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

[AVX-512] Remove masked packss/packus intrinsics and autoupgrade to unmasked intrinsics with select instructions. For 512-bit add new unmasked intrinsics. 

The new 512-bit unmasked intrinsics will make it easy to handle these with the SSE/AVX intrinsics in InstCombine where we currently have a TODO.

llvm-svn: 295290
This commit is contained in:
Craig Topper 2017-02-16 06:31:54 +00:00
parent cd19b039ce
commit 715873ead3
7 changed files with 1589 additions and 264 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
llvm/include/llvm/IR/IntrinsicsX86.td
View File

@ -3913,42 +3913,18 @@ let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
// Pack ops.
let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
def int_x86_avx512_mask_packsswb_128 : GCCBuiltin<"__builtin_ia32_packsswb128_mask">,
Intrinsic<[llvm_v16i8_ty], [llvm_v8i16_ty, llvm_v8i16_ty,
llvm_v16i8_ty, llvm_i16_ty], [IntrNoMem]>;
def int_x86_avx512_mask_packsswb_256 : GCCBuiltin<"__builtin_ia32_packsswb256_mask">,
Intrinsic<[llvm_v32i8_ty], [llvm_v16i16_ty,llvm_v16i16_ty,
llvm_v32i8_ty, llvm_i32_ty], [IntrNoMem]>;
def int_x86_avx512_mask_packsswb_512 : GCCBuiltin<"__builtin_ia32_packsswb512_mask">,
Intrinsic<[llvm_v64i8_ty], [llvm_v32i16_ty,llvm_v32i16_ty,
llvm_v64i8_ty, llvm_i64_ty], [IntrNoMem]>;
def int_x86_avx512_mask_packssdw_128 : GCCBuiltin<"__builtin_ia32_packssdw128_mask">,
Intrinsic<[llvm_v8i16_ty], [llvm_v4i32_ty, llvm_v4i32_ty,
llvm_v8i16_ty, llvm_i8_ty], [IntrNoMem]>;
def int_x86_avx512_mask_packssdw_256 : GCCBuiltin<"__builtin_ia32_packssdw256_mask">,
Intrinsic<[llvm_v16i16_ty], [llvm_v8i32_ty, llvm_v8i32_ty,
llvm_v16i16_ty, llvm_i16_ty], [IntrNoMem]>;
def int_x86_avx512_mask_packssdw_512 : GCCBuiltin<"__builtin_ia32_packssdw512_mask">,
Intrinsic<[llvm_v32i16_ty], [llvm_v16i32_ty, llvm_v16i32_ty,
llvm_v32i16_ty, llvm_i32_ty], [IntrNoMem]>;
def int_x86_avx512_mask_packuswb_128 : GCCBuiltin<"__builtin_ia32_packuswb128_mask">,
Intrinsic<[llvm_v16i8_ty], [llvm_v8i16_ty, llvm_v8i16_ty,
llvm_v16i8_ty, llvm_i16_ty], [IntrNoMem]>;
def int_x86_avx512_mask_packuswb_256 : GCCBuiltin<"__builtin_ia32_packuswb256_mask">,
Intrinsic<[llvm_v32i8_ty], [llvm_v16i16_ty,llvm_v16i16_ty,
llvm_v32i8_ty, llvm_i32_ty], [IntrNoMem]>;
def int_x86_avx512_mask_packuswb_512 : GCCBuiltin<"__builtin_ia32_packuswb512_mask">,
Intrinsic<[llvm_v64i8_ty], [llvm_v32i16_ty,llvm_v32i16_ty,
llvm_v64i8_ty, llvm_i64_ty], [IntrNoMem]>;
def int_x86_avx512_mask_packusdw_128 : GCCBuiltin<"__builtin_ia32_packusdw128_mask">,
Intrinsic<[llvm_v8i16_ty], [llvm_v4i32_ty, llvm_v4i32_ty,
llvm_v8i16_ty, llvm_i8_ty], [IntrNoMem]>;
def int_x86_avx512_mask_packusdw_256 : GCCBuiltin<"__builtin_ia32_packusdw256_mask">,
Intrinsic<[llvm_v16i16_ty], [llvm_v8i32_ty, llvm_v8i32_ty,
llvm_v16i16_ty, llvm_i16_ty], [IntrNoMem]>;
def int_x86_avx512_mask_packusdw_512 : GCCBuiltin<"__builtin_ia32_packusdw512_mask">,
Intrinsic<[llvm_v32i16_ty], [llvm_v16i32_ty, llvm_v16i32_ty,
llvm_v32i16_ty, llvm_i32_ty], [IntrNoMem]>;
def int_x86_avx512_packsswb_512 : GCCBuiltin<"__builtin_ia32_packsswb512">,
Intrinsic<[llvm_v64i8_ty], [llvm_v32i16_ty,llvm_v32i16_ty],
[IntrNoMem]>;
def int_x86_avx512_packssdw_512 : GCCBuiltin<"__builtin_ia32_packssdw512">,
Intrinsic<[llvm_v32i16_ty], [llvm_v16i32_ty, llvm_v16i32_ty],
[IntrNoMem]>;
def int_x86_avx512_packuswb_512 : GCCBuiltin<"__builtin_ia32_packuswb512">,
Intrinsic<[llvm_v64i8_ty], [llvm_v32i16_ty,llvm_v32i16_ty],
[IntrNoMem]>;
def int_x86_avx512_packusdw_512 : GCCBuiltin<"__builtin_ia32_packusdw512">,
Intrinsic<[llvm_v32i16_ty], [llvm_v16i32_ty, llvm_v16i32_ty],
[IntrNoMem]>;
}
// Vector convert

40
llvm/lib/IR/AutoUpgrade.cpp
View File

@ -335,6 +335,10 @@ static bool UpgradeIntrinsicFunction1(Function *F, Function *&NewFn) {
Name.startswith("avx512.mask.cvtudq2pd.") || // Added in 4.0
Name.startswith("avx512.mask.pmul.dq.") || // Added in 4.0
Name.startswith("avx512.mask.pmulu.dq.") || // Added in 4.0
Name.startswith("avx512.mask.packsswb.") || // Added in 4.0
Name.startswith("avx512.mask.packssdw.") || // Added in 4.0
Name.startswith("avx512.mask.packuswb.") || // Added in 4.0
Name.startswith("avx512.mask.packusdw.") || // Added in 4.0
Name == "avx512.mask.add.pd.128" || // Added in 4.0
Name == "avx512.mask.add.pd.256" || // Added in 4.0
Name == "avx512.mask.add.ps.128" || // Added in 4.0
@ -1538,6 +1542,42 @@ void llvm::UpgradeIntrinsicCall(CallInst *CI, Function *NewFn) {
else
llvm_unreachable("Unexpected intrinsic");
Rep = Builder.CreateCall(Intrinsic::getDeclaration(F->getParent(), IID),
{ CI->getArgOperand(0), CI->getArgOperand(1) });
Rep = EmitX86Select(Builder, CI->getArgOperand(3), Rep,
CI->getArgOperand(2));
} else if (IsX86 && Name.startswith("avx512.mask.pack")) {
bool IsUnsigned = Name[16] == 'u';
bool IsDW = Name[18] == 'd';
VectorType *VecTy = cast<VectorType>(CI->getType());
Intrinsic::ID IID;
if (!IsUnsigned && !IsDW && VecTy->getPrimitiveSizeInBits() == 128)
IID = Intrinsic::x86_sse2_packsswb_128;
else if (!IsUnsigned && !IsDW && VecTy->getPrimitiveSizeInBits() == 256)
IID = Intrinsic::x86_avx2_packsswb;
else if (!IsUnsigned && !IsDW && VecTy->getPrimitiveSizeInBits() == 512)
IID = Intrinsic::x86_avx512_packsswb_512;
else if (!IsUnsigned && IsDW && VecTy->getPrimitiveSizeInBits() == 128)
IID = Intrinsic::x86_sse2_packssdw_128;
else if (!IsUnsigned && IsDW && VecTy->getPrimitiveSizeInBits() == 256)
IID = Intrinsic::x86_avx2_packssdw;
else if (!IsUnsigned && IsDW && VecTy->getPrimitiveSizeInBits() == 512)
IID = Intrinsic::x86_avx512_packssdw_512;
else if (IsUnsigned && !IsDW && VecTy->getPrimitiveSizeInBits() == 128)
IID = Intrinsic::x86_sse2_packuswb_128;
else if (IsUnsigned && !IsDW && VecTy->getPrimitiveSizeInBits() == 256)
IID = Intrinsic::x86_avx2_packuswb;
else if (IsUnsigned && !IsDW && VecTy->getPrimitiveSizeInBits() == 512)
IID = Intrinsic::x86_avx512_packuswb_512;
else if (IsUnsigned && IsDW && VecTy->getPrimitiveSizeInBits() == 128)
IID = Intrinsic::x86_sse41_packusdw;
else if (IsUnsigned && IsDW && VecTy->getPrimitiveSizeInBits() == 256)
IID = Intrinsic::x86_avx2_packusdw;
else if (IsUnsigned && IsDW && VecTy->getPrimitiveSizeInBits() == 512)
IID = Intrinsic::x86_avx512_packusdw_512;
else
llvm_unreachable("Unexpected intrinsic");
Rep = Builder.CreateCall(Intrinsic::getDeclaration(F->getParent(), IID),
{ CI->getArgOperand(0), CI->getArgOperand(1) });
Rep = EmitX86Select(Builder, CI->getArgOperand(3), Rep,

