm2[6],ymm4[6],ymm2[7],ymm4[7],ymm2[16],ymm4[16],ymm2[17],ymm4[17],ymm2[18],ymm4[18],ymm2[19],ymm4[19],ymm2[20],ymm4[20],ymm2[21],ymm4[21],ymm2[22],ymm4[22],ymm2[23],ymm4[23] +; AVX10_256-NEXT: vpsllvw %ymm1, %ymm0, %ymm0 +; AVX10_256-NEXT: vpsrlw $8, %ymm0, %ymm0 +; AVX10_256-NEXT: vpackuswb %ymm3, %ymm0, %ymm0 +; AVX10_256-NEXT: retq +; ; XOPAVX1-LABEL: var_funnnel_v32i8: ; XOPAVX1: # %bb.0: ; XOPAVX1-NEXT: vextractf128 $1, %ymm1, %xmm3 @@ -824,11 +841,11 @@ define <4 x i64> @splatvar_funnnel_v4i64(<4 x i64> %x, <4 x i64> %y, <4 x i64> % ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatvar_funnnel_v4i64: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpbroadcastq %xmm2, %ymm2 -; AVX512VLVBMI2-NEXT: vpshldvq %ymm2, %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatvar_funnnel_v4i64: +; AVX10: # %bb.0: +; AVX10-NEXT: vpbroadcastq %xmm2, %ymm2 +; AVX10-NEXT: vpshldvq %ymm2, %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatvar_funnnel_v4i64: ; XOPAVX1: # %bb.0: @@ -942,11 +959,11 @@ define <8 x i32> @splatvar_funnnel_v8i32(<8 x i32> %x, <8 x i32> %y, <8 x i32> % ; AVX512VLBW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm3[1,3],ymm0[5,7],ymm3[5,7] ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatvar_funnnel_v8i32: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpbroadcastd %xmm2, %ymm2 -; AVX512VLVBMI2-NEXT: vpshldvd %ymm2, %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatvar_funnnel_v8i32: +; AVX10: # %bb.0: +; AVX10-NEXT: vpbroadcastd %xmm2, %ymm2 +; AVX10-NEXT: vpshldvd %ymm2, %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatvar_funnnel_v8i32: ; XOPAVX1: # %bb.0: @@ -1063,11 +1080,11 @@ define <16 x i16> @splatvar_funnnel_v16i16(<16 x i16> %x, <16 x i16> %y, <16 x i ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatvar_funnnel_v16i16: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpbroadcastw %xmm2, %ymm2 -; AVX512VLVBMI2-NEXT: vpshldvw %ymm2, %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatvar_funnnel_v16i16: +; AVX10: # %bb.0: +; AVX10-NEXT: vpbroadcastw %xmm2, %ymm2 +; AVX10-NEXT: vpshldvw %ymm2, %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatvar_funnnel_v16i16: ; XOPAVX1: # %bb.0: @@ -1197,17 +1214,17 @@ define <32 x i8> @splatvar_funnnel_v32i8(<32 x i8> %x, <32 x i8> %y, <32 x i8> % ; AVX512VLBW-NEXT: vpackuswb %ymm3, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatvar_funnnel_v32i8: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpunpckhbw {{.*#+}} ymm3 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31] -; AVX512VLVBMI2-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2, %xmm2 -; AVX512VLVBMI2-NEXT: vpsllw %xmm2, %ymm3, %ymm3 -; AVX512VLVBMI2-NEXT: vpsrlw $8, %ymm3, %ymm3 -; AVX512VLVBMI2-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23] -; AVX512VLVBMI2-NEXT: vpsllw %xmm2, %ymm0, %ymm0 -; AVX512VLVBMI2-NEXT: vpsrlw $8, %ymm0, %ymm0 -; AVX512VLVBMI2-NEXT: vpackuswb %ymm3, %ymm0, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatvar_funnnel_v32i8: +; AVX10: # %bb.0: +; AVX10-NEXT: vpunpckhbw {{.*#+}} ymm3 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31] +; AVX10-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2, %xmm2 +; AVX10-NEXT: vpsllw %xmm2, %ymm3, %ymm3 +; AVX10-NEXT: vpsrlw $8, %ymm3, %ymm3 +; AVX10-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23] +; AVX10-NEXT: vpsllw %xmm2, %ymm0, %ymm0 +; AVX10-NEXT: vpsrlw $8, %ymm0, %ymm0 +; AVX10-NEXT: vpackuswb %ymm3, %ymm0, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatvar_funnnel_v32i8: ; XOPAVX1: # %bb.0: @@ -1438,25 +1455,25 @@ define void @fancierRotate2(ptr %arr, ptr %control, i32 %rot0, i32 %rot1) { ; AVX512VLBW-NEXT: vzeroupper ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: fancierRotate2: -; AVX512VLVBMI2: # %bb.0: # %entry -; AVX512VLVBMI2-NEXT: vpbroadcastd %edx, %ymm0 -; AVX512VLVBMI2-NEXT: vpbroadcastd %ecx, %ymm1 -; AVX512VLVBMI2-NEXT: movq $-1024, %rax # imm = 0xFC00 -; AVX512VLVBMI2-NEXT: .p2align 4, 0x90 -; AVX512VLVBMI2-NEXT: .LBB8_1: # %loop -; AVX512VLVBMI2-NEXT: # =>This Inner Loop Header: Depth=1 -; AVX512VLVBMI2-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero -; AVX512VLVBMI2-NEXT: vptestnmb %xmm2, %xmm2, %k1 -; AVX512VLVBMI2-NEXT: vpblendmd %ymm0, %ymm1, %ymm2 {%k1} -; AVX512VLVBMI2-NEXT: vmovdqu 4096(%rdi,%rax,4), %ymm3 -; AVX512VLVBMI2-NEXT: vprolvd %ymm2, %ymm3, %ymm2 -; AVX512VLVBMI2-NEXT: vmovdqu %ymm2, 4096(%rdi,%rax,4) -; AVX512VLVBMI2-NEXT: addq $8, %rax -; AVX512VLVBMI2-NEXT: jne .LBB8_1 -; AVX512VLVBMI2-NEXT: # %bb.2: # %exit -; AVX512VLVBMI2-NEXT: vzeroupper -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: fancierRotate2: +; AVX10: # %bb.0: # %entry +; AVX10-NEXT: vpbroadcastd %edx, %ymm0 +; AVX10-NEXT: vpbroadcastd %ecx, %ymm1 +; AVX10-NEXT: movq $-1024, %rax # imm = 0xFC00 +; AVX10-NEXT: .p2align 4, 0x90 +; AVX10-NEXT: .LBB8_1: # %loop +; AVX10-NEXT: # =>This Inner Loop Header: Depth=1 +; AVX10-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero +; AVX10-NEXT: vptestnmb %xmm2, %xmm2, %k1 +; AVX10-NEXT: vpblendmd %ymm0, %ymm1, %ymm2 {%k1} +; AVX10-NEXT: vmovdqu 4096(%rdi,%rax,4), %ymm3 +; AVX10-NEXT: vprolvd %ymm2, %ymm3, %ymm2 +; AVX10-NEXT: vmovdqu %ymm2, 4096(%rdi,%rax,4) +; AVX10-NEXT: addq $8, %rax +; AVX10-NEXT: jne .LBB8_1 +; AVX10-NEXT: # %bb.2: # %exit +; AVX10-NEXT: vzeroupper +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: fancierRotate2: ; XOPAVX1: # %bb.0: # %entry @@ -1609,10 +1626,10 @@ define <4 x i64> @constant_funnnel_v4i64(<4 x i64> %x, <4 x i64> %y) nounwind { ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: constant_funnnel_v4i64: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshldvq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: constant_funnnel_v4i64: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshldvq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: constant_funnnel_v4i64: ; XOPAVX1: # %bb.0: @@ -1707,10 +1724,10 @@ define <8 x i32> @constant_funnnel_v8i32(<8 x i32> %x, <8 x i32> %y) nounwind { ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: constant_funnnel_v8i32: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshldvd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: constant_funnnel_v8i32: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshldvd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: constant_funnnel_v8i32: ; XOPAVX1: # %bb.0: @@ -1810,10 +1827,10 @@ define <16 x i16> @constant_funnnel_v16i16(<16 x i16> %x, <16 x i16> %y) nounwin ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: constant_funnnel_v16i16: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshldvw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: constant_funnnel_v16i16: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshldvw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: constant_funnnel_v16i16: ; XOPAVX1: # %bb.0: @@ -1944,6 +1961,17 @@ define <32 x i8> @constant_funnnel_v32i8(<32 x i8> %x, <32 x i8> %y) nounwind { ; AVX512VLVBMI2-NEXT: vpmovwb %zmm0, %ymm0 ; AVX512VLVBMI2-NEXT: retq ; +; AVX10_256-LABEL: constant_funnnel_v32i8: +; AVX10_256: # %bb.0: +; AVX10_256-NEXT: vpunpckhbw {{.*#+}} ymm2 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31] +; AVX10_256-NEXT: vpsllvw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm2, %ymm2 +; AVX10_256-NEXT: vpsrlw $8, %ymm2, %ymm2 +; AVX10_256-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23] +; AVX10_256-NEXT: vpsllvw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm0 +; AVX10_256-NEXT: vpsrlw $8, %ymm0, %ymm0 +; AVX10_256-NEXT: vpackuswb %ymm2, %ymm0, %ymm0 +; AVX10_256-NEXT: retq +; ; XOPAVX1-LABEL: constant_funnnel_v32i8: ; XOPAVX1: # %bb.0: ; XOPAVX1-NEXT: vextractf128 $1, %ymm0, %xmm2 @@ -2044,10 +2072,10 @@ define <4 x i64> @splatconstant_funnnel_v4i64(<4 x i64> %x, <4 x i64> %y) nounwi ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatconstant_funnnel_v4i64: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshldq $14, %ymm1, %ymm0, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatconstant_funnnel_v4i64: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshldq $14, %ymm1, %ymm0, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatconstant_funnnel_v4i64: ; XOPAVX1: # %bb.0: @@ -2129,10 +2157,10 @@ define <8 x i32> @splatconstant_funnnel_v8i32(<8 x i32> %x, <8 x i32> %y) nounwi ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatconstant_funnnel_v8i32: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshldd $4, %ymm1, %ymm0, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatconstant_funnnel_v8i32: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshldd $4, %ymm1, %ymm0, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatconstant_funnnel_v8i32: ; XOPAVX1: # %bb.0: @@ -2214,10 +2242,10 @@ define <16 x i16> @splatconstant_funnnel_v16i16(<16 x i16> %x, <16 x i16> %y) no ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatconstant_funnnel_v16i16: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshldw $7, %ymm1, %ymm0, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatconstant_funnnel_v16i16: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshldw $7, %ymm1, %ymm0, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatconstant_funnnel_v16i16: ; XOPAVX1: # %bb.0: @@ -2309,12 +2337,12 @@ define <32 x i8> @splatconstant_funnnel_v32i8(<32 x i8> %x, <32 x i8> %y) nounwi ; AVX512VLBW-NEXT: vpternlogq $216, {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %ymm2, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatconstant_funnnel_v32i8: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpsllw $4, %ymm0, %ymm2 -; AVX512VLVBMI2-NEXT: vpsrlw $4, %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: vpternlogq $216, {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %ymm2, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatconstant_funnnel_v32i8: +; AVX10: # %bb.0: +; AVX10-NEXT: vpsllw $4, %ymm0, %ymm2 +; AVX10-NEXT: vpsrlw $4, %ymm1, %ymm0 +; AVX10-NEXT: vpternlogq $216, {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %ymm2, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatconstant_funnnel_v32i8: ; XOPAVX1: # %bb.0: diff --git a/llvm/test/CodeGen/X86/vector-fshr-128.ll b/llvm/test/CodeGen/X86/vector-fshr-128.ll index ea54d0567eccf1..809735a88f2080 100644 --- a/llvm/test/CodeGen/X86/vector-fshr-128.ll +++ b/llvm/test/CodeGen/X86/vector-fshr-128.ll @@ -9,6 +9,8 @@ ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi,+avx512vbmi2 | FileCheck %s --check-prefixes=AVX512VBMI2 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=AVX512VLBW ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi,+avx512vbmi2,+avx512vl | FileCheck %s --check-prefixes=AVX512VLVBMI2 +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx10.1-256 | FileCheck %s --check-prefixes=AVX512VLVBMI2 +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx10.1-512 | FileCheck %s --check-prefixes=AVX512VLVBMI2 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx | FileCheck %s --check-prefixes=XOP,XOPAVX1 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx2 | FileCheck %s --check-prefixes=XOP,XOPAVX2 diff --git a/llvm/test/CodeGen/X86/vector-fshr-256.ll b/llvm/test/CodeGen/X86/vector-fshr-256.ll index b39b7c140a451d..df52633ef6da0b 100644 --- a/llvm/test/CodeGen/X86/vector-fshr-256.ll +++ b/llvm/test/CodeGen/X86/vector-fshr-256.ll @@ -6,7 +6,9 @@ ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=AVX512BW ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi,+avx512vbmi2 | FileCheck %s --check-prefixes=AVX512VBMI2 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=AVX512VLBW -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi,+avx512vbmi2,+avx512vl | FileCheck %s --check-prefixes=AVX512VLVBMI2 +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi,+avx512vbmi2,+avx512vl | FileCheck %s --check-prefixes=AVX10,AVX512VLVBMI2 +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx10.1-256 | FileCheck %s --check-prefixes=AVX10,AVX10_256 +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx10.1-512 | FileCheck %s --check-prefixes=AVX10,AVX512VLVBMI2 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx | FileCheck %s --check-prefixes=XOPAVX1 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx2 | FileCheck %s --check-prefixes=XOPAVX2 @@ -116,11 +118,11 @@ define <4 x i64> @var_funnnel_v4i64(<4 x i64> %x, <4 x i64> %y, <4 x i64> %amt) ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: var_funnnel_v4i64: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshrdvq %ymm2, %ymm0, %ymm1 -; AVX512VLVBMI2-NEXT: vmovdqa %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: var_funnnel_v4i64: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshrdvq %ymm2, %ymm0, %ymm1 +; AVX10-NEXT: vmovdqa %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: var_funnnel_v4i64: ; XOPAVX1: # %bb.0: @@ -272,11 +274,11 @@ define <8 x i32> @var_funnnel_v8i32(<8 x i32> %x, <8 x i32> %y, <8 x i32> %amt) ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: var_funnnel_v8i32: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshrdvd %ymm2, %ymm0, %ymm1 -; AVX512VLVBMI2-NEXT: vmovdqa %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: var_funnnel_v8i32: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshrdvd %ymm2, %ymm0, %ymm1 +; AVX10-NEXT: vmovdqa %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: var_funnnel_v8i32: ; XOPAVX1: # %bb.0: @@ -452,11 +454,11 @@ define <16 x i16> @var_funnnel_v16i16(<16 x i16> %x, <16 x i16> %y, <16 x i16> % ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: var_funnnel_v16i16: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshrdvw %ymm2, %ymm0, %ymm1 -; AVX512VLVBMI2-NEXT: vmovdqa %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: var_funnnel_v16i16: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshrdvw %ymm2, %ymm0, %ymm1 +; AVX10-NEXT: vmovdqa %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: var_funnnel_v16i16: ; XOPAVX1: # %bb.0: @@ -718,6 +720,20 @@ define <32 x i8> @var_funnnel_v32i8(<32 x i8> %x, <32 x i8> %y, <32 x i8> %amt) ; AVX512VLVBMI2-NEXT: vpmovwb %zmm0, %ymm0 ; AVX512VLVBMI2-NEXT: retq ; +; AVX10_256-LABEL: var_funnnel_v32i8: +; AVX10_256: # %bb.0: +; AVX10_256-NEXT: vpunpckhbw {{.*#+}} ymm3 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31] +; AVX10_256-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to8}, %ymm2, %ymm2 +; AVX10_256-NEXT: vpxor %xmm4, %xmm4, %xmm4 +; AVX10_256-NEXT: vpunpckhbw {{.*#+}} ymm5 = ymm2[8],ymm4[8],ymm2[9],ymm4[9],ymm2[10],ymm4[10],ymm2[11],ymm4[11],ymm2[12],ymm4[12],ymm2[13],ymm4[13],ymm2[14],ymm4[14],ymm2[15],ymm4[15],ymm2[24],ymm4[24],ymm2[25],ymm4[25],ymm2[26],ymm4[26],ymm2[27],ymm4[27],ymm2[28],ymm4[28],ymm2[29],ymm4[29],ymm2[30],ymm4[30],ymm2[31],ymm4[31] +; AVX10_256-NEXT: vpsrlvw %ymm5, %ymm3, %ymm3 +; AVX10_256-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23] +; AVX10_256-NEXT: vpunpcklbw {{.*#+}} ymm1 = ymm2[0],ymm4[0],ymm2[1],ymm4[1],ymm2[2],ymm4[2],ymm2[3],ymm4[3],ymm2[4],ymm4[4],ymm2[5],ymm4[5],ymm2[6],ymm4[6],ymm2[7],ymm4[7],ymm2[16],ymm4[16],ymm2[17],ymm4[17],ymm2[18],ymm4[18],ymm2[19],ymm4[19],ymm2[20],ymm4[20],ymm2[21],ymm4[21],ymm2[22],ymm4[22],ymm2[23],ymm4[23] +; AVX10_256-NEXT: vpsrlvw %ymm1, %ymm0, %ymm1 +; AVX10_256-NEXT: vmovdqa {{.*#+}} ymm0 = [0,2,4,6,8,10,12,14,32,34,36,38,40,42,44,46,16,18,20,22,24,26,28,30,48,50,52,54,56,58,60,62] +; AVX10_256-NEXT: vpermi2b %ymm3, %ymm1, %ymm0 +; AVX10_256-NEXT: retq +; ; XOPAVX1-LABEL: var_funnnel_v32i8: ; XOPAVX1: # %bb.0: ; XOPAVX1-NEXT: vandps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm2, %ymm2 @@ -855,12 +871,12 @@ define <4 x i64> @splatvar_funnnel_v4i64(<4 x i64> %x, <4 x i64> %y, <4 x i64> % ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatvar_funnnel_v4i64: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpbroadcastq %xmm2, %ymm2 -; AVX512VLVBMI2-NEXT: vpshrdvq %ymm2, %ymm0, %ymm1 -; AVX512VLVBMI2-NEXT: vmovdqa %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatvar_funnnel_v4i64: +; AVX10: # %bb.0: +; AVX10-NEXT: vpbroadcastq %xmm2, %ymm2 +; AVX10-NEXT: vpshrdvq %ymm2, %ymm0, %ymm1 +; AVX10-NEXT: vmovdqa %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatvar_funnnel_v4i64: ; XOPAVX1: # %bb.0: @@ -974,12 +990,12 @@ define <8 x i32> @splatvar_funnnel_v8i32(<8 x i32> %x, <8 x i32> %y, <8 x i32> % ; AVX512VLBW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm3[0,2],ymm0[4,6],ymm3[4,6] ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatvar_funnnel_v8i32: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpbroadcastd %xmm2, %ymm2 -; AVX512VLVBMI2-NEXT: vpshrdvd %ymm2, %ymm0, %ymm1 -; AVX512VLVBMI2-NEXT: vmovdqa %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatvar_funnnel_v8i32: +; AVX10: # %bb.0: +; AVX10-NEXT: vpbroadcastd %xmm2, %ymm2 +; AVX10-NEXT: vpshrdvd %ymm2, %ymm0, %ymm1 +; AVX10-NEXT: vmovdqa %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatvar_funnnel_v8i32: ; XOPAVX1: # %bb.0: @@ -1096,12 +1112,12 @@ define <16 x i16> @splatvar_funnnel_v16i16(<16 x i16> %x, <16 x i16> %y, <16 x i ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatvar_funnnel_v16i16: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpbroadcastw %xmm2, %ymm2 -; AVX512VLVBMI2-NEXT: vpshrdvw %ymm2, %ymm0, %ymm1 -; AVX512VLVBMI2-NEXT: vmovdqa %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatvar_funnnel_v16i16: +; AVX10: # %bb.0: +; AVX10-NEXT: vpbroadcastw %xmm2, %ymm2 +; AVX10-NEXT: vpshrdvw %ymm2, %ymm0, %ymm1 +; AVX10-NEXT: vmovdqa %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatvar_funnnel_v16i16: ; XOPAVX1: # %bb.0: @@ -1237,16 +1253,16 @@ define <32 x i8> @splatvar_funnnel_v32i8(<32 x i8> %x, <32 x i8> %y, <32 x i8> % ; AVX512VLBW-NEXT: vpackuswb %ymm3, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatvar_funnnel_v32i8: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpunpckhbw {{.*#+}} ymm3 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31] -; AVX512VLVBMI2-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2, %xmm2 -; AVX512VLVBMI2-NEXT: vpsrlw %xmm2, %ymm3, %ymm3 -; AVX512VLVBMI2-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23] -; AVX512VLVBMI2-NEXT: vpsrlw %xmm2, %ymm0, %ymm1 -; AVX512VLVBMI2-NEXT: vmovdqa {{.*#+}} ymm0 = [0,2,4,6,8,10,12,14,32,34,36,38,40,42,44,46,16,18,20,22,24,26,28,30,48,50,52,54,56,58,60,62] -; AVX512VLVBMI2-NEXT: vpermi2b %ymm3, %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatvar_funnnel_v32i8: +; AVX10: # %bb.0: +; AVX10-NEXT: vpunpckhbw {{.*#+}} ymm3 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31] +; AVX10-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2, %xmm2 +; AVX10-NEXT: vpsrlw %xmm2, %ymm3, %ymm3 +; AVX10-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23] +; AVX10-NEXT: vpsrlw %xmm2, %ymm0, %ymm1 +; AVX10-NEXT: vmovdqa {{.*#+}} ymm0 = [0,2,4,6,8,10,12,14,32,34,36,38,40,42,44,46,16,18,20,22,24,26,28,30,48,50,52,54,56,58,60,62] +; AVX10-NEXT: vpermi2b %ymm3, %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatvar_funnnel_v32i8: ; XOPAVX1: # %bb.0: @@ -1360,11 +1376,11 @@ define <4 x i64> @constant_funnnel_v4i64(<4 x i64> %x, <4 x i64> %y) nounwind { ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: constant_funnnel_v4i64: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshrdvq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm1 -; AVX512VLVBMI2-NEXT: vmovdqa %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: constant_funnnel_v4i64: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshrdvq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm1 +; AVX10-NEXT: vmovdqa %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: constant_funnnel_v4i64: ; XOPAVX1: # %bb.0: @@ -1459,11 +1475,11 @@ define <8 x i32> @constant_funnnel_v8i32(<8 x i32> %x, <8 x i32> %y) nounwind { ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: constant_funnnel_v8i32: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshrdvd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm1 -; AVX512VLVBMI2-NEXT: vmovdqa %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: constant_funnnel_v8i32: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshrdvd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm1 +; AVX10-NEXT: vmovdqa %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: constant_funnnel_v8i32: ; XOPAVX1: # %bb.0: @@ -1563,11 +1579,11 @@ define <16 x i16> @constant_funnnel_v16i16(<16 x i16> %x, <16 x i16> %y) nounwin ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: constant_funnnel_v16i16: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshrdvw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm1 -; AVX512VLVBMI2-NEXT: vmovdqa %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: constant_funnnel_v16i16: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshrdvw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm1 +; AVX10-NEXT: vmovdqa %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: constant_funnnel_v16i16: ; XOPAVX1: # %bb.0: @@ -1749,6 +1765,16 @@ define <32 x i8> @constant_funnnel_v32i8(<32 x i8> %x, <32 x i8> %y) nounwind { ; AVX512VLVBMI2-NEXT: vpmovwb %zmm0, %ymm0 ; AVX512VLVBMI2-NEXT: retq ; +; AVX10_256-LABEL: constant_funnnel_v32i8: +; AVX10_256: # %bb.0: +; AVX10_256-NEXT: vpunpckhbw {{.*#+}} ymm2 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31] +; AVX10_256-NEXT: vpsrlvw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm2, %ymm2 +; AVX10_256-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23] +; AVX10_256-NEXT: vpsrlvw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm1 +; AVX10_256-NEXT: vmovdqa {{.*#+}} ymm0 = [0,2,4,6,8,10,12,14,32,34,36,38,40,42,44,46,16,18,20,22,24,26,28,30,48,50,52,54,56,58,60,62] +; AVX10_256-NEXT: vpermi2b %ymm2, %ymm1, %ymm0 +; AVX10_256-NEXT: retq +; ; XOPAVX1-LABEL: constant_funnnel_v32i8: ; XOPAVX1: # %bb.0: ; XOPAVX1-NEXT: vextractf128 $1, %ymm1, %xmm2 @@ -1847,10 +1873,10 @@ define <4 x i64> @splatconstant_funnnel_v4i64(<4 x i64> %x, <4 x i64> %y) nounwi ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatconstant_funnnel_v4i64: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshrdq $14, %ymm0, %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatconstant_funnnel_v4i64: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshrdq $14, %ymm0, %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatconstant_funnnel_v4i64: ; XOPAVX1: # %bb.0: @@ -1932,10 +1958,10 @@ define <8 x i32> @splatconstant_funnnel_v8i32(<8 x i32> %x, <8 x i32> %y) nounwi ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatconstant_funnnel_v8i32: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshrdd $4, %ymm0, %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatconstant_funnnel_v8i32: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshrdd $4, %ymm0, %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatconstant_funnnel_v8i32: ; XOPAVX1: # %bb.0: @@ -2017,10 +2043,10 @@ define <16 x i16> @splatconstant_funnnel_v16i16(<16 x i16> %x, <16 x i16> %y) no ; AVX512VLBW-NEXT: vpor %ymm1, %ymm0, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatconstant_funnnel_v16i16: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpshrdw $7, %ymm0, %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatconstant_funnnel_v16i16: +; AVX10: # %bb.0: +; AVX10-NEXT: vpshrdw $7, %ymm0, %ymm1, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatconstant_funnnel_v16i16: ; XOPAVX1: # %bb.0: @@ -2112,12 +2138,12 @@ define <32 x i8> @splatconstant_funnnel_v32i8(<32 x i8> %x, <32 x i8> %y) nounwi ; AVX512VLBW-NEXT: vpternlogq $216, {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %ymm2, %ymm0 ; AVX512VLBW-NEXT: retq ; -; AVX512VLVBMI2-LABEL: splatconstant_funnnel_v32i8: -; AVX512VLVBMI2: # %bb.0: -; AVX512VLVBMI2-NEXT: vpsllw $4, %ymm0, %ymm2 -; AVX512VLVBMI2-NEXT: vpsrlw $4, %ymm1, %ymm0 -; AVX512VLVBMI2-NEXT: vpternlogq $216, {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %ymm2, %ymm0 -; AVX512VLVBMI2-NEXT: retq +; AVX10-LABEL: splatconstant_funnnel_v32i8: +; AVX10: # %bb.0: +; AVX10-NEXT: vpsllw $4, %ymm0, %ymm2 +; AVX10-NEXT: vpsrlw $4, %ymm1, %ymm0 +; AVX10-NEXT: vpternlogq $216, {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %ymm2, %ymm0 +; AVX10-NEXT: retq ; ; XOPAVX1-LABEL: splatconstant_funnnel_v32i8: ; XOPAVX1: # %bb.0: