maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics 

llvm-svn: 274439
This commit is contained in:
Simon Pilgrim 2016-07-02 14:42:35 +00:00
parent 52a692d28d
commit 19adee9d84
5 changed files with 227 additions and 204 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
llvm/lib/IR/AutoUpgrade.cpp
View File

@ -219,6 +219,9 @@ static bool UpgradeIntrinsicFunction1(Function *F, Function *&NewFn) {
Name.startswith("x86.avx2.pbroadcast") || Name.startswith("x86.avx2.pbroadcast") ||
Name.startswith("x86.avx.vpermil.") || Name.startswith("x86.avx.vpermil.") ||
Name.startswith("x86.sse2.pshuf") || Name.startswith("x86.sse2.pshuf") ||
Name.startswith("x86.avx512.mask.movddup") ||
Name.startswith("x86.avx512.mask.movshdup") ||
Name.startswith("x86.avx512.mask.movsldup") ||
Name.startswith("x86.avx512.mask.pshuf.d.") || Name.startswith("x86.avx512.mask.pshuf.d.") ||
Name.startswith("x86.avx512.mask.pshufl.w.") || Name.startswith("x86.avx512.mask.pshufl.w.") ||
Name.startswith("x86.avx512.mask.pshufh.w.") || Name.startswith("x86.avx512.mask.pshufh.w.") ||
@ -1063,6 +1066,28 @@ void llvm::UpgradeIntrinsicCall(CallInst *CI, Function *NewFn) {
if (CI->getNumArgOperands() == 4) if (CI->getNumArgOperands() == 4)
Rep = EmitX86Select(Builder, CI->getArgOperand(3), Rep, Rep = EmitX86Select(Builder, CI->getArgOperand(3), Rep,
CI->getArgOperand(2)); CI->getArgOperand(2));
} else if (Name.startswith("llvm.x86.avx512.mask.movddup") ||
Name.startswith("llvm.x86.avx512.mask.movshdup") ||
Name.startswith("llvm.x86.avx512.mask.movsldup")) {
Value *Op0 = CI->getArgOperand(0);
unsigned NumElts = CI->getType()->getVectorNumElements();
unsigned NumLaneElts = 128/CI->getType()->getScalarSizeInBits();
unsigned Offset = 0;
if (Name.startswith("llvm.x86.avx512.mask.movshdup."))
Offset = 1;
SmallVector<uint32_t, 16> Idxs(NumElts);
for (unsigned l = 0; l != NumElts; l += NumLaneElts)
for (unsigned i = 0; i != NumLaneElts; i += 2) {
Idxs[i + l + 0] = i + l + Offset;
Idxs[i + l + 1] = i + l + Offset;
}
Rep = Builder.CreateShuffleVector(Op0, Op0, Idxs);
Rep = EmitX86Select(Builder, CI->getArgOperand(2), Rep,
CI->getArgOperand(1));
} else if (Name.startswith("llvm.x86.avx512.mask.punpckl") || } else if (Name.startswith("llvm.x86.avx512.mask.punpckl") ||
Name.startswith("llvm.x86.avx512.mask.unpckl.")) { Name.startswith("llvm.x86.avx512.mask.unpckl.")) {
Value *Op0 = CI->getArgOperand(0); Value *Op0 = CI->getArgOperand(0);

60
llvm/test/CodeGen/X86/avx512-intrinsics-upgrade.ll
View File

@ -1,6 +1,66 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s ; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s
declare <16 x float> @llvm.x86.avx512.mask.movsldup.512(<16 x float>, <16 x float>, i16)
define <16 x float>@test_int_x86_avx512_mask_movsldup_512(<16 x float> %x0, <16 x float> %x1, i16 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movsldup_512:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovsldup {{.*#+}} zmm2 = zmm0[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14]
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovsldup {{.*#+}} zmm1 = zmm0[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14]
; CHECK-NEXT: vmovsldup {{.*#+}} zmm0 = zmm0[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14]
; CHECK-NEXT: vaddps %zmm2, %zmm1, %zmm1
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm0
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.movsldup.512(<16 x float> %x0, <16 x float> %x1, i16 %x2)
%res1 = call <16 x float> @llvm.x86.avx512.mask.movsldup.512(<16 x float> %x0, <16 x float> %x1, i16 -1)
%res2 = call <16 x float> @llvm.x86.avx512.mask.movsldup.512(<16 x float> %x0, <16 x float> zeroinitializer, i16 %x2)
%res3 = fadd <16 x float> %res, %res1