16
llvm/lib/Target/X86/X86IntrinsicsInfo.h
View File

@ -851,18 +851,6 @@ static const IntrinsicData IntrinsicsWithoutChain[] = {
X86_INTRINSIC_DATA(avx512_mask_pabs_w_128, INTR_TYPE_1OP_MASK, X86ISD::ABS, 0),
X86_INTRINSIC_DATA(avx512_mask_pabs_w_256, INTR_TYPE_1OP_MASK, X86ISD::ABS, 0),
X86_INTRINSIC_DATA(avx512_mask_pabs_w_512, INTR_TYPE_1OP_MASK, X86ISD::ABS, 0),
X86_INTRINSIC_DATA(avx512_mask_packssdw_128, INTR_TYPE_2OP_MASK, X86ISD::PACKSS, 0),
X86_INTRINSIC_DATA(avx512_mask_packssdw_256, INTR_TYPE_2OP_MASK, X86ISD::PACKSS, 0),
X86_INTRINSIC_DATA(avx512_mask_packssdw_512, INTR_TYPE_2OP_MASK, X86ISD::PACKSS, 0),
X86_INTRINSIC_DATA(avx512_mask_packsswb_128, INTR_TYPE_2OP_MASK, X86ISD::PACKSS, 0),
X86_INTRINSIC_DATA(avx512_mask_packsswb_256, INTR_TYPE_2OP_MASK, X86ISD::PACKSS, 0),
X86_INTRINSIC_DATA(avx512_mask_packsswb_512, INTR_TYPE_2OP_MASK, X86ISD::PACKSS, 0),
X86_INTRINSIC_DATA(avx512_mask_packusdw_128, INTR_TYPE_2OP_MASK, X86ISD::PACKUS, 0),
X86_INTRINSIC_DATA(avx512_mask_packusdw_256, INTR_TYPE_2OP_MASK, X86ISD::PACKUS, 0),
X86_INTRINSIC_DATA(avx512_mask_packusdw_512, INTR_TYPE_2OP_MASK, X86ISD::PACKUS, 0),
X86_INTRINSIC_DATA(avx512_mask_packuswb_128, INTR_TYPE_2OP_MASK, X86ISD::PACKUS, 0),
X86_INTRINSIC_DATA(avx512_mask_packuswb_256, INTR_TYPE_2OP_MASK, X86ISD::PACKUS, 0),
X86_INTRINSIC_DATA(avx512_mask_packuswb_512, INTR_TYPE_2OP_MASK, X86ISD::PACKUS, 0),
X86_INTRINSIC_DATA(avx512_mask_padds_b_128, INTR_TYPE_2OP_MASK, X86ISD::ADDS, 0),
X86_INTRINSIC_DATA(avx512_mask_padds_b_256, INTR_TYPE_2OP_MASK, X86ISD::ADDS, 0),
X86_INTRINSIC_DATA(avx512_mask_padds_b_512, INTR_TYPE_2OP_MASK, X86ISD::ADDS, 0),
@ -1486,6 +1474,10 @@ static const IntrinsicData IntrinsicsWithoutChain[] = {
X86ISD::VPMADD52L, 0),
X86_INTRINSIC_DATA(avx512_maskz_vpmadd52l_uq_512, FMA_OP_MASKZ,
X86ISD::VPMADD52L, 0),
X86_INTRINSIC_DATA(avx512_packssdw_512, INTR_TYPE_2OP, X86ISD::PACKSS, 0),
X86_INTRINSIC_DATA(avx512_packsswb_512, INTR_TYPE_2OP, X86ISD::PACKSS, 0),
X86_INTRINSIC_DATA(avx512_packusdw_512, INTR_TYPE_2OP, X86ISD::PACKUS, 0),
X86_INTRINSIC_DATA(avx512_packuswb_512, INTR_TYPE_2OP, X86ISD::PACKUS, 0),
X86_INTRINSIC_DATA(avx512_pmul_dq_512, INTR_TYPE_2OP, X86ISD::PMULDQ, 0),
X86_INTRINSIC_DATA(avx512_pmulu_dq_512, INTR_TYPE_2OP, X86ISD::PMULUDQ, 0),
X86_INTRINSIC_DATA(avx512_psad_bw_512, INTR_TYPE_2OP, X86ISD::PSADBW, 0),

536
llvm/test/CodeGen/X86/avx512bw-intrinsics-upgrade.ll
View File

@ -992,3 +992,539 @@ define <64 x i8>@test_int_x86_avx512_mask_pshuf_b_512(<64 x i8> %x0, <64 x i8> %
ret <64 x i8> %res2
}
define <32 x i16> @test_mask_packs_epi32_rr_512(<16 x i32> %a, <16 x i32> %b) {
; AVX512BW-LABEL: test_mask_packs_epi32_rr_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: vpackssdw %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi32_rr_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: vpackssdw %zmm1, %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 -1)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packs_epi32_rrk_512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask) {
; AVX512BW-LABEL: test_mask_packs_epi32_rrk_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovd %edi, %k1
; AVX512BW-NEXT: vpackssdw %zmm1, %zmm0, %zmm2 {%k1}
; AVX512BW-NEXT: vmovdqa64 %zmm2, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi32_rrk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackssdw %zmm1, %zmm0, %zmm2 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm2, %zmm0
; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packs_epi32_rrkz_512(<16 x i32> %a, <16 x i32> %b, i32 %mask) {
; AVX512BW-LABEL: test_mask_packs_epi32_rrkz_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovd %edi, %k1
; AVX512BW-NEXT: vpackssdw %zmm1, %zmm0, %zmm0 {%k1} {z}
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi32_rrkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackssdw %zmm1, %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 %mask)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packs_epi32_rm_512(<16 x i32> %a, <16 x i32>* %ptr_b) {
; AVX512BW-LABEL: test_mask_packs_epi32_rm_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: vpackssdw (%rdi), %zmm0, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi32_rm_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: vpackssdw (%eax), %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%b = load <16 x i32>, <16 x i32>* %ptr_b
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 -1)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packs_epi32_rmk_512(<16 x i32> %a, <16 x i32>* %ptr_b, <32 x i16> %passThru, i32 %mask) {
; AVX512BW-LABEL: test_mask_packs_epi32_rmk_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovd %esi, %k1
; AVX512BW-NEXT: vpackssdw (%rdi), %zmm0, %zmm1 {%k1}
; AVX512BW-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi32_rmk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackssdw (%eax), %zmm0, %zmm1 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512F-32-NEXT: retl
%b = load <16 x i32>, <16 x i32>* %ptr_b
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packs_epi32_rmkz_512(<16 x i32> %a, <16 x i32>* %ptr_b, i32 %mask) {
; AVX512BW-LABEL: test_mask_packs_epi32_rmkz_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovd %esi, %k1
; AVX512BW-NEXT: vpackssdw (%rdi), %zmm0, %zmm0 {%k1} {z}
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi32_rmkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackssdw (%eax), %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%b = load <16 x i32>, <16 x i32>* %ptr_b
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 %mask)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packs_epi32_rmb_512(<16 x i32> %a, i32* %ptr_b) {
; AVX512BW-LABEL: test_mask_packs_epi32_rmb_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: vpackssdw (%rdi){1to16}, %zmm0, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi32_rmb_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: vpackssdw (%eax){1to16}, %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 -1)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packs_epi32_rmbk_512(<16 x i32> %a, i32* %ptr_b, <32 x i16> %passThru, i32 %mask) {
; AVX512BW-LABEL: test_mask_packs_epi32_rmbk_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovd %esi, %k1
; AVX512BW-NEXT: vpackssdw (%rdi){1to16}, %zmm0, %zmm1 {%k1}
; AVX512BW-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi32_rmbk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackssdw (%eax){1to16}, %zmm0, %zmm1 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512F-32-NEXT: retl
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packs_epi32_rmbkz_512(<16 x i32> %a, i32* %ptr_b, i32 %mask) {
; AVX512BW-LABEL: test_mask_packs_epi32_rmbkz_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovd %esi, %k1
; AVX512BW-NEXT: vpackssdw (%rdi){1to16}, %zmm0, %zmm0 {%k1} {z}
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi32_rmbkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackssdw (%eax){1to16}, %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 %mask)
ret <32 x i16> %res
}
declare <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32>, <16 x i32>, <32 x i16>, i32)
define <64 x i8> @test_mask_packs_epi16_rr_512(<32 x i16> %a, <32 x i16> %b) {
; AVX512BW-LABEL: test_mask_packs_epi16_rr_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: vpacksswb %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi16_rr_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: vpacksswb %zmm1, %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%res = call <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 -1)
ret <64 x i8> %res
}
define <64 x i8> @test_mask_packs_epi16_rrk_512(<32 x i16> %a, <32 x i16> %b, <64 x i8> %passThru, i64 %mask) {
; AVX512BW-LABEL: test_mask_packs_epi16_rrk_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovq %rdi, %k1
; AVX512BW-NEXT: vpacksswb %zmm1, %zmm0, %zmm2 {%k1}
; AVX512BW-NEXT: vmovdqa64 %zmm2, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi16_rrk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpacksswb %zmm1, %zmm0, %zmm2 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm2, %zmm0
; AVX512F-32-NEXT: retl
%res = call <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> %passThru, i64 %mask)
ret <64 x i8> %res
}
define <64 x i8> @test_mask_packs_epi16_rrkz_512(<32 x i16> %a, <32 x i16> %b, i64 %mask) {
; AVX512BW-LABEL: test_mask_packs_epi16_rrkz_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovq %rdi, %k1
; AVX512BW-NEXT: vpacksswb %zmm1, %zmm0, %zmm0 {%k1} {z}
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi16_rrkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpacksswb %zmm1, %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%res = call <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 %mask)
ret <64 x i8> %res
}
define <64 x i8> @test_mask_packs_epi16_rm_512(<32 x i16> %a, <32 x i16>* %ptr_b) {
; AVX512BW-LABEL: test_mask_packs_epi16_rm_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: vpacksswb (%rdi), %zmm0, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi16_rm_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: vpacksswb (%eax), %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%b = load <32 x i16>, <32 x i16>* %ptr_b
%res = call <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 -1)
ret <64 x i8> %res
}
define <64 x i8> @test_mask_packs_epi16_rmk_512(<32 x i16> %a, <32 x i16>* %ptr_b, <64 x i8> %passThru, i64 %mask) {
