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

[X86][AVX512] Removing llvm x86 intrinsics for _mm_mask_move_{ss|sd} intrinsics. 

Differential Revision: https://reviews.llvm.org/D26128

llvm-svn: 286761
This commit is contained in:
Ayman Musa 2016-11-13 14:51:25 +00:00
parent 22012a5973
commit c09b3769ae
4 changed files with 65 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
llvm/include/llvm/IR/IntrinsicsX86.td
View File

@ -1668,20 +1668,6 @@ let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
[IntrReadMem, IntrArgMemOnly]>;
}
// Conditional move ops
let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
def int_x86_avx512_mask_move_ss :
GCCBuiltin<"__builtin_ia32_movss_mask">,
Intrinsic<[llvm_v4f32_ty],
[llvm_v4f32_ty, llvm_v4f32_ty, llvm_v4f32_ty, llvm_i8_ty],
[IntrNoMem]>;
def int_x86_avx512_mask_move_sd :
GCCBuiltin<"__builtin_ia32_movsd_mask">,
Intrinsic<[llvm_v2f64_ty],
[llvm_v2f64_ty, llvm_v2f64_ty, llvm_v2f64_ty, llvm_i8_ty],
[IntrNoMem]>;
}
// Conditional store ops
let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
def int_x86_avx_maskstore_pd : GCCBuiltin<"__builtin_ia32_maskstorepd">,

17
llvm/lib/IR/AutoUpgrade.cpp
View File

@ -365,6 +365,7 @@ static bool UpgradeIntrinsicFunction1(Function *F, Function *&NewFn) {
Name.startswith("avx2.pblendd.") ||
Name.startswith("avx.vbroadcastf128") ||
Name == "avx2.vbroadcasti128" ||
Name.startswith("avx512.mask.move.s") ||
Name == "xop.vpcmov" ||
(Name.startswith("xop.vpcom") && F->arg_size() == 2))) {
NewFn = nullptr;
@ -679,6 +680,20 @@ static Value *upgradeMaskedCompare(IRBuilder<> &Builder, CallInst &CI,
std::max(NumElts, 8U)));
}
static Value* upgradeMaskedMove(IRBuilder<> &Builder, CallInst &CI) {
Value* A = CI.getArgOperand(0);
Value* B = CI.getArgOperand(1);
Value* Src = CI.getArgOperand(2);
Value* Mask = CI.getArgOperand(3);
Value* AndNode = Builder.CreateAnd(Mask, APInt(8, 1));
Value* Cmp = Builder.CreateIsNotNull(AndNode);
Value* Extract1 = Builder.CreateExtractElement(B, (uint64_t)0);
Value* Extract2 = Builder.CreateExtractElement(Src, (uint64_t)0);
Value* Select = Builder.CreateSelect(Cmp, Extract1, Extract2);
return Builder.CreateInsertElement(A, Select, (uint64_t)0);
}
// Replace a masked intrinsic with an older unmasked intrinsic.
static Value *UpgradeX86MaskedShift(IRBuilder<> &Builder, CallInst &CI,
Intrinsic::ID IID) {
@ -1341,6 +1356,8 @@ void llvm::UpgradeIntrinsicCall(CallInst *CI, Function *NewFn) {
Rep = Builder.CreateFSub(CI->getArgOperand(0), CI->getArgOperand(1));
Rep = EmitX86Select(Builder, CI->getArgOperand(3), Rep,
CI->getArgOperand(2));
} else if (IsX86 && Name.startswith("avx512.mask.move.s")) {
Rep = upgradeMaskedMove(Builder, *CI);
} else if (IsX86 && Name.startswith("avx512.mask.pshuf.b.")) {
VectorType *VecTy = cast<VectorType>(CI->getType());
Intrinsic::ID IID;