%res4 = fadd <16 x float> %res2, %res3
ret <16 x float> %res4
}
declare <16 x float> @llvm.x86.avx512.mask.movshdup.512(<16 x float>, <16 x float>, i16)
define <16 x float>@test_int_x86_avx512_mask_movshdup_512(<16 x float> %x0, <16 x float> %x1, i16 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movshdup_512:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovshdup {{.*#+}} zmm2 = zmm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15]
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovshdup {{.*#+}} zmm1 = zmm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15]
; CHECK-NEXT: vmovshdup {{.*#+}} zmm0 = zmm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15]
; CHECK-NEXT: vaddps %zmm2, %zmm1, %zmm1
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm0
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.movshdup.512(<16 x float> %x0, <16 x float> %x1, i16 %x2)
%res1 = call <16 x float> @llvm.x86.avx512.mask.movshdup.512(<16 x float> %x0, <16 x float> %x1, i16 -1)
%res2 = call <16 x float> @llvm.x86.avx512.mask.movshdup.512(<16 x float> %x0, <16 x float> zeroinitializer, i16 %x2)
%res3 = fadd <16 x float> %res, %res1
%res4 = fadd <16 x float> %res2, %res3
ret <16 x float> %res4
}
declare <8 x double> @llvm.x86.avx512.mask.movddup.512(<8 x double>, <8 x double>, i8)
define <8 x double>@test_int_x86_avx512_mask_movddup_512(<8 x double> %x0, <8 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movddup_512:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovddup {{.*#+}} zmm2 = zmm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovddup {{.*#+}} zmm1 = zmm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: vmovddup {{.*#+}} zmm0 = zmm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: vaddpd %zmm2, %zmm1, %zmm1
; CHECK-NEXT: vaddpd %zmm1, %zmm0, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.movddup.512(<8 x double> %x0, <8 x double> %x1, i8 %x2)
%res1 = call <8 x double> @llvm.x86.avx512.mask.movddup.512(<8 x double> %x0, <8 x double> %x1, i8 -1)
%res2 = call <8 x double> @llvm.x86.avx512.mask.movddup.512(<8 x double> %x0, <8 x double> zeroinitializer, i8 %x2)
%res3 = fadd <8 x double> %res, %res1
%res4 = fadd <8 x double> %res2, %res3
ret <8 x double> %res4
}
define void @test_store1(<16 x float> %data, i8* %ptr, i8* %ptr2, i16 %mask) { define void @test_store1(<16 x float> %data, i8* %ptr, i8* %ptr2, i16 %mask) {
; CHECK-LABEL: test_store1: ; CHECK-LABEL: test_store1:
; CHECK: ## BB#0: ; CHECK: ## BB#0:

61
llvm/test/CodeGen/X86/avx512-intrinsics.ll
View File

@ -1,4 +1,3 @@
; NOTE: Assertions have been autogenerated by update_llc_test_checks.py
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s ; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s
@ -5701,66 +5700,6 @@ define <8 x i64>@test_int_x86_avx512_maskz_pternlog_q_512(<8 x i64> %x0, <8 x i6
ret <8 x i64> %res2 ret <8 x i64> %res2
} }
declare <16 x float> @llvm.x86.avx512.mask.movsldup.512(<16 x float>, <16 x float>, i16)
define <16 x float>@test_int_x86_avx512_mask_movsldup_512(<16 x float> %x0, <16 x float> %x1, i16 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movsldup_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovsldup {{.*#+}} zmm1 = zmm0[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14]
; CHECK-NEXT: vmovsldup {{.*#+}} zmm2 = zmm0[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14]
; CHECK-NEXT: vmovsldup {{.*#+}} zmm0 = zmm0[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14]
; CHECK-NEXT: vaddps %zmm0, %zmm1, %zmm0
; CHECK-NEXT: vaddps %zmm0, %zmm2, %zmm0
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.movsldup.512(<16 x float> %x0, <16 x float> %x1, i16 %x2)