; AVX512BW-LABEL: test_mask_packs_epi16_rmk_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovq %rsi, %k1
; AVX512BW-NEXT: vpacksswb (%rdi), %zmm0, %zmm1 {%k1}
; AVX512BW-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi16_rmk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpacksswb (%eax), %zmm0, %zmm1 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512F-32-NEXT: retl
%b = load <32 x i16>, <32 x i16>* %ptr_b
%res = call <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> %passThru, i64 %mask)
ret <64 x i8> %res
}
define <64 x i8> @test_mask_packs_epi16_rmkz_512(<32 x i16> %a, <32 x i16>* %ptr_b, i64 %mask) {
; AVX512BW-LABEL: test_mask_packs_epi16_rmkz_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovq %rsi, %k1
; AVX512BW-NEXT: vpacksswb (%rdi), %zmm0, %zmm0 {%k1} {z}
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packs_epi16_rmkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpacksswb (%eax), %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%b = load <32 x i16>, <32 x i16>* %ptr_b
%res = call <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 %mask)
ret <64 x i8> %res
}
declare <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16>, <32 x i16>, <64 x i8>, i64)
define <32 x i16> @test_mask_packus_epi32_rr_512(<16 x i32> %a, <16 x i32> %b) {
; AVX512BW-LABEL: test_mask_packus_epi32_rr_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: vpackusdw %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi32_rr_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: vpackusdw %zmm1, %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 -1)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packus_epi32_rrk_512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask) {
; AVX512BW-LABEL: test_mask_packus_epi32_rrk_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovd %edi, %k1
; AVX512BW-NEXT: vpackusdw %zmm1, %zmm0, %zmm2 {%k1}
; AVX512BW-NEXT: vmovdqa64 %zmm2, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi32_rrk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackusdw %zmm1, %zmm0, %zmm2 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm2, %zmm0
; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packus_epi32_rrkz_512(<16 x i32> %a, <16 x i32> %b, i32 %mask) {
; AVX512BW-LABEL: test_mask_packus_epi32_rrkz_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovd %edi, %k1
; AVX512BW-NEXT: vpackusdw %zmm1, %zmm0, %zmm0 {%k1} {z}
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi32_rrkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackusdw %zmm1, %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 %mask)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packus_epi32_rm_512(<16 x i32> %a, <16 x i32>* %ptr_b) {
; AVX512BW-LABEL: test_mask_packus_epi32_rm_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: vpackusdw (%rdi), %zmm0, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi32_rm_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: vpackusdw (%eax), %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%b = load <16 x i32>, <16 x i32>* %ptr_b
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 -1)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packus_epi32_rmk_512(<16 x i32> %a, <16 x i32>* %ptr_b, <32 x i16> %passThru, i32 %mask) {
; AVX512BW-LABEL: test_mask_packus_epi32_rmk_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovd %esi, %k1
; AVX512BW-NEXT: vpackusdw (%rdi), %zmm0, %zmm1 {%k1}
; AVX512BW-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi32_rmk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackusdw (%eax), %zmm0, %zmm1 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512F-32-NEXT: retl
%b = load <16 x i32>, <16 x i32>* %ptr_b
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packus_epi32_rmkz_512(<16 x i32> %a, <16 x i32>* %ptr_b, i32 %mask) {
; AVX512BW-LABEL: test_mask_packus_epi32_rmkz_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovd %esi, %k1
; AVX512BW-NEXT: vpackusdw (%rdi), %zmm0, %zmm0 {%k1} {z}
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi32_rmkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackusdw (%eax), %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%b = load <16 x i32>, <16 x i32>* %ptr_b
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 %mask)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packus_epi32_rmb_512(<16 x i32> %a, i32* %ptr_b) {
; AVX512BW-LABEL: test_mask_packus_epi32_rmb_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: vpackusdw (%rdi){1to16}, %zmm0, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi32_rmb_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: vpackusdw (%eax){1to16}, %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 -1)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packus_epi32_rmbk_512(<16 x i32> %a, i32* %ptr_b, <32 x i16> %passThru, i32 %mask) {
; AVX512BW-LABEL: test_mask_packus_epi32_rmbk_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovd %esi, %k1
; AVX512BW-NEXT: vpackusdw (%rdi){1to16}, %zmm0, %zmm1 {%k1}
; AVX512BW-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi32_rmbk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackusdw (%eax){1to16}, %zmm0, %zmm1 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512F-32-NEXT: retl
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask)
ret <32 x i16> %res
}
define <32 x i16> @test_mask_packus_epi32_rmbkz_512(<16 x i32> %a, i32* %ptr_b, i32 %mask) {
; AVX512BW-LABEL: test_mask_packus_epi32_rmbkz_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovd %esi, %k1
; AVX512BW-NEXT: vpackusdw (%rdi){1to16}, %zmm0, %zmm0 {%k1} {z}
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi32_rmbkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackusdw (%eax){1to16}, %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 %mask)
ret <32 x i16> %res
}
declare <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32>, <16 x i32>, <32 x i16>, i32)
define <64 x i8> @test_mask_packus_epi16_rr_512(<32 x i16> %a, <32 x i16> %b) {
; AVX512BW-LABEL: test_mask_packus_epi16_rr_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: vpackuswb %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi16_rr_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: vpackuswb %zmm1, %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%res = call <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 -1)
ret <64 x i8> %res
}
define <64 x i8> @test_mask_packus_epi16_rrk_512(<32 x i16> %a, <32 x i16> %b, <64 x i8> %passThru, i64 %mask) {
; AVX512BW-LABEL: test_mask_packus_epi16_rrk_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovq %rdi, %k1
; AVX512BW-NEXT: vpackuswb %zmm1, %zmm0, %zmm2 {%k1}
; AVX512BW-NEXT: vmovdqa64 %zmm2, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi16_rrk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackuswb %zmm1, %zmm0, %zmm2 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm2, %zmm0
; AVX512F-32-NEXT: retl
%res = call <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> %passThru, i64 %mask)
ret <64 x i8> %res
}
define <64 x i8> @test_mask_packus_epi16_rrkz_512(<32 x i16> %a, <32 x i16> %b, i64 %mask) {
; AVX512BW-LABEL: test_mask_packus_epi16_rrkz_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovq %rdi, %k1
; AVX512BW-NEXT: vpackuswb %zmm1, %zmm0, %zmm0 {%k1} {z}
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi16_rrkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackuswb %zmm1, %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%res = call <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 %mask)
ret <64 x i8> %res
}
define <64 x i8> @test_mask_packus_epi16_rm_512(<32 x i16> %a, <32 x i16>* %ptr_b) {
; AVX512BW-LABEL: test_mask_packus_epi16_rm_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: vpackuswb (%rdi), %zmm0, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi16_rm_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: vpackuswb (%eax), %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%b = load <32 x i16>, <32 x i16>* %ptr_b
%res = call <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 -1)
ret <64 x i8> %res
}
define <64 x i8> @test_mask_packus_epi16_rmk_512(<32 x i16> %a, <32 x i16>* %ptr_b, <64 x i8> %passThru, i64 %mask) {
; AVX512BW-LABEL: test_mask_packus_epi16_rmk_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovq %rsi, %k1
; AVX512BW-NEXT: vpackuswb (%rdi), %zmm0, %zmm1 {%k1}
; AVX512BW-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi16_rmk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackuswb (%eax), %zmm0, %zmm1 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512F-32-NEXT: retl
%b = load <32 x i16>, <32 x i16>* %ptr_b
%res = call <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> %passThru, i64 %mask)
ret <64 x i8> %res
}
define <64 x i8> @test_mask_packus_epi16_rmkz_512(<32 x i16> %a, <32 x i16>* %ptr_b, i64 %mask) {
; AVX512BW-LABEL: test_mask_packus_epi16_rmkz_512:
; AVX512BW: ## BB#0:
; AVX512BW-NEXT: kmovq %rsi, %k1
; AVX512BW-NEXT: vpackuswb (%rdi), %zmm0, %zmm0 {%k1} {z}
; AVX512BW-NEXT: retq
;
; AVX512F-32-LABEL: test_mask_packus_epi16_rmkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackuswb (%eax), %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%b = load <32 x i16>, <32 x i16>* %ptr_b
%res = call <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 %mask)
ret <64 x i8> %res
}
declare <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16>, <32 x i16>, <64 x i8>, i64)