4
llvm/lib/Target/X86/X86IntrinsicsInfo.h
View File

@ -794,10 +794,6 @@ static const IntrinsicData IntrinsicsWithoutChain[] = {
X86ISD::FMIN_RND, 0),
X86_INTRINSIC_DATA(avx512_mask_min_ss_round, INTR_TYPE_SCALAR_MASK_RM,
X86ISD::FMIN_RND, 0),
X86_INTRINSIC_DATA(avx512_mask_move_sd, INTR_TYPE_SCALAR_MASK,
X86ISD::MOVSD, 0),
X86_INTRINSIC_DATA(avx512_mask_move_ss, INTR_TYPE_SCALAR_MASK,
X86ISD::MOVSS, 0),
X86_INTRINSIC_DATA(avx512_mask_mul_pd_512, INTR_TYPE_2OP_MASK, ISD::FMUL,
X86ISD::FMUL_RND),
X86_INTRINSIC_DATA(avx512_mask_mul_ps_512, INTR_TYPE_2OP_MASK, ISD::FMUL,

48
llvm/test/CodeGen/X86/avx512-intrinsics-upgrade.ll
View File

@ -1765,6 +1765,54 @@ define <8 x i64>@test_int_x86_avx512_mask_pminu_q_512(<8 x i64> %x0, <8 x i64> %
ret <8 x i64> %res2
}
define <4 x float> @test_mm_mask_move_ss(<4 x float> %__W, i8 zeroext %__U, <4 x float> %__A, <4 x float> %__B) {
; CHECK-LABEL: test_mm_mask_move_ss:
; CHECK: ## BB#0: ## %entry
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovss %xmm2, %xmm1, %xmm0 {%k1}
; CHECK-NEXT: retq
entry:
%res = call <4 x float> @llvm.x86.avx512.mask.move.ss(<4 x float> %__A, <4 x float> %__B, <4 x float> %__W, i8 %__U)
ret <4 x float> %res
}
define <4 x float> @test_mm_maskz_move_ss(i8 zeroext %__U, <4 x float> %__A, <4 x float> %__B) {
; CHECK-LABEL: test_mm_maskz_move_ss:
; CHECK: ## BB#0: ## %entry
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovss %xmm1, %xmm0, %xmm0 {%k1} {z}
; CHECK-NEXT: retq
entry:
%res = call <4 x float> @llvm.x86.avx512.mask.move.ss(<4 x float> %__A, <4 x float> %__B, <4 x float> zeroinitializer, i8 %__U)
ret <4 x float> %res
}
define <2 x double> @test_mm_mask_move_sd(<2 x double> %__W, i8 zeroext %__U, <2 x double> %__A, <2 x double> %__B) {
; CHECK-LABEL: test_mm_mask_move_sd:
; CHECK: ## BB#0: ## %entry
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovsd %xmm2, %xmm1, %xmm0 {%k1}
; CHECK-NEXT: retq
entry:
%res = call <2 x double> @llvm.x86.avx512.mask.move.sd(<2 x double> %__A, <2 x double> %__B, <2 x double> %__W, i8 %__U)
ret <2 x double> %res
}
define <2 x double> @test_mm_maskz_move_sd(i8 zeroext %__U, <2 x double> %__A, <2 x double> %__B) {
; CHECK-LABEL: test_mm_maskz_move_sd:
; CHECK: ## BB#0: ## %entry
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vmovsd %xmm1, %xmm0, %xmm0 {%k1} {z}
; CHECK-NEXT: retq
entry:
%res = call <2 x double> @llvm.x86.avx512.mask.move.sd(<2 x double> %__A, <2 x double> %__B, <2 x double> zeroinitializer, i8 %__U)
ret <2 x double> %res
}
declare <4 x float> @llvm.x86.avx512.mask.move.ss(<4 x float>, <4 x float>, <4 x float>, i8)
declare <2 x double> @llvm.x86.avx512.mask.move.sd(<2 x double>, <2 x double>, <2 x double>, i8)
declare <16 x i32> @llvm.x86.avx512.mask.pmovzxb.d.512(<16 x i8>, <16 x i32>, i16)
define <16 x i32>@test_int_x86_avx512_mask_pmovzxb_d_512(<16 x i8> %x0, <16 x i32> %x1, i16 %x2) {