%res1 = call <16 x float> @llvm.x86.avx512.mask.movsldup.512(<16 x float> %x0, <16 x float> %x1, i16 -1)
%res2 = call <16 x float> @llvm.x86.avx512.mask.movsldup.512(<16 x float> %x0, <16 x float> zeroinitializer, i16 %x2)
%res3 = fadd <16 x float> %res, %res1
%res4 = fadd <16 x float> %res2, %res3
ret <16 x float> %res4
}
declare <16 x float> @llvm.x86.avx512.mask.movshdup.512(<16 x float>, <16 x float>, i16)
define <16 x float>@test_int_x86_avx512_mask_movshdup_512(<16 x float> %x0, <16 x float> %x1, i16 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movshdup_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovshdup {{.*#+}} zmm1 = zmm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15]
; CHECK-NEXT: vmovshdup {{.*#+}} zmm2 = zmm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15]
; CHECK-NEXT: vmovshdup {{.*#+}} zmm0 = zmm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15]
; CHECK-NEXT: vaddps %zmm0, %zmm1, %zmm0
; CHECK-NEXT: vaddps %zmm0, %zmm2, %zmm0
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.movshdup.512(<16 x float> %x0, <16 x float> %x1, i16 %x2)
%res1 = call <16 x float> @llvm.x86.avx512.mask.movshdup.512(<16 x float> %x0, <16 x float> %x1, i16 -1)
%res2 = call <16 x float> @llvm.x86.avx512.mask.movshdup.512(<16 x float> %x0, <16 x float> zeroinitializer, i16 %x2)
%res3 = fadd <16 x float> %res, %res1
%res4 = fadd <16 x float> %res2, %res3
ret <16 x float> %res4
}
declare <8 x double> @llvm.x86.avx512.mask.movddup.512(<8 x double>, <8 x double>, i8)
define <8 x double>@test_int_x86_avx512_mask_movddup_512(<8 x double> %x0, <8 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movddup_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovddup {{.*#+}} zmm1 = zmm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: vmovddup {{.*#+}} zmm2 = zmm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: vmovddup {{.*#+}} zmm0 = zmm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: vaddpd %zmm0, %zmm1, %zmm0
; CHECK-NEXT: vaddpd %zmm0, %zmm2, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.movddup.512(<8 x double> %x0, <8 x double> %x1, i8 %x2)
%res1 = call <8 x double> @llvm.x86.avx512.mask.movddup.512(<8 x double> %x0, <8 x double> %x1, i8 -1)
%res2 = call <8 x double> @llvm.x86.avx512.mask.movddup.512(<8 x double> %x0, <8 x double> zeroinitializer, i8 %x2)
%res3 = fadd <8 x double> %res, %res1
%res4 = fadd <8 x double> %res2, %res3
ret <8 x double> %res4
}
define i32 @test_x86_avx512_comi_sd_eq_sae(<2 x double> %a0, <2 x double> %a1) { define i32 @test_x86_avx512_comi_sd_eq_sae(<2 x double> %a0, <2 x double> %a1) {
; CHECK-LABEL: test_x86_avx512_comi_sd_eq_sae: ; CHECK-LABEL: test_x86_avx512_comi_sd_eq_sae:
; CHECK: ## BB#0: ; CHECK: ## BB#0:

139
llvm/test/CodeGen/X86/avx512vl-intrinsics-upgrade.ll
View File

@ -1,6 +1,143 @@
; NOTE: Assertions have been autogenerated by update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl -mattr=+avx512vl --show-mc-encoding| FileCheck %s ; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl -mattr=+avx512vl --show-mc-encoding| FileCheck %s
declare <4 x float> @llvm.x86.avx512.mask.movsldup.128(<4 x float>, <4 x float>, i8)
define <4 x float>@test_int_x86_avx512_mask_movsldup_128(<4 x float> %x0, <4 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movsldup_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovsldup %xmm0, %xmm2 ## encoding: [0x62,0xf1,0x7e,0x08,0x12,0xd0]
; CHECK-NEXT: ## xmm2 = xmm0[0,0,2,2]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovsldup %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7e,0x09,0x12,0xc8]
; CHECK-NEXT: ## xmm1 = xmm0[0,0,2,2]
; CHECK-NEXT: vmovsldup %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0x89,0x12,0xc0]
; CHECK-NEXT: ## xmm0 = xmm0[0,0,2,2]
; CHECK-NEXT: vaddps %xmm2, %xmm1, %xmm1 ## encoding: [0x62,0xf1,0x74,0x08,0x58,0xca]
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.movsldup.128(<4 x float> %x0, <4 x float> %x1, i8 %x2)
%res1 = call <4 x float> @llvm.x86.avx512.mask.movsldup.128(<4 x float> %x0, <4 x float> %x1, i8 -1)
%res2 = call <4 x float> @llvm.x86.avx512.mask.movsldup.128(<4 x float> %x0, <4 x float> zeroinitializer, i8 %x2)
%res3 = fadd <4 x float> %res, %res1
%res4 = fadd <4 x float> %res2, %res3
ret <4 x float> %res4
}
declare <8 x float> @llvm.x86.avx512.mask.movsldup.256(<8 x float>, <8 x float>, i8)
define <8 x float>@test_int_x86_avx512_mask_movsldup_256(<8 x float> %x0, <8 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movsldup_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovsldup %ymm0, %ymm2 ## encoding: [0x62,0xf1,0x7e,0x28,0x12,0xd0]
; CHECK-NEXT: ## ymm2 = ymm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovsldup %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7e,0x29,0x12,0xc8]
; CHECK-NEXT: ## ymm1 = ymm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: vmovsldup %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0xa9,0x12,0xc0]
; CHECK-NEXT: ## ymm0 = ymm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: vaddps %ymm2, %ymm1, %ymm1 ## encoding: [0x62,0xf1,0x74,0x28,0x58,0xca]
; CHECK-NEXT: vaddps %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.movsldup.256(<8 x float> %x0, <8 x float> %x1, i8 %x2)
%res1 = call <8 x float> @llvm.x86.avx512.mask.movsldup.256(<8 x float> %x0, <8 x float> %x1, i8 -1)
%res2 = call <8 x float> @llvm.x86.avx512.mask.movsldup.256(<8 x float> %x0, <8 x float> zeroinitializer, i8 %x2)
%res3 = fadd <8 x float> %res, %res1
%res4 = fadd <8 x float> %res2, %res3
ret <8 x float> %res4
}
declare <4 x float> @llvm.x86.avx512.mask.movshdup.128(<4 x float>, <4 x float>, i8)
define <4 x float>@test_int_x86_avx512_mask_movshdup_128(<4 x float> %x0, <4 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movshdup_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovshdup %xmm0, %xmm2 ## encoding: [0x62,0xf1,0x7e,0x08,0x16,0xd0]
; CHECK-NEXT: ## xmm2 = xmm0[1,1,3,3]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovshdup %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7e,0x09,0x16,0xc8]
; CHECK-NEXT: ## xmm1 = xmm0[1,1,3,3]
; CHECK-NEXT: vmovshdup %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0x89,0x16,0xc0]
; CHECK-NEXT: ## xmm0 = xmm0[1,1,3,3]
; CHECK-NEXT: vaddps %xmm2, %xmm1, %xmm1 ## encoding: [0x62,0xf1,0x74,0x08,0x58,0xca]
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.movshdup.128(<4 x float> %x0, <4 x float> %x1, i8 %x2)
%res1 = call <4 x float> @llvm.x86.avx512.mask.movshdup.128(<4 x float> %x0, <4 x float> %x1, i8 -1)
%res2 = call <4 x float> @llvm.x86.avx512.mask.movshdup.128(<4 x float> %x0, <4 x float> zeroinitializer, i8 %x2)
%res3 = fadd <4 x float> %res, %res1
%res4 = fadd <4 x float> %res2, %res3
ret <4 x float> %res4
}
declare <8 x float> @llvm.x86.avx512.mask.movshdup.256(<8 x float>, <8 x float>, i8)
define <8 x float>@test_int_x86_avx512_mask_movshdup_256(<8 x float> %x0, <8 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movshdup_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovshdup %ymm0, %ymm2 ## encoding: [0x62,0xf1,0x7e,0x28,0x16,0xd0]
; CHECK-NEXT: ## ymm2 = ymm0[1,1,3,3,5,5,7,7]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovshdup %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7e,0x29,0x16,0xc8]
; CHECK-NEXT: ## ymm1 = ymm0[1,1,3,3,5,5,7,7]
; CHECK-NEXT: vmovshdup %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0xa9,0x16,0xc0]
; CHECK-NEXT: ## ymm0 = ymm0[1,1,3,3,5,5,7,7]
; CHECK-NEXT: vaddps %ymm2, %ymm1, %ymm1 ## encoding: [0x62,0xf1,0x74,0x28,0x58,0xca]
; CHECK-NEXT: vaddps %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.movshdup.256(<8 x float> %x0, <8 x float> %x1, i8 %x2)
%res1 = call <8 x float> @llvm.x86.avx512.mask.movshdup.256(<8 x float> %x0, <8 x float> %x1, i8 -1)
%res2 = call <8 x float> @llvm.x86.avx512.mask.movshdup.256(<8 x float> %x0, <8 x float> zeroinitializer, i8 %x2)
%res3 = fadd <8 x float> %res, %res1
%res4 = fadd <8 x float> %res2, %res3
ret <8 x float> %res4
}
declare <2 x double> @llvm.x86.avx512.mask.movddup.128(<2 x double>, <2 x double>, i8)
define <2 x double>@test_int_x86_avx512_mask_movddup_128(<2 x double> %x0, <2 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movddup_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovddup %xmm0, %xmm2 ## encoding: [0x62,0xf1,0xff,0x08,0x12,0xd0]
; CHECK-NEXT: ## xmm2 = xmm0[0,0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovddup %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0xff,0x09,0x12,0xc8]
; CHECK-NEXT: ## xmm1 = xmm0[0,0]
; CHECK-NEXT: vmovddup %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0xff,0x89,0x12,0xc0]
; CHECK-NEXT: ## xmm0 = xmm0[0,0]
; CHECK-NEXT: vaddpd %xmm2, %xmm1, %xmm1 ## encoding: [0x62,0xf1,0xf5,0x08,0x58,0xca]
; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask.movddup.128(<2 x double> %x0, <2 x double> %x1, i8 %x2)
%res1 = call <2 x double> @llvm.x86.avx512.mask.movddup.128(<2 x double> %x0, <2 x double> %x1, i8 -1)
%res2 = call <2 x double> @llvm.x86.avx512.mask.movddup.128(<2 x double> %x0, <2 x double> zeroinitializer, i8 %x2)
%res3 = fadd <2 x double> %res, %res1
%res4 = fadd <2 x double> %res2, %res3
ret <2 x double> %res4
}
declare <4 x double> @llvm.x86.avx512.mask.movddup.256(<4 x double>, <4 x double>, i8)
define <4 x double>@test_int_x86_avx512_mask_movddup_256(<4 x double> %x0, <4 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movddup_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovddup %ymm0, %ymm2 ## encoding: [0x62,0xf1,0xff,0x28,0x12,0xd0]
; CHECK-NEXT: ## ymm2 = ymm0[0,0,2,2]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovddup %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0xff,0x29,0x12,0xc8]
; CHECK-NEXT: ## ymm1 = ymm0[0,0,2,2]
; CHECK-NEXT: vmovddup %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0xff,0xa9,0x12,0xc0]
; CHECK-NEXT: ## ymm0 = ymm0[0,0,2,2]
; CHECK-NEXT: vaddpd %ymm2, %ymm1, %ymm1 ## encoding: [0x62,0xf1,0xf5,0x28,0x58,0xca]
; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x double> @llvm.x86.avx512.mask.movddup.256(<4 x double> %x0, <4 x double> %x1, i8 %x2)
%res1 = call <4 x double> @llvm.x86.avx512.mask.movddup.256(<4 x double> %x0, <4 x double> %x1, i8 -1)
%res2 = call <4 x double> @llvm.x86.avx512.mask.movddup.256(<4 x double> %x0, <4 x double> zeroinitializer, i8 %x2)
%res3 = fadd <4 x double> %res, %res1
%res4 = fadd <4 x double> %res2, %res3
ret <4 x double> %res4
}
declare void @llvm.x86.avx512.mask.store.pd.128(i8*, <2 x double>, i8) declare void @llvm.x86.avx512.mask.store.pd.128(i8*, <2 x double>, i8)
define void@test_int_x86_avx512_mask_store_pd_128(i8* %ptr1, i8* %ptr2, <2 x double> %x1, i8 %x2) { define void@test_int_x86_avx512_mask_store_pd_128(i8* %ptr1, i8* %ptr2, <2 x double> %x1, i8 %x2) {

146
llvm/test/CodeGen/X86/avx512vl-intrinsics.ll
View File

@ -1,5 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; NOTE: Assertions have been autogenerated by update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl -mattr=+avx512vl --show-mc-encoding| FileCheck %s ; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl -mattr=+avx512vl --show-mc-encoding| FileCheck %s
; 256-bit ; 256-bit
@ -6259,143 +6258,6 @@ define <8 x i16> @test_x86_vcvtps2ph_256(<8 x float> %a0, i8 %mask, <8 x i16> %s
declare <8 x i16> @llvm.x86.avx512.mask.vcvtps2ph.256(<8 x float>, i32, <8 x i16>, i8) nounwind readonly declare <8 x i16> @llvm.x86.avx512.mask.vcvtps2ph.256(<8 x float>, i32, <8 x i16>, i8) nounwind readonly
declare <4 x float> @llvm.x86.avx512.mask.movsldup.128(<4 x float>, <4 x float>, i8)
define <4 x float>@test_int_x86_avx512_mask_movsldup_128(<4 x float> %x0, <4 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movsldup_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovsldup %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7e,0x09,0x12,0xc8]
; CHECK-NEXT: ## xmm1 = xmm0[0,0,2,2]
; CHECK-NEXT: vmovsldup %xmm0, %xmm2 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0x89,0x12,0xd0]
; CHECK-NEXT: ## xmm2 = xmm0[0,0,2,2]
; CHECK-NEXT: vmovsldup %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7e,0x08,0x12,0xc0]
; CHECK-NEXT: ## xmm0 = xmm0[0,0,2,2]
; CHECK-NEXT: vaddps %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0x74,0x08,0x58,0xc0]
; CHECK-NEXT: vaddps %xmm0, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x6c,0x08,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.movsldup.128(<4 x float> %x0, <4 x float> %x1, i8 %x2)
%res1 = call <4 x float> @llvm.x86.avx512.mask.movsldup.128(<4 x float> %x0, <4 x float> %x1, i8 -1)
%res2 = call <4 x float> @llvm.x86.avx512.mask.movsldup.128(<4 x float> %x0, <4 x float> zeroinitializer, i8 %x2)
%res3 = fadd <4 x float> %res, %res1
%res4 = fadd <4 x float> %res2, %res3
ret <4 x float> %res4
}
declare <8 x float> @llvm.x86.avx512.mask.movsldup.256(<8 x float>, <8 x float>, i8)
define <8 x float>@test_int_x86_avx512_mask_movsldup_256(<8 x float> %x0, <8 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movsldup_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovsldup %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7e,0x29,0x12,0xc8]
; CHECK-NEXT: ## ymm1 = ymm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: vmovsldup %ymm0, %ymm2 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0xa9,0x12,0xd0]
; CHECK-NEXT: ## ymm2 = ymm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: vmovsldup %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7e,0x28,0x12,0xc0]
; CHECK-NEXT: ## ymm0 = ymm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: vaddps %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0x74,0x28,0x58,0xc0]
; CHECK-NEXT: vaddps %ymm0, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x6c,0x28,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.movsldup.256(<8 x float> %x0, <8 x float> %x1, i8 %x2)
%res1 = call <8 x float> @llvm.x86.avx512.mask.movsldup.256(<8 x float> %x0, <8 x float> %x1, i8 -1)
%res2 = call <8 x float> @llvm.x86.avx512.mask.movsldup.256(<8 x float> %x0, <8 x float> zeroinitializer, i8 %x2)
%res3 = fadd <8 x float> %res, %res1
%res4 = fadd <8 x float> %res2, %res3
ret <8 x float> %res4
}
declare <4 x float> @llvm.x86.avx512.mask.movshdup.128(<4 x float>, <4 x float>, i8)
define <4 x float>@test_int_x86_avx512_mask_movshdup_128(<4 x float> %x0, <4 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movshdup_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovshdup %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7e,0x09,0x16,0xc8]
; CHECK-NEXT: ## xmm1 = xmm0[1,1,3,3]
; CHECK-NEXT: vmovshdup %xmm0, %xmm2 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0x89,0x16,0xd0]
; CHECK-NEXT: ## xmm2 = xmm0[1,1,3,3]
; CHECK-NEXT: vmovshdup %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7e,0x08,0x16,0xc0]
; CHECK-NEXT: ## xmm0 = xmm0[1,1,3,3]
; CHECK-NEXT: vaddps %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0x74,0x08,0x58,0xc0]
; CHECK-NEXT: vaddps %xmm0, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x6c,0x08,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.movshdup.128(<4 x float> %x0, <4 x float> %x1, i8 %x2)
%res1 = call <4 x float> @llvm.x86.avx512.mask.movshdup.128(<4 x float> %x0, <4 x float> %x1, i8 -1)
%res2 = call <4 x float> @llvm.x86.avx512.mask.movshdup.128(<4 x float> %x0, <4 x float> zeroinitializer, i8 %x2)
%res3 = fadd <4 x float> %res, %res1
%res4 = fadd <4 x float> %res2, %res3
ret <4 x float> %res4
}
declare <8 x float> @llvm.x86.avx512.mask.movshdup.256(<8 x float>, <8 x float>, i8)
define <8 x float>@test_int_x86_avx512_mask_movshdup_256(<8 x float> %x0, <8 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movshdup_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovshdup %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7e,0x29,0x16,0xc8]
; CHECK-NEXT: ## ymm1 = ymm0[1,1,3,3,5,5,7,7]
; CHECK-NEXT: vmovshdup %ymm0, %ymm2 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0xa9,0x16,0xd0]
; CHECK-NEXT: ## ymm2 = ymm0[1,1,3,3,5,5,7,7]
; CHECK-NEXT: vmovshdup %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7e,0x28,0x16,0xc0]
; CHECK-NEXT: ## ymm0 = ymm0[1,1,3,3,5,5,7,7]
; CHECK-NEXT: vaddps %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0x74,0x28,0x58,0xc0]
; CHECK-NEXT: vaddps %ymm0, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x6c,0x28,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.movshdup.256(<8 x float> %x0, <8 x float> %x1, i8 %x2)
%res1 = call <8 x float> @llvm.x86.avx512.mask.movshdup.256(<8 x float> %x0, <8 x float> %x1, i8 -1)
%res2 = call <8 x float> @llvm.x86.avx512.mask.movshdup.256(<8 x float> %x0, <8 x float> zeroinitializer, i8 %x2)
%res3 = fadd <8 x float> %res, %res1
%res4 = fadd <8 x float> %res2, %res3
ret <8 x float> %res4
}
declare <2 x double> @llvm.x86.avx512.mask.movddup.128(<2 x double>, <2 x double>, i8)
define <2 x double>@test_int_x86_avx512_mask_movddup_128(<2 x double> %x0, <2 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movddup_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovddup %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0xff,0x09,0x12,0xc8]
; CHECK-NEXT: ## xmm1 = xmm0[0,0]
; CHECK-NEXT: vmovddup %xmm0, %xmm2 {%k1} {z} ## encoding: [0x62,0xf1,0xff,0x89,0x12,0xd0]
; CHECK-NEXT: ## xmm2 = xmm0[0,0]
; CHECK-NEXT: vmovddup %xmm0, %xmm0 ## encoding: [0x62,0xf1,0xff,0x08,0x12,0xc0]
; CHECK-NEXT: ## xmm0 = xmm0[0,0]
; CHECK-NEXT: vaddpd %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xf5,0x08,0x58,0xc0]
; CHECK-NEXT: vaddpd %xmm0, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xed,0x08,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask.movddup.128(<2 x double> %x0, <2 x double> %x1, i8 %x2)
%res1 = call <2 x double> @llvm.x86.avx512.mask.movddup.128(<2 x double> %x0, <2 x double> %x1, i8 -1)
%res2 = call <2 x double> @llvm.x86.avx512.mask.movddup.128(<2 x double> %x0, <2 x double> zeroinitializer, i8 %x2)
%res3 = fadd <2 x double> %res, %res1
%res4 = fadd <2 x double> %res2, %res3
ret <2 x double> %res4
}
declare <4 x double> @llvm.x86.avx512.mask.movddup.256(<4 x double>, <4 x double>, i8)
define <4 x double>@test_int_x86_avx512_mask_movddup_256(<4 x double> %x0, <4 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movddup_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovddup %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0xff,0x29,0x12,0xc8]
; CHECK-NEXT: ## ymm1 = ymm0[0,0,2,2]
; CHECK-NEXT: vmovddup %ymm0, %ymm2 {%k1} {z} ## encoding: [0x62,0xf1,0xff,0xa9,0x12,0xd0]
; CHECK-NEXT: ## ymm2 = ymm0[0,0,2,2]
; CHECK-NEXT: vmovddup %ymm0, %ymm0 ## encoding: [0x62,0xf1,0xff,0x28,0x12,0xc0]
; CHECK-NEXT: ## ymm0 = ymm0[0,0,2,2]
; CHECK-NEXT: vaddpd %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xf5,0x28,0x58,0xc0]
; CHECK-NEXT: vaddpd %ymm0, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xed,0x28,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x double> @llvm.x86.avx512.mask.movddup.256(<4 x double> %x0, <4 x double> %x1, i8 %x2)
%res1 = call <4 x double> @llvm.x86.avx512.mask.movddup.256(<4 x double> %x0, <4 x double> %x1, i8 -1)
%res2 = call <4 x double> @llvm.x86.avx512.mask.movddup.256(<4 x double> %x0, <4 x double> zeroinitializer, i8 %x2)
%res3 = fadd <4 x double> %res, %res1
%res4 = fadd <4 x double> %res2, %res3
ret <4 x double> %res4
}
define <8 x float> @test_rsqrt_ps_256_rr(<8 x float> %a0) { define <8 x float> @test_rsqrt_ps_256_rr(<8 x float> %a0) {
; CHECK-LABEL: test_rsqrt_ps_256_rr: ; CHECK-LABEL: test_rsqrt_ps_256_rr:
; CHECK: ## BB#0: ; CHECK: ## BB#0:
@ -7356,9 +7218,9 @@ define <8 x i32>@test_int_x86_avx512_mask_psrav8_si_const() {
; CHECK: ## BB#0: ; CHECK: ## BB#0:
; CHECK-NEXT: vmovdqa32 {{.*#+}} ymm0 = [2,9,4294967284,23,4294967270,37,4294967256,51] ; CHECK-NEXT: vmovdqa32 {{.*#+}} ymm0 = [2,9,4294967284,23,4294967270,37,4294967256,51]
; CHECK-NEXT: ## encoding: [0x62,0xf1,0x7d,0x28,0x6f,0x05,A,A,A,A] ; CHECK-NEXT: ## encoding: [0x62,0xf1,0x7d,0x28,0x6f,0x05,A,A,A,A]
; CHECK-NEXT: ## fixup A - offset: 6, value: LCPI478_0-4, kind: reloc_riprel_4byte ; CHECK-NEXT: ## fixup A - offset: 6, value: LCPI472_0-4, kind: reloc_riprel_4byte
; CHECK-NEXT: vpsravd {{.*}}(%rip), %ymm0, %ymm0 ## encoding: [0x62,0xf2,0x7d,0x28,0x46,0x05,A,A,A,A] ; CHECK-NEXT: vpsravd {{.*}}(%rip), %ymm0, %ymm0 ## encoding: [0x62,0xf2,0x7d,0x28,0x46,0x05,A,A,A,A]
; CHECK-NEXT: ## fixup A - offset: 6, value: LCPI478_1-4, kind: reloc_riprel_4byte ; CHECK-NEXT: ## fixup A - offset: 6, value: LCPI472_1-4, kind: reloc_riprel_4byte
; CHECK-NEXT: retq ## encoding: [0xc3] ; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.psrav8.si(<8 x i32> <i32 2, i32 9, i32 -12, i32 23, i32 -26, i32 37, i32 -40, i32 51>, <8 x i32> <i32 1, i32 18, i32 35, i32 52, i32 69, i32 15, i32 32, i32 49>, <8 x i32> zeroinitializer, i8 -1) %res = call <8 x i32> @llvm.x86.avx512.mask.psrav8.si(<8 x i32> <i32 2, i32 9, i32 -12, i32 23, i32 -26, i32 37, i32 -40, i32 51>, <8 x i32> <i32 1, i32 18, i32 35, i32 52, i32 69, i32 15, i32 32, i32 49>, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res ret <8 x i32> %res
@ -7389,9 +7251,9 @@ define <2 x i64>@test_int_x86_avx512_mask_psrav_q_128_const(i8 %x3) {
; CHECK: ## BB#0: ; CHECK: ## BB#0:
; CHECK-NEXT: vmovdqa64 {{.*#+}} xmm0 = [2,18446744073709551607] ; CHECK-NEXT: vmovdqa64 {{.*#+}} xmm0 = [2,18446744073709551607]
; CHECK-NEXT: ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0x05,A,A,A,A] ; CHECK-NEXT: ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0x05,A,A,A,A]
; CHECK-NEXT: ## fixup A - offset: 6, value: LCPI480_0-4, kind: reloc_riprel_4byte ; CHECK-NEXT: ## fixup A - offset: 6, value: LCPI474_0-4, kind: reloc_riprel_4byte
; CHECK-NEXT: vpsravq {{.*}}(%rip), %xmm0, %xmm0 ## encoding: [0x62,0xf2,0xfd,0x08,0x46,0x05,A,A,A,A] ; CHECK-NEXT: vpsravq {{.*}}(%rip), %xmm0, %xmm0 ## encoding: [0x62,0xf2,0xfd,0x08,0x46,0x05,A,A,A,A]
; CHECK-NEXT: ## fixup A - offset: 6, value: LCPI480_1-4, kind: reloc_riprel_4byte ; CHECK-NEXT: ## fixup A - offset: 6, value: LCPI474_1-4, kind: reloc_riprel_4byte
; CHECK-NEXT: retq ## encoding: [0xc3] ; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.psrav.q.128(<2 x i64> <i64 2, i64 -9>, <2 x i64> <i64 1, i64 90>, <2 x i64> zeroinitializer, i8 -1) %res = call <2 x i64> @llvm.x86.avx512.mask.psrav.q.128(<2 x i64> <i64 2, i64 -9>, <2 x i64> <i64 1, i64 90>, <2 x i64> zeroinitializer, i8 -1)
ret <2 x i64> %res ret <2 x i64> %res