200
llvm/test/CodeGen/X86/avx512bw-intrinsics.ll
View File

@ -660,8 +660,8 @@ define <32 x i16> @test_mask_packs_epi32_rr_512(<16 x i32> %a, <16 x i32> %b) {
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: vpackssdw %zmm1, %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 -1)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packssdw.512(<16 x i32> %a, <16 x i32> %b)
ret <32 x i16> %1
}
define <32 x i16> @test_mask_packs_epi32_rrk_512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask) {
@ -678,8 +678,10 @@ define <32 x i16> @test_mask_packs_epi32_rrk_512(<16 x i32> %a, <16 x i32> %b, <
; AVX512F-32-NEXT: vpackssdw %zmm1, %zmm0, %zmm2 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm2, %zmm0
; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packssdw.512(<16 x i32> %a, <16 x i32> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %passThru
ret <32 x i16> %3
}
define <32 x i16> @test_mask_packs_epi32_rrkz_512(<16 x i32> %a, <16 x i32> %b, i32 %mask) {
@ -694,8 +696,10 @@ define <32 x i16> @test_mask_packs_epi32_rrkz_512(<16 x i32> %a, <16 x i32> %b,
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackssdw %zmm1, %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 %mask)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packssdw.512(<16 x i32> %a, <16 x i32> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> zeroinitializer
ret <32 x i16> %3
}
define <32 x i16> @test_mask_packs_epi32_rm_512(<16 x i32> %a, <16 x i32>* %ptr_b) {
@ -710,8 +714,8 @@ define <32 x i16> @test_mask_packs_epi32_rm_512(<16 x i32> %a, <16 x i32>* %ptr_
; AVX512F-32-NEXT: vpackssdw (%eax), %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%b = load <16 x i32>, <16 x i32>* %ptr_b
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 -1)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packssdw.512(<16 x i32> %a, <16 x i32> %b)
ret <32 x i16> %1
}
define <32 x i16> @test_mask_packs_epi32_rmk_512(<16 x i32> %a, <16 x i32>* %ptr_b, <32 x i16> %passThru, i32 %mask) {
@ -730,8 +734,10 @@ define <32 x i16> @test_mask_packs_epi32_rmk_512(<16 x i32> %a, <16 x i32>* %ptr
; AVX512F-32-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512F-32-NEXT: retl
%b = load <16 x i32>, <16 x i32>* %ptr_b
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packssdw.512(<16 x i32> %a, <16 x i32> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %passThru
ret <32 x i16> %3
}
define <32 x i16> @test_mask_packs_epi32_rmkz_512(<16 x i32> %a, <16 x i32>* %ptr_b, i32 %mask) {
@ -748,8 +754,10 @@ define <32 x i16> @test_mask_packs_epi32_rmkz_512(<16 x i32> %a, <16 x i32>* %pt
; AVX512F-32-NEXT: vpackssdw (%eax), %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%b = load <16 x i32>, <16 x i32>* %ptr_b
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 %mask)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packssdw.512(<16 x i32> %a, <16 x i32> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> zeroinitializer
ret <32 x i16> %3
}
define <32 x i16> @test_mask_packs_epi32_rmb_512(<16 x i32> %a, i32* %ptr_b) {
@ -766,8 +774,8 @@ define <32 x i16> @test_mask_packs_epi32_rmb_512(<16 x i32> %a, i32* %ptr_b) {
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 -1)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packssdw.512(<16 x i32> %a, <16 x i32> %b)
ret <32 x i16> %1
}
define <32 x i16> @test_mask_packs_epi32_rmbk_512(<16 x i32> %a, i32* %ptr_b, <32 x i16> %passThru, i32 %mask) {
@ -788,8 +796,10 @@ define <32 x i16> @test_mask_packs_epi32_rmbk_512(<16 x i32> %a, i32* %ptr_b, <3
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packssdw.512(<16 x i32> %a, <16 x i32> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %passThru
ret <32 x i16> %3
}
define <32 x i16> @test_mask_packs_epi32_rmbkz_512(<16 x i32> %a, i32* %ptr_b, i32 %mask) {
@ -808,11 +818,13 @@ define <32 x i16> @test_mask_packs_epi32_rmbkz_512(<16 x i32> %a, i32* %ptr_b, i
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
%res = call <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 %mask)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packssdw.512(<16 x i32> %a, <16 x i32> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> zeroinitializer
ret <32 x i16> %3
}
declare <32 x i16> @llvm.x86.avx512.mask.packssdw.512(<16 x i32>, <16 x i32>, <32 x i16>, i32)
declare <32 x i16> @llvm.x86.avx512.packssdw.512(<16 x i32>, <16 x i32>)
define <64 x i8> @test_mask_packs_epi16_rr_512(<32 x i16> %a, <32 x i16> %b) {
; AVX512BW-LABEL: test_mask_packs_epi16_rr_512:
@ -824,8 +836,8 @@ define <64 x i8> @test_mask_packs_epi16_rr_512(<32 x i16> %a, <32 x i16> %b) {
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: vpacksswb %zmm1, %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%res = call <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 -1)
ret <64 x i8> %res
%1 = call <64 x i8> @llvm.x86.avx512.packsswb.512(<32 x i16> %a, <32 x i16> %b)
ret <64 x i8> %1
}
define <64 x i8> @test_mask_packs_epi16_rrk_512(<32 x i16> %a, <32 x i16> %b, <64 x i8> %passThru, i64 %mask) {
@ -838,14 +850,14 @@ define <64 x i8> @test_mask_packs_epi16_rrk_512(<32 x i16> %a, <32 x i16> %b, <6
;
; AVX512F-32-LABEL: test_mask_packs_epi16_rrk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k0
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: kunpckdq %k0, %k1, %k1
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpacksswb %zmm1, %zmm0, %zmm2 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm2, %zmm0
; AVX512F-32-NEXT: retl
%res = call <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> %passThru, i64 %mask)
ret <64 x i8> %res
%1 = call <64 x i8> @llvm.x86.avx512.packsswb.512(<32 x i16> %a, <32 x i16> %b)
%2 = bitcast i64 %mask to <64 x i1>
%3 = select <64 x i1> %2, <64 x i8> %1, <64 x i8> %passThru
ret <64 x i8> %3
}
define <64 x i8> @test_mask_packs_epi16_rrkz_512(<32 x i16> %a, <32 x i16> %b, i64 %mask) {
@ -857,13 +869,13 @@ define <64 x i8> @test_mask_packs_epi16_rrkz_512(<32 x i16> %a, <32 x i16> %b, i
;
; AVX512F-32-LABEL: test_mask_packs_epi16_rrkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k0
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: kunpckdq %k0, %k1, %k1
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpacksswb %zmm1, %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%res = call <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 %mask)
ret <64 x i8> %res
%1 = call <64 x i8> @llvm.x86.avx512.packsswb.512(<32 x i16> %a, <32 x i16> %b)
%2 = bitcast i64 %mask to <64 x i1>
%3 = select <64 x i1> %2, <64 x i8> %1, <64 x i8> zeroinitializer
ret <64 x i8> %3
}
define <64 x i8> @test_mask_packs_epi16_rm_512(<32 x i16> %a, <32 x i16>* %ptr_b) {
@ -878,8 +890,8 @@ define <64 x i8> @test_mask_packs_epi16_rm_512(<32 x i16> %a, <32 x i16>* %ptr_b
; AVX512F-32-NEXT: vpacksswb (%eax), %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%b = load <32 x i16>, <32 x i16>* %ptr_b
%res = call <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 -1)
ret <64 x i8> %res
%1 = call <64 x i8> @llvm.x86.avx512.packsswb.512(<32 x i16> %a, <32 x i16> %b)
ret <64 x i8> %1
}
define <64 x i8> @test_mask_packs_epi16_rmk_512(<32 x i16> %a, <32 x i16>* %ptr_b, <64 x i8> %passThru, i64 %mask) {
@ -893,15 +905,15 @@ define <64 x i8> @test_mask_packs_epi16_rmk_512(<32 x i16> %a, <32 x i16>* %ptr_
; AVX512F-32-LABEL: test_mask_packs_epi16_rmk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k0
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: kunpckdq %k0, %k1, %k1
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpacksswb (%eax), %zmm0, %zmm1 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512F-32-NEXT: retl
%b = load <32 x i16>, <32 x i16>* %ptr_b
%res = call <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> %passThru, i64 %mask)
ret <64 x i8> %res
%1 = call <64 x i8> @llvm.x86.avx512.packsswb.512(<32 x i16> %a, <32 x i16> %b)
%2 = bitcast i64 %mask to <64 x i1>
%3 = select <64 x i1> %2, <64 x i8> %1, <64 x i8> %passThru
ret <64 x i8> %3
}
define <64 x i8> @test_mask_packs_epi16_rmkz_512(<32 x i16> %a, <32 x i16>* %ptr_b, i64 %mask) {
@ -914,17 +926,17 @@ define <64 x i8> @test_mask_packs_epi16_rmkz_512(<32 x i16> %a, <32 x i16>* %ptr
; AVX512F-32-LABEL: test_mask_packs_epi16_rmkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k0
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: kunpckdq %k0, %k1, %k1
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpacksswb (%eax), %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%b = load <32 x i16>, <32 x i16>* %ptr_b
%res = call <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 %mask)
ret <64 x i8> %res
%1 = call <64 x i8> @llvm.x86.avx512.packsswb.512(<32 x i16> %a, <32 x i16> %b)
%2 = bitcast i64 %mask to <64 x i1>
%3 = select <64 x i1> %2, <64 x i8> %1, <64 x i8> zeroinitializer
ret <64 x i8> %3
}
declare <64 x i8> @llvm.x86.avx512.mask.packsswb.512(<32 x i16>, <32 x i16>, <64 x i8>, i64)
declare <64 x i8> @llvm.x86.avx512.packsswb.512(<32 x i16>, <32 x i16>)
define <32 x i16> @test_mask_packus_epi32_rr_512(<16 x i32> %a, <16 x i32> %b) {
@ -937,8 +949,8 @@ define <32 x i16> @test_mask_packus_epi32_rr_512(<16 x i32> %a, <16 x i32> %b) {
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: vpackusdw %zmm1, %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 -1)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packusdw.512(<16 x i32> %a, <16 x i32> %b)
ret <32 x i16> %1
}
define <32 x i16> @test_mask_packus_epi32_rrk_512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask) {
@ -955,8 +967,10 @@ define <32 x i16> @test_mask_packus_epi32_rrk_512(<16 x i32> %a, <16 x i32> %b,
; AVX512F-32-NEXT: vpackusdw %zmm1, %zmm0, %zmm2 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm2, %zmm0
; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packusdw.512(<16 x i32> %a, <16 x i32> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %passThru
ret <32 x i16> %3
}
define <32 x i16> @test_mask_packus_epi32_rrkz_512(<16 x i32> %a, <16 x i32> %b, i32 %mask) {
@ -971,8 +985,10 @@ define <32 x i16> @test_mask_packus_epi32_rrkz_512(<16 x i32> %a, <16 x i32> %b,
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackusdw %zmm1, %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 %mask)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packusdw.512(<16 x i32> %a, <16 x i32> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> zeroinitializer
ret <32 x i16> %3
}
define <32 x i16> @test_mask_packus_epi32_rm_512(<16 x i32> %a, <16 x i32>* %ptr_b) {
@ -987,8 +1003,8 @@ define <32 x i16> @test_mask_packus_epi32_rm_512(<16 x i32> %a, <16 x i32>* %ptr
; AVX512F-32-NEXT: vpackusdw (%eax), %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%b = load <16 x i32>, <16 x i32>* %ptr_b
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 -1)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packusdw.512(<16 x i32> %a, <16 x i32> %b)
ret <32 x i16> %1
}
define <32 x i16> @test_mask_packus_epi32_rmk_512(<16 x i32> %a, <16 x i32>* %ptr_b, <32 x i16> %passThru, i32 %mask) {
@ -1007,8 +1023,10 @@ define <32 x i16> @test_mask_packus_epi32_rmk_512(<16 x i32> %a, <16 x i32>* %pt
; AVX512F-32-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512F-32-NEXT: retl
%b = load <16 x i32>, <16 x i32>* %ptr_b
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packusdw.512(<16 x i32> %a, <16 x i32> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %passThru
ret <32 x i16> %3
}
define <32 x i16> @test_mask_packus_epi32_rmkz_512(<16 x i32> %a, <16 x i32>* %ptr_b, i32 %mask) {
@ -1025,8 +1043,10 @@ define <32 x i16> @test_mask_packus_epi32_rmkz_512(<16 x i32> %a, <16 x i32>* %p
; AVX512F-32-NEXT: vpackusdw (%eax), %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%b = load <16 x i32>, <16 x i32>* %ptr_b
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 %mask)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packusdw.512(<16 x i32> %a, <16 x i32> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> zeroinitializer
ret <32 x i16> %3
}
define <32 x i16> @test_mask_packus_epi32_rmb_512(<16 x i32> %a, i32* %ptr_b) {
@ -1043,8 +1063,8 @@ define <32 x i16> @test_mask_packus_epi32_rmb_512(<16 x i32> %a, i32* %ptr_b) {
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 -1)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packusdw.512(<16 x i32> %a, <16 x i32> %b)
ret <32 x i16> %1
}
define <32 x i16> @test_mask_packus_epi32_rmbk_512(<16 x i32> %a, i32* %ptr_b, <32 x i16> %passThru, i32 %mask) {
@ -1065,8 +1085,10 @@ define <32 x i16> @test_mask_packus_epi32_rmbk_512(<16 x i32> %a, i32* %ptr_b, <
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> %passThru, i32 %mask)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packusdw.512(<16 x i32> %a, <16 x i32> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %passThru
ret <32 x i16> %3
}
define <32 x i16> @test_mask_packus_epi32_rmbkz_512(<16 x i32> %a, i32* %ptr_b, i32 %mask) {
@ -1085,11 +1107,13 @@ define <32 x i16> @test_mask_packus_epi32_rmbkz_512(<16 x i32> %a, i32* %ptr_b,
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
%res = call <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32> %a, <16 x i32> %b, <32 x i16> zeroinitializer, i32 %mask)
ret <32 x i16> %res
%1 = call <32 x i16> @llvm.x86.avx512.packusdw.512(<16 x i32> %a, <16 x i32> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> zeroinitializer
ret <32 x i16> %3
}
declare <32 x i16> @llvm.x86.avx512.mask.packusdw.512(<16 x i32>, <16 x i32>, <32 x i16>, i32)
declare <32 x i16> @llvm.x86.avx512.packusdw.512(<16 x i32>, <16 x i32>)
define <64 x i8> @test_mask_packus_epi16_rr_512(<32 x i16> %a, <32 x i16> %b) {
; AVX512BW-LABEL: test_mask_packus_epi16_rr_512:
@ -1101,8 +1125,8 @@ define <64 x i8> @test_mask_packus_epi16_rr_512(<32 x i16> %a, <32 x i16> %b) {
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: vpackuswb %zmm1, %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%res = call <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 -1)
ret <64 x i8> %res
%1 = call <64 x i8> @llvm.x86.avx512.packuswb.512(<32 x i16> %a, <32 x i16> %b)
ret <64 x i8> %1
}
define <64 x i8> @test_mask_packus_epi16_rrk_512(<32 x i16> %a, <32 x i16> %b, <64 x i8> %passThru, i64 %mask) {
@ -1115,14 +1139,14 @@ define <64 x i8> @test_mask_packus_epi16_rrk_512(<32 x i16> %a, <32 x i16> %b, <
;
; AVX512F-32-LABEL: test_mask_packus_epi16_rrk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k0
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: kunpckdq %k0, %k1, %k1
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackuswb %zmm1, %zmm0, %zmm2 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm2, %zmm0
; AVX512F-32-NEXT: retl
%res = call <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> %passThru, i64 %mask)
ret <64 x i8> %res
%1 = call <64 x i8> @llvm.x86.avx512.packuswb.512(<32 x i16> %a, <32 x i16> %b)
%2 = bitcast i64 %mask to <64 x i1>
%3 = select <64 x i1> %2, <64 x i8> %1, <64 x i8> %passThru
ret <64 x i8> %3
}
define <64 x i8> @test_mask_packus_epi16_rrkz_512(<32 x i16> %a, <32 x i16> %b, i64 %mask) {
@ -1134,13 +1158,13 @@ define <64 x i8> @test_mask_packus_epi16_rrkz_512(<32 x i16> %a, <32 x i16> %b,
;
; AVX512F-32-LABEL: test_mask_packus_epi16_rrkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k0
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: kunpckdq %k0, %k1, %k1
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackuswb %zmm1, %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%res = call <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 %mask)
ret <64 x i8> %res
%1 = call <64 x i8> @llvm.x86.avx512.packuswb.512(<32 x i16> %a, <32 x i16> %b)
%2 = bitcast i64 %mask to <64 x i1>
%3 = select <64 x i1> %2, <64 x i8> %1, <64 x i8> zeroinitializer
ret <64 x i8> %3
}
define <64 x i8> @test_mask_packus_epi16_rm_512(<32 x i16> %a, <32 x i16>* %ptr_b) {
@ -1155,8 +1179,8 @@ define <64 x i8> @test_mask_packus_epi16_rm_512(<32 x i16> %a, <32 x i16>* %ptr_
; AVX512F-32-NEXT: vpackuswb (%eax), %zmm0, %zmm0
; AVX512F-32-NEXT: retl
%b = load <32 x i16>, <32 x i16>* %ptr_b
%res = call <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 -1)
ret <64 x i8> %res
%1 = call <64 x i8> @llvm.x86.avx512.packuswb.512(<32 x i16> %a, <32 x i16> %b)
ret <64 x i8> %1
}
define <64 x i8> @test_mask_packus_epi16_rmk_512(<32 x i16> %a, <32 x i16>* %ptr_b, <64 x i8> %passThru, i64 %mask) {
@ -1170,15 +1194,15 @@ define <64 x i8> @test_mask_packus_epi16_rmk_512(<32 x i16> %a, <32 x i16>* %ptr
; AVX512F-32-LABEL: test_mask_packus_epi16_rmk_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k0
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: kunpckdq %k0, %k1, %k1
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackuswb (%eax), %zmm0, %zmm1 {%k1}
; AVX512F-32-NEXT: vmovdqa64 %zmm1, %zmm0
; AVX512F-32-NEXT: retl
%b = load <32 x i16>, <32 x i16>* %ptr_b
%res = call <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> %passThru, i64 %mask)
ret <64 x i8> %res
%1 = call <64 x i8> @llvm.x86.avx512.packuswb.512(<32 x i16> %a, <32 x i16> %b)
%2 = bitcast i64 %mask to <64 x i1>
%3 = select <64 x i1> %2, <64 x i8> %1, <64 x i8> %passThru
ret <64 x i8> %3
}
define <64 x i8> @test_mask_packus_epi16_rmkz_512(<32 x i16> %a, <32 x i16>* %ptr_b, i64 %mask) {
@ -1191,17 +1215,17 @@ define <64 x i8> @test_mask_packus_epi16_rmkz_512(<32 x i16> %a, <32 x i16>* %pt
; AVX512F-32-LABEL: test_mask_packus_epi16_rmkz_512:
; AVX512F-32: # BB#0:
; AVX512F-32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k0
; AVX512F-32-NEXT: kmovd {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: kunpckdq %k0, %k1, %k1
; AVX512F-32-NEXT: kmovq {{[0-9]+}}(%esp), %k1
; AVX512F-32-NEXT: vpackuswb (%eax), %zmm0, %zmm0 {%k1} {z}
; AVX512F-32-NEXT: retl
%b = load <32 x i16>, <32 x i16>* %ptr_b
%res = call <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16> %a, <32 x i16> %b, <64 x i8> zeroinitializer, i64 %mask)
ret <64 x i8> %res
%1 = call <64 x i8> @llvm.x86.avx512.packuswb.512(<32 x i16> %a, <32 x i16> %b)
%2 = bitcast i64 %mask to <64 x i1>
%3 = select <64 x i1> %2, <64 x i8> %1, <64 x i8> zeroinitializer
ret <64 x i8> %3
}
declare <64 x i8> @llvm.x86.avx512.mask.packuswb.512(<32 x i16>, <32 x i16>, <64 x i8>, i64)
declare <64 x i8> @llvm.x86.avx512.packuswb.512(<32 x i16>, <32 x i16>)
define <32 x i16> @test_mask_adds_epi16_rr_512(<32 x i16> %a, <32 x i16> %b) {
; AVX512BW-LABEL: test_mask_adds_epi16_rr_512:

677
llvm/test/CodeGen/X86/avx512bwvl-intrinsics-upgrade.ll
View File

@ -1863,3 +1863,680 @@ define <4 x i64>@test_int_x86_avx512_mask_pmovsxd_q_256(<4 x i32> %x0, <4 x i64>
ret <4 x i64> %res4
}
define <8 x i16> @test_mask_packs_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test_mask_packs_epi32_rr_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 -1)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packs_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_packs_epi32_rrk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackssdw %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x6b,0xd1]
; CHECK-NEXT: vmovdqa %xmm2, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packs_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_packs_epi32_rrkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x6b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packs_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_packs_epi32_rm_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackssdw (%rdi), %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 -1)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packs_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b, <8 x i16> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_packs_epi32_rmk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackssdw (%rdi), %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x6b,0x0f]
; CHECK-NEXT: vmovdqa %xmm1, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packs_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_packs_epi32_rmkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackssdw (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x6b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packs_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_packs_epi32_rmb_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackssdw (%rdi){1to4}, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x18,0x6b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 -1)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packs_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <8 x i16> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_packs_epi32_rmbk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackssdw (%rdi){1to4}, %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x19,0x6b,0x0f]
; CHECK-NEXT: vmovdqa %xmm1, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packs_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_packs_epi32_rmbkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackssdw (%rdi){1to4}, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x99,0x6b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
}
declare <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32>, <4 x i32>, <8 x i16>, i8)
define <16 x i16> @test_mask_packs_epi32_rr_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_mask_packs_epi32_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 -1)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packs_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask) {
; CHECK-LABEL: test_mask_packs_epi32_rrk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackssdw %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x6b,0xd1]
; CHECK-NEXT: vmovdqa %ymm2, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packs_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i16 %mask) {
; CHECK-LABEL: test_mask_packs_epi32_rrkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x6b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packs_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_packs_epi32_rm_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackssdw (%rdi), %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 -1)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packs_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b, <16 x i16> %passThru, i16 %mask) {
; CHECK-LABEL: test_mask_packs_epi32_rmk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackssdw (%rdi), %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x6b,0x0f]
; CHECK-NEXT: vmovdqa %ymm1, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packs_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_b, i16 %mask) {
; CHECK-LABEL: test_mask_packs_epi32_rmkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackssdw (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x6b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packs_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_packs_epi32_rmb_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackssdw (%rdi){1to8}, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x38,0x6b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 -1)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packs_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <16 x i16> %passThru, i16 %mask) {
; CHECK-LABEL: test_mask_packs_epi32_rmbk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackssdw (%rdi){1to8}, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x39,0x6b,0x0f]
; CHECK-NEXT: vmovdqa %ymm1, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packs_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i16 %mask) {
; CHECK-LABEL: test_mask_packs_epi32_rmbkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackssdw (%rdi){1to8}, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xb9,0x6b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
}
declare <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32>, <8 x i32>, <16 x i16>, i16)
define <16 x i8> @test_mask_packs_epi16_rr_128(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: test_mask_packs_epi16_rr_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x63,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 -1)
ret <16 x i8> %res
}
define <16 x i8> @test_mask_packs_epi16_rrk_128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask) {
; CHECK-LABEL: test_mask_packs_epi16_rrk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpacksswb %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x63,0xd1]
; CHECK-NEXT: vmovdqa %xmm2, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask)
ret <16 x i8> %res
}
define <16 x i8> @test_mask_packs_epi16_rrkz_128(<8 x i16> %a, <8 x i16> %b, i16 %mask) {
; CHECK-LABEL: test_mask_packs_epi16_rrkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x63,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 %mask)
ret <16 x i8> %res
}
define <16 x i8> @test_mask_packs_epi16_rm_128(<8 x i16> %a, <8 x i16>* %ptr_b) {
; CHECK-LABEL: test_mask_packs_epi16_rm_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpacksswb (%rdi), %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x63,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i16>, <8 x i16>* %ptr_b
%res = call <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 -1)
ret <16 x i8> %res
}
define <16 x i8> @test_mask_packs_epi16_rmk_128(<8 x i16> %a, <8 x i16>* %ptr_b, <16 x i8> %passThru, i16 %mask) {
; CHECK-LABEL: test_mask_packs_epi16_rmk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpacksswb (%rdi), %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x63,0x0f]
; CHECK-NEXT: vmovdqa %xmm1, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i16>, <8 x i16>* %ptr_b
%res = call <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask)
ret <16 x i8> %res
}
define <16 x i8> @test_mask_packs_epi16_rmkz_128(<8 x i16> %a, <8 x i16>* %ptr_b, i16 %mask) {
; CHECK-LABEL: test_mask_packs_epi16_rmkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpacksswb (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x63,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i16>, <8 x i16>* %ptr_b
%res = call <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 %mask)
ret <16 x i8> %res
}
declare <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16>, <8 x i16>, <16 x i8>, i16)
define <32 x i8> @test_mask_packs_epi16_rr_256(<16 x i16> %a, <16 x i16> %b) {
; CHECK-LABEL: test_mask_packs_epi16_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpacksswb %ymm1, %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x63,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 -1)
ret <32 x i8> %res
}
define <32 x i8> @test_mask_packs_epi16_rrk_256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask) {
; CHECK-LABEL: test_mask_packs_epi16_rrk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovd %edi, %k1 ## encoding: [0xc5,0xfb,0x92,0xcf]
; CHECK-NEXT: vpacksswb %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x63,0xd1]
; CHECK-NEXT: vmovdqa %ymm2, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask)
ret <32 x i8> %res
}
define <32 x i8> @test_mask_packs_epi16_rrkz_256(<16 x i16> %a, <16 x i16> %b, i32 %mask) {
; CHECK-LABEL: test_mask_packs_epi16_rrkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovd %edi, %k1 ## encoding: [0xc5,0xfb,0x92,0xcf]
; CHECK-NEXT: vpacksswb %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x63,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 %mask)
ret <32 x i8> %res
}
define <32 x i8> @test_mask_packs_epi16_rm_256(<16 x i16> %a, <16 x i16>* %ptr_b) {
; CHECK-LABEL: test_mask_packs_epi16_rm_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpacksswb (%rdi), %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x63,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <16 x i16>, <16 x i16>* %ptr_b
%res = call <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 -1)
ret <32 x i8> %res
}
define <32 x i8> @test_mask_packs_epi16_rmk_256(<16 x i16> %a, <16 x i16>* %ptr_b, <32 x i8> %passThru, i32 %mask) {
; CHECK-LABEL: test_mask_packs_epi16_rmk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovd %esi, %k1 ## encoding: [0xc5,0xfb,0x92,0xce]
; CHECK-NEXT: vpacksswb (%rdi), %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x63,0x0f]
; CHECK-NEXT: vmovdqa %ymm1, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <16 x i16>, <16 x i16>* %ptr_b
%res = call <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask)
ret <32 x i8> %res
}
define <32 x i8> @test_mask_packs_epi16_rmkz_256(<16 x i16> %a, <16 x i16>* %ptr_b, i32 %mask) {
; CHECK-LABEL: test_mask_packs_epi16_rmkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovd %esi, %k1 ## encoding: [0xc5,0xfb,0x92,0xce]
; CHECK-NEXT: vpacksswb (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x63,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <16 x i16>, <16 x i16>* %ptr_b
%res = call <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 %mask)
ret <32 x i8> %res
}
declare <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16>, <16 x i16>, <32 x i8>, i32)
define <8 x i16> @test_mask_packus_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test_mask_packus_epi32_rr_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackusdw %xmm1, %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x2b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 -1)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packus_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_packus_epi32_rrk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackusdw %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf2,0x7d,0x09,0x2b,0xd1]
; CHECK-NEXT: vmovdqa %xmm2, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packus_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_packus_epi32_rrkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackusdw %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x2b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packus_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_packus_epi32_rm_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackusdw (%rdi), %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x2b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 -1)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packus_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b, <8 x i16> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_packus_epi32_rmk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackusdw (%rdi), %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf2,0x7d,0x09,0x2b,0x0f]
; CHECK-NEXT: vmovdqa %xmm1, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packus_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_packus_epi32_rmkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackusdw (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x2b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packus_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_packus_epi32_rmb_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackusdw (%rdi){1to4}, %xmm0, %xmm0 ## encoding: [0x62,0xf2,0x7d,0x18,0x2b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 -1)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packus_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <8 x i16> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_packus_epi32_rmbk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackusdw (%rdi){1to4}, %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf2,0x7d,0x19,0x2b,0x0f]
; CHECK-NEXT: vmovdqa %xmm1, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask)
ret <8 x i16> %res
}
define <8 x i16> @test_mask_packus_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_packus_epi32_rmbkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackusdw (%rdi){1to4}, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x99,0x2b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
}
declare <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32>, <4 x i32>, <8 x i16>, i8)
define <16 x i16> @test_mask_packus_epi32_rr_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_mask_packus_epi32_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackusdw %ymm1, %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x2b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 -1)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packus_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask) {
; CHECK-LABEL: test_mask_packus_epi32_rrk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackusdw %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf2,0x7d,0x29,0x2b,0xd1]
; CHECK-NEXT: vmovdqa %ymm2, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packus_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i16 %mask) {
; CHECK-LABEL: test_mask_packus_epi32_rrkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackusdw %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0xa9,0x2b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packus_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_packus_epi32_rm_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackusdw (%rdi), %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x2b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 -1)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packus_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b, <16 x i16> %passThru, i16 %mask) {
; CHECK-LABEL: test_mask_packus_epi32_rmk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackusdw (%rdi), %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf2,0x7d,0x29,0x2b,0x0f]
; CHECK-NEXT: vmovdqa %ymm1, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packus_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_b, i16 %mask) {
; CHECK-LABEL: test_mask_packus_epi32_rmkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackusdw (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0xa9,0x2b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packus_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_packus_epi32_rmb_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackusdw (%rdi){1to8}, %ymm0, %ymm0 ## encoding: [0x62,0xf2,0x7d,0x38,0x2b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 -1)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packus_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <16 x i16> %passThru, i16 %mask) {
; CHECK-LABEL: test_mask_packus_epi32_rmbk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackusdw (%rdi){1to8}, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf2,0x7d,0x39,0x2b,0x0f]
; CHECK-NEXT: vmovdqa %ymm1, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask)
ret <16 x i16> %res
}
define <16 x i16> @test_mask_packus_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i16 %mask) {
; CHECK-LABEL: test_mask_packus_epi32_rmbkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackusdw (%rdi){1to8}, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0xb9,0x2b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
}
declare <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32>, <8 x i32>, <16 x i16>, i16)
define <16 x i8> @test_mask_packus_epi16_rr_128(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: test_mask_packus_epi16_rr_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackuswb %xmm1, %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x67,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 -1)
ret <16 x i8> %res
}
define <16 x i8> @test_mask_packus_epi16_rrk_128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask) {
; CHECK-LABEL: test_mask_packus_epi16_rrk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackuswb %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x67,0xd1]
; CHECK-NEXT: vmovdqa %xmm2, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask)
ret <16 x i8> %res
}
define <16 x i8> @test_mask_packus_epi16_rrkz_128(<8 x i16> %a, <8 x i16> %b, i16 %mask) {
; CHECK-LABEL: test_mask_packus_epi16_rrkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackuswb %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x67,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 %mask)
ret <16 x i8> %res
}
define <16 x i8> @test_mask_packus_epi16_rm_128(<8 x i16> %a, <8 x i16>* %ptr_b) {
; CHECK-LABEL: test_mask_packus_epi16_rm_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackuswb (%rdi), %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x67,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i16>, <8 x i16>* %ptr_b
%res = call <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 -1)
ret <16 x i8> %res
}
define <16 x i8> @test_mask_packus_epi16_rmk_128(<8 x i16> %a, <8 x i16>* %ptr_b, <16 x i8> %passThru, i16 %mask) {
; CHECK-LABEL: test_mask_packus_epi16_rmk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackuswb (%rdi), %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x67,0x0f]
; CHECK-NEXT: vmovdqa %xmm1, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i16>, <8 x i16>* %ptr_b
%res = call <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask)
ret <16 x i8> %res
}
define <16 x i8> @test_mask_packus_epi16_rmkz_128(<8 x i16> %a, <8 x i16>* %ptr_b, i16 %mask) {
; CHECK-LABEL: test_mask_packus_epi16_rmkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpackuswb (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x67,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i16>, <8 x i16>* %ptr_b
%res = call <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 %mask)
ret <16 x i8> %res
}
declare <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16>, <8 x i16>, <16 x i8>, i16)
define <32 x i8> @test_mask_packus_epi16_rr_256(<16 x i16> %a, <16 x i16> %b) {
; CHECK-LABEL: test_mask_packus_epi16_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackuswb %ymm1, %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x67,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 -1)
ret <32 x i8> %res
}
define <32 x i8> @test_mask_packus_epi16_rrk_256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask) {
; CHECK-LABEL: test_mask_packus_epi16_rrk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovd %edi, %k1 ## encoding: [0xc5,0xfb,0x92,0xcf]
; CHECK-NEXT: vpackuswb %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x67,0xd1]
; CHECK-NEXT: vmovdqa %ymm2, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask)
ret <32 x i8> %res
}
define <32 x i8> @test_mask_packus_epi16_rrkz_256(<16 x i16> %a, <16 x i16> %b, i32 %mask) {
; CHECK-LABEL: test_mask_packus_epi16_rrkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovd %edi, %k1 ## encoding: [0xc5,0xfb,0x92,0xcf]
; CHECK-NEXT: vpackuswb %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x67,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 %mask)
ret <32 x i8> %res
}
define <32 x i8> @test_mask_packus_epi16_rm_256(<16 x i16> %a, <16 x i16>* %ptr_b) {
; CHECK-LABEL: test_mask_packus_epi16_rm_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackuswb (%rdi), %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x67,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <16 x i16>, <16 x i16>* %ptr_b
%res = call <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 -1)
ret <32 x i8> %res
}
define <32 x i8> @test_mask_packus_epi16_rmk_256(<16 x i16> %a, <16 x i16>* %ptr_b, <32 x i8> %passThru, i32 %mask) {
; CHECK-LABEL: test_mask_packus_epi16_rmk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovd %esi, %k1 ## encoding: [0xc5,0xfb,0x92,0xce]
; CHECK-NEXT: vpackuswb (%rdi), %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x67,0x0f]
; CHECK-NEXT: vmovdqa %ymm1, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <16 x i16>, <16 x i16>* %ptr_b
%res = call <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask)
ret <32 x i8> %res
}
define <32 x i8> @test_mask_packus_epi16_rmkz_256(<16 x i16> %a, <16 x i16>* %ptr_b, i32 %mask) {
; CHECK-LABEL: test_mask_packus_epi16_rmkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovd %esi, %k1 ## encoding: [0xc5,0xfb,0x92,0xce]
; CHECK-NEXT: vpackuswb (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x67,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <16 x i16>, <16 x i16>* %ptr_b
%res = call <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 %mask)
ret <32 x i8> %res
}
declare <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16>, <16 x i16>, <32 x i8>, i32)

336
llvm/test/CodeGen/X86/avx512bwvl-intrinsics.ll
View File

@ -882,8 +882,8 @@ define <8 x i16> @test_mask_packs_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK: ## BB#0:
; CHECK-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 -1)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
ret <8 x i16> %1
}
define <8 x i16> @test_mask_packs_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask) {
@ -893,8 +893,10 @@ define <8 x i16> @test_mask_packs_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <8 x
; CHECK-NEXT: vpackssdw %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x6b,0xd1]
; CHECK-NEXT: vmovdqa %xmm2, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
ret <8 x i16> %3
}
define <8 x i16> @test_mask_packs_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
@ -903,8 +905,10 @@ define <8 x i16> @test_mask_packs_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackssdw %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x6b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
ret <8 x i16> %3
}
define <8 x i16> @test_mask_packs_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b) {
@ -913,8 +917,8 @@ define <8 x i16> @test_mask_packs_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b)
; CHECK-NEXT: vpackssdw (%rdi), %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 -1)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
ret <8 x i16> %1
}
define <8 x i16> @test_mask_packs_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b, <8 x i16> %passThru, i8 %mask) {
@ -925,8 +929,10 @@ define <8 x i16> @test_mask_packs_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b,
; CHECK-NEXT: vmovdqa %xmm1, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
ret <8 x i16> %3
}
define <8 x i16> @test_mask_packs_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b, i8 %mask) {
@ -936,8 +942,10 @@ define <8 x i16> @test_mask_packs_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b
; CHECK-NEXT: vpackssdw (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x6b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
ret <8 x i16> %3
}
define <8 x i16> @test_mask_packs_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
@ -948,8 +956,8 @@ define <8 x i16> @test_mask_packs_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 -1)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
ret <8 x i16> %1
}
define <8 x i16> @test_mask_packs_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <8 x i16> %passThru, i8 %mask) {
@ -962,8 +970,10 @@ define <8 x i16> @test_mask_packs_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <8 x
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
ret <8 x i16> %3
}
define <8 x i16> @test_mask_packs_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8 %mask) {
@ -975,19 +985,21 @@ define <8 x i16> @test_mask_packs_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
ret <8 x i16> %3
}
declare <8 x i16> @llvm.x86.avx512.mask.packssdw.128(<4 x i32>, <4 x i32>, <8 x i16>, i8)
declare <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32>, <4 x i32>)
define <16 x i16> @test_mask_packs_epi32_rr_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_mask_packs_epi32_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 -1)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
ret <16 x i16> %1
}
define <16 x i16> @test_mask_packs_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask) {
@ -997,8 +1009,10 @@ define <16 x i16> @test_mask_packs_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <16
; CHECK-NEXT: vpackssdw %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x6b,0xd1]
; CHECK-NEXT: vmovdqa %ymm2, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
ret <16 x i16> %3
}
define <16 x i16> @test_mask_packs_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i16 %mask) {
@ -1007,8 +1021,10 @@ define <16 x i16> @test_mask_packs_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i1
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x6b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
ret <16 x i16> %3
}
define <16 x i16> @test_mask_packs_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b) {
@ -1017,8 +1033,8 @@ define <16 x i16> @test_mask_packs_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b)
; CHECK-NEXT: vpackssdw (%rdi), %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 -1)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
ret <16 x i16> %1
}
define <16 x i16> @test_mask_packs_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b, <16 x i16> %passThru, i16 %mask) {
@ -1029,8 +1045,10 @@ define <16 x i16> @test_mask_packs_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b
; CHECK-NEXT: vmovdqa %ymm1, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
ret <16 x i16> %3
}
define <16 x i16> @test_mask_packs_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_b, i16 %mask) {
@ -1040,8 +1058,10 @@ define <16 x i16> @test_mask_packs_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_
; CHECK-NEXT: vpackssdw (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x6b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
ret <16 x i16> %3
}
define <16 x i16> @test_mask_packs_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
@ -1052,8 +1072,8 @@ define <16 x i16> @test_mask_packs_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 -1)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
ret <16 x i16> %1
}
define <16 x i16> @test_mask_packs_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <16 x i16> %passThru, i16 %mask) {
@ -1066,8 +1086,10 @@ define <16 x i16> @test_mask_packs_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <16
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
ret <16 x i16> %3
}
define <16 x i16> @test_mask_packs_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i16 %mask) {
@ -1079,19 +1101,21 @@ define <16 x i16> @test_mask_packs_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i1
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
ret <16 x i16> %3
}
declare <16 x i16> @llvm.x86.avx512.mask.packssdw.256(<8 x i32>, <8 x i32>, <16 x i16>, i16)
declare <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32>, <8 x i32>)
define <16 x i8> @test_mask_packs_epi16_rr_128(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: test_mask_packs_epi16_rr_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x63,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 -1)
ret <16 x i8> %res
%1 = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a, <8 x i16> %b)
ret <16 x i8> %1
}
define <16 x i8> @test_mask_packs_epi16_rrk_128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask) {
@ -1101,8 +1125,10 @@ define <16 x i8> @test_mask_packs_epi16_rrk_128(<8 x i16> %a, <8 x i16> %b, <16
; CHECK-NEXT: vpacksswb %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x63,0xd1]
; CHECK-NEXT: vmovdqa %xmm2, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask)
ret <16 x i8> %res
%1 = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a, <8 x i16> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passThru
ret <16 x i8> %3
}
define <16 x i8> @test_mask_packs_epi16_rrkz_128(<8 x i16> %a, <8 x i16> %b, i16 %mask) {
@ -1111,8 +1137,10 @@ define <16 x i8> @test_mask_packs_epi16_rrkz_128(<8 x i16> %a, <8 x i16> %b, i16
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpacksswb %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x63,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 %mask)
ret <16 x i8> %res
%1 = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a, <8 x i16> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> zeroinitializer
ret <16 x i8> %3
}
define <16 x i8> @test_mask_packs_epi16_rm_128(<8 x i16> %a, <8 x i16>* %ptr_b) {
@ -1121,8 +1149,8 @@ define <16 x i8> @test_mask_packs_epi16_rm_128(<8 x i16> %a, <8 x i16>* %ptr_b)
; CHECK-NEXT: vpacksswb (%rdi), %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x63,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i16>, <8 x i16>* %ptr_b
%res = call <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 -1)
ret <16 x i8> %res
%1 = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a, <8 x i16> %b)
ret <16 x i8> %1
}
define <16 x i8> @test_mask_packs_epi16_rmk_128(<8 x i16> %a, <8 x i16>* %ptr_b, <16 x i8> %passThru, i16 %mask) {
@ -1133,8 +1161,10 @@ define <16 x i8> @test_mask_packs_epi16_rmk_128(<8 x i16> %a, <8 x i16>* %ptr_b,
; CHECK-NEXT: vmovdqa %xmm1, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i16>, <8 x i16>* %ptr_b
%res = call <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask)
ret <16 x i8> %res
%1 = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a, <8 x i16> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passThru
ret <16 x i8> %3
}
define <16 x i8> @test_mask_packs_epi16_rmkz_128(<8 x i16> %a, <8 x i16>* %ptr_b, i16 %mask) {
@ -1144,19 +1174,21 @@ define <16 x i8> @test_mask_packs_epi16_rmkz_128(<8 x i16> %a, <8 x i16>* %ptr_b
; CHECK-NEXT: vpacksswb (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x63,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i16>, <8 x i16>* %ptr_b
%res = call <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 %mask)
ret <16 x i8> %res
%1 = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a, <8 x i16> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> zeroinitializer
ret <16 x i8> %3
}
declare <16 x i8> @llvm.x86.avx512.mask.packsswb.128(<8 x i16>, <8 x i16>, <16 x i8>, i16)
declare <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16>, <8 x i16>)
define <32 x i8> @test_mask_packs_epi16_rr_256(<16 x i16> %a, <16 x i16> %b) {
; CHECK-LABEL: test_mask_packs_epi16_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpacksswb %ymm1, %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x63,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 -1)
ret <32 x i8> %res
%1 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a, <16 x i16> %b)
ret <32 x i8> %1
}
define <32 x i8> @test_mask_packs_epi16_rrk_256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask) {
@ -1166,8 +1198,10 @@ define <32 x i8> @test_mask_packs_epi16_rrk_256(<16 x i16> %a, <16 x i16> %b, <3
; CHECK-NEXT: vpacksswb %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x63,0xd1]
; CHECK-NEXT: vmovdqa %ymm2, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask)
ret <32 x i8> %res
%1 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a, <16 x i16> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passThru
ret <32 x i8> %3
}
define <32 x i8> @test_mask_packs_epi16_rrkz_256(<16 x i16> %a, <16 x i16> %b, i32 %mask) {
@ -1176,8 +1210,10 @@ define <32 x i8> @test_mask_packs_epi16_rrkz_256(<16 x i16> %a, <16 x i16> %b, i
; CHECK-NEXT: kmovd %edi, %k1 ## encoding: [0xc5,0xfb,0x92,0xcf]
; CHECK-NEXT: vpacksswb %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x63,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 %mask)
ret <32 x i8> %res
%1 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a, <16 x i16> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> zeroinitializer
ret <32 x i8> %3
}
define <32 x i8> @test_mask_packs_epi16_rm_256(<16 x i16> %a, <16 x i16>* %ptr_b) {
@ -1186,8 +1222,8 @@ define <32 x i8> @test_mask_packs_epi16_rm_256(<16 x i16> %a, <16 x i16>* %ptr_b
; CHECK-NEXT: vpacksswb (%rdi), %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x63,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <16 x i16>, <16 x i16>* %ptr_b
%res = call <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 -1)
ret <32 x i8> %res
%1 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a, <16 x i16> %b)
ret <32 x i8> %1
}
define <32 x i8> @test_mask_packs_epi16_rmk_256(<16 x i16> %a, <16 x i16>* %ptr_b, <32 x i8> %passThru, i32 %mask) {
@ -1198,8 +1234,10 @@ define <32 x i8> @test_mask_packs_epi16_rmk_256(<16 x i16> %a, <16 x i16>* %ptr_
; CHECK-NEXT: vmovdqa %ymm1, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <16 x i16>, <16 x i16>* %ptr_b
%res = call <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask)
ret <32 x i8> %res
%1 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a, <16 x i16> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passThru
ret <32 x i8> %3
}
define <32 x i8> @test_mask_packs_epi16_rmkz_256(<16 x i16> %a, <16 x i16>* %ptr_b, i32 %mask) {
@ -1209,11 +1247,13 @@ define <32 x i8> @test_mask_packs_epi16_rmkz_256(<16 x i16> %a, <16 x i16>* %ptr
; CHECK-NEXT: vpacksswb (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x63,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <16 x i16>, <16 x i16>* %ptr_b
%res = call <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 %mask)
ret <32 x i8> %res
%1 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a, <16 x i16> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> zeroinitializer
ret <32 x i8> %3
}
declare <32 x i8> @llvm.x86.avx512.mask.packsswb.256(<16 x i16>, <16 x i16>, <32 x i8>, i32)
declare <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16>, <16 x i16>)
define <8 x i16> @test_mask_packus_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
@ -1221,8 +1261,8 @@ define <8 x i16> @test_mask_packus_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK: ## BB#0:
; CHECK-NEXT: vpackusdw %xmm1, %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x2b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 -1)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
ret <8 x i16> %1
}
define <8 x i16> @test_mask_packus_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask) {
@ -1232,8 +1272,10 @@ define <8 x i16> @test_mask_packus_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <8
; CHECK-NEXT: vpackusdw %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf2,0x7d,0x09,0x2b,0xd1]
; CHECK-NEXT: vmovdqa %xmm2, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
ret <8 x i16> %3
}
define <8 x i16> @test_mask_packus_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
@ -1242,8 +1284,10 @@ define <8 x i16> @test_mask_packus_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackusdw %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x2b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
ret <8 x i16> %3
}
define <8 x i16> @test_mask_packus_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b) {
@ -1252,8 +1296,8 @@ define <8 x i16> @test_mask_packus_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b)
; CHECK-NEXT: vpackusdw (%rdi), %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x2b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 -1)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
ret <8 x i16> %1
}
define <8 x i16> @test_mask_packus_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b, <8 x i16> %passThru, i8 %mask) {
@ -1264,8 +1308,10 @@ define <8 x i16> @test_mask_packus_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b
; CHECK-NEXT: vmovdqa %xmm1, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
ret <8 x i16> %3
}
define <8 x i16> @test_mask_packus_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b, i8 %mask) {
@ -1275,8 +1321,10 @@ define <8 x i16> @test_mask_packus_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_
; CHECK-NEXT: vpackusdw (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x2b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
ret <8 x i16> %3
}
define <8 x i16> @test_mask_packus_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
@ -1287,8 +1335,8 @@ define <8 x i16> @test_mask_packus_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 -1)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
ret <8 x i16> %1
}
define <8 x i16> @test_mask_packus_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <8 x i16> %passThru, i8 %mask) {
@ -1301,8 +1349,10 @@ define <8 x i16> @test_mask_packus_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <8
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
ret <8 x i16> %3
}
define <8 x i16> @test_mask_packus_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8 %mask) {
@ -1314,19 +1364,21 @@ define <8 x i16> @test_mask_packus_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32> %a, <4 x i32> %b, <8 x i16> zeroinitializer, i8 %mask)
ret <8 x i16> %res
%1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
ret <8 x i16> %3
}
declare <8 x i16> @llvm.x86.avx512.mask.packusdw.128(<4 x i32>, <4 x i32>, <8 x i16>, i8)
declare <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32>, <4 x i32>)
define <16 x i16> @test_mask_packus_epi32_rr_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_mask_packus_epi32_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackusdw %ymm1, %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x2b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 -1)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
ret <16 x i16> %1
}
define <16 x i16> @test_mask_packus_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask) {
@ -1336,8 +1388,10 @@ define <16 x i16> @test_mask_packus_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <1
; CHECK-NEXT: vpackusdw %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf2,0x7d,0x29,0x2b,0xd1]
; CHECK-NEXT: vmovdqa %ymm2, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
ret <16 x i16> %3
}
define <16 x i16> @test_mask_packus_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i16 %mask) {
@ -1346,8 +1400,10 @@ define <16 x i16> @test_mask_packus_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackusdw %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0xa9,0x2b,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
ret <16 x i16> %3
}
define <16 x i16> @test_mask_packus_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b) {
@ -1356,8 +1412,8 @@ define <16 x i16> @test_mask_packus_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b
; CHECK-NEXT: vpackusdw (%rdi), %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x2b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 -1)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
ret <16 x i16> %1
}
define <16 x i16> @test_mask_packus_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b, <16 x i16> %passThru, i16 %mask) {
@ -1368,8 +1424,10 @@ define <16 x i16> @test_mask_packus_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_
; CHECK-NEXT: vmovdqa %ymm1, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
ret <16 x i16> %3
}
define <16 x i16> @test_mask_packus_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_b, i16 %mask) {
@ -1379,8 +1437,10 @@ define <16 x i16> @test_mask_packus_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr
; CHECK-NEXT: vpackusdw (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0xa9,0x2b,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
ret <16 x i16> %3
}
define <16 x i16> @test_mask_packus_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
@ -1391,8 +1451,8 @@ define <16 x i16> @test_mask_packus_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 -1)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
ret <16 x i16> %1
}
define <16 x i16> @test_mask_packus_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <16 x i16> %passThru, i16 %mask) {
@ -1405,8 +1465,10 @@ define <16 x i16> @test_mask_packus_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <1
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
ret <16 x i16> %3
}
define <16 x i16> @test_mask_packus_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i16 %mask) {
@ -1418,19 +1480,21 @@ define <16 x i16> @test_mask_packus_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32> %a, <8 x i32> %b, <16 x i16> zeroinitializer, i16 %mask)
ret <16 x i16> %res
%1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
ret <16 x i16> %3
}
declare <16 x i16> @llvm.x86.avx512.mask.packusdw.256(<8 x i32>, <8 x i32>, <16 x i16>, i16)
declare <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32>, <8 x i32>)
define <16 x i8> @test_mask_packus_epi16_rr_128(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: test_mask_packus_epi16_rr_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackuswb %xmm1, %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x67,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 -1)
ret <16 x i8> %res
%1 = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a, <8 x i16> %b)
ret <16 x i8> %1
}
define <16 x i8> @test_mask_packus_epi16_rrk_128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask) {
@ -1440,8 +1504,10 @@ define <16 x i8> @test_mask_packus_epi16_rrk_128(<8 x i16> %a, <8 x i16> %b, <16
; CHECK-NEXT: vpackuswb %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x67,0xd1]
; CHECK-NEXT: vmovdqa %xmm2, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask)
ret <16 x i8> %res
%1 = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a, <8 x i16> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passThru
ret <16 x i8> %3
}
define <16 x i8> @test_mask_packus_epi16_rrkz_128(<8 x i16> %a, <8 x i16> %b, i16 %mask) {
@ -1450,8 +1516,10 @@ define <16 x i8> @test_mask_packus_epi16_rrkz_128(<8 x i16> %a, <8 x i16> %b, i1
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpackuswb %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x67,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 %mask)
ret <16 x i8> %res
%1 = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a, <8 x i16> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> zeroinitializer
ret <16 x i8> %3
}
define <16 x i8> @test_mask_packus_epi16_rm_128(<8 x i16> %a, <8 x i16>* %ptr_b) {
@ -1460,8 +1528,8 @@ define <16 x i8> @test_mask_packus_epi16_rm_128(<8 x i16> %a, <8 x i16>* %ptr_b)
; CHECK-NEXT: vpackuswb (%rdi), %xmm0, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x67,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i16>, <8 x i16>* %ptr_b
%res = call <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 -1)
ret <16 x i8> %res
%1 = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a, <8 x i16> %b)
ret <16 x i8> %1
}
define <16 x i8> @test_mask_packus_epi16_rmk_128(<8 x i16> %a, <8 x i16>* %ptr_b, <16 x i8> %passThru, i16 %mask) {
@ -1472,8 +1540,10 @@ define <16 x i8> @test_mask_packus_epi16_rmk_128(<8 x i16> %a, <8 x i16>* %ptr_b
; CHECK-NEXT: vmovdqa %xmm1, %xmm0 ## EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i16>, <8 x i16>* %ptr_b
%res = call <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask)
ret <16 x i8> %res
%1 = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a, <8 x i16> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passThru
ret <16 x i8> %3
}
define <16 x i8> @test_mask_packus_epi16_rmkz_128(<8 x i16> %a, <8 x i16>* %ptr_b, i16 %mask) {
@ -1483,19 +1553,21 @@ define <16 x i8> @test_mask_packus_epi16_rmkz_128(<8 x i16> %a, <8 x i16>* %ptr_
; CHECK-NEXT: vpackuswb (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x67,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i16>, <8 x i16>* %ptr_b
%res = call <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16> %a, <8 x i16> %b, <16 x i8> zeroinitializer, i16 %mask)
ret <16 x i8> %res
%1 = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a, <8 x i16> %b)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> zeroinitializer
ret <16 x i8> %3
}
declare <16 x i8> @llvm.x86.avx512.mask.packuswb.128(<8 x i16>, <8 x i16>, <16 x i8>, i16)
declare <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16>, <8 x i16>)
define <32 x i8> @test_mask_packus_epi16_rr_256(<16 x i16> %a, <16 x i16> %b) {
; CHECK-LABEL: test_mask_packus_epi16_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpackuswb %ymm1, %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x67,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 -1)
ret <32 x i8> %res
%1 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a, <16 x i16> %b)
ret <32 x i8> %1
}
define <32 x i8> @test_mask_packus_epi16_rrk_256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask) {
@ -1505,8 +1577,10 @@ define <32 x i8> @test_mask_packus_epi16_rrk_256(<16 x i16> %a, <16 x i16> %b, <
; CHECK-NEXT: vpackuswb %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x67,0xd1]
; CHECK-NEXT: vmovdqa %ymm2, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask)
ret <32 x i8> %res
%1 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a, <16 x i16> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passThru
ret <32 x i8> %3
}
define <32 x i8> @test_mask_packus_epi16_rrkz_256(<16 x i16> %a, <16 x i16> %b, i32 %mask) {
@ -1515,8 +1589,10 @@ define <32 x i8> @test_mask_packus_epi16_rrkz_256(<16 x i16> %a, <16 x i16> %b,
; CHECK-NEXT: kmovd %edi, %k1 ## encoding: [0xc5,0xfb,0x92,0xcf]
; CHECK-NEXT: vpackuswb %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x67,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 %mask)
ret <32 x i8> %res
%1 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a, <16 x i16> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> zeroinitializer
ret <32 x i8> %3
}
define <32 x i8> @test_mask_packus_epi16_rm_256(<16 x i16> %a, <16 x i16>* %ptr_b) {
@ -1525,8 +1601,8 @@ define <32 x i8> @test_mask_packus_epi16_rm_256(<16 x i16> %a, <16 x i16>* %ptr_
; CHECK-NEXT: vpackuswb (%rdi), %ymm0, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x67,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <16 x i16>, <16 x i16>* %ptr_b
%res = call <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 -1)
ret <32 x i8> %res
%1 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a, <16 x i16> %b)
ret <32 x i8> %1
}
define <32 x i8> @test_mask_packus_epi16_rmk_256(<16 x i16> %a, <16 x i16>* %ptr_b, <32 x i8> %passThru, i32 %mask) {
@ -1537,8 +1613,10 @@ define <32 x i8> @test_mask_packus_epi16_rmk_256(<16 x i16> %a, <16 x i16>* %ptr
; CHECK-NEXT: vmovdqa %ymm1, %ymm0 ## EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <16 x i16>, <16 x i16>* %ptr_b
%res = call <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask)
ret <32 x i8> %res
%1 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a, <16 x i16> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passThru
ret <32 x i8> %3
}
define <32 x i8> @test_mask_packus_epi16_rmkz_256(<16 x i16> %a, <16 x i16>* %ptr_b, i32 %mask) {
@ -1548,11 +1626,13 @@ define <32 x i8> @test_mask_packus_epi16_rmkz_256(<16 x i16> %a, <16 x i16>* %pt
; CHECK-NEXT: vpackuswb (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x67,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <16 x i16>, <16 x i16>* %ptr_b
%res = call <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16> %a, <16 x i16> %b, <32 x i8> zeroinitializer, i32 %mask)
ret <32 x i8> %res
%1 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a, <16 x i16> %b)
%2 = bitcast i32 %mask to <32 x i1>
%3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> zeroinitializer
ret <32 x i8> %3
}
declare <32 x i8> @llvm.x86.avx512.mask.packuswb.256(<16 x i16>, <16 x i16>, <32 x i8>, i32)
declare <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16>, <16 x i16>)
define <8 x i16> @test_mask_adds_epi16_rr_128(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: test_mask_adds_epi16_rr_128: