From: Dinar Temirbulatov Date: Fri, 16 Jun 2017 12:09:52 +0000 (+0000) Subject: Expand vector oparation to as IR constants, PR28129. X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=6adac51dabb51771aade9b29f059f562b7f457c3;p=clang Expand vector oparation to as IR constants, PR28129. git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@305551 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/lib/CodeGen/CGBuiltin.cpp b/lib/CodeGen/CGBuiltin.cpp index 3b4f8854a9..8f0c22d1f7 100644 --- a/lib/CodeGen/CGBuiltin.cpp +++ b/lib/CodeGen/CGBuiltin.cpp @@ -7923,6 +7923,7 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID, } // We can't handle 8-31 immediates with native IR, use the intrinsic. + // Except for predicates that create constants. Intrinsic::ID ID; switch (BuiltinID) { default: llvm_unreachable("Unsupported intrinsic!"); @@ -7930,12 +7931,32 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID, ID = Intrinsic::x86_sse_cmp_ps; break; case X86::BI__builtin_ia32_cmpps256: + // _CMP_TRUE_UQ, _CMP_TRUE_US produce -1,-1... vector + // on any input and _CMP_FALSE_OQ, _CMP_FALSE_OS produce 0, 0... + if (CC == 0xf || CC == 0xb || CC == 0x1b || CC == 0x1f) { + Value *Constant = (CC == 0xf || CC == 0x1f) ? + llvm::Constant::getAllOnesValue(Builder.getInt32Ty()) : + llvm::Constant::getNullValue(Builder.getInt32Ty()); + Value *Vec = Builder.CreateVectorSplat( + Ops[0]->getType()->getVectorNumElements(), Constant); + return Builder.CreateBitCast(Vec, Ops[0]->getType()); + } ID = Intrinsic::x86_avx_cmp_ps_256; break; case X86::BI__builtin_ia32_cmppd: ID = Intrinsic::x86_sse2_cmp_pd; break; case X86::BI__builtin_ia32_cmppd256: + // _CMP_TRUE_UQ, _CMP_TRUE_US produce -1,-1... vector + // on any input and _CMP_FALSE_OQ, _CMP_FALSE_OS produce 0, 0... + if (CC == 0xf || CC == 0xb || CC == 0x1b || CC == 0x1f) { + Value *Constant = (CC == 0xf || CC == 0x1f) ? + llvm::Constant::getAllOnesValue(Builder.getInt64Ty()) : + llvm::Constant::getNullValue(Builder.getInt64Ty()); + Value *Vec = Builder.CreateVectorSplat( + Ops[0]->getType()->getVectorNumElements(), Constant); + return Builder.CreateBitCast(Vec, Ops[0]->getType()); + } ID = Intrinsic::x86_avx_cmp_pd_256; break; } diff --git a/test/CodeGen/avx-builtins.c b/test/CodeGen/avx-builtins.c index 90f428efb3..31a08440d0 100644 --- a/test/CodeGen/avx-builtins.c +++ b/test/CodeGen/avx-builtins.c @@ -1427,3 +1427,51 @@ float test_mm256_cvtss_f32(__m256 __a) // CHECK: extractelement <8 x float> %{{.*}}, i32 0 return _mm256_cvtss_f32(__a); } + +__m256 test_mm256_cmp_ps_true(__m256 a, __m256 b) { + // CHECK-LABEL: @test_mm256_cmp_ps_true + // CHECK: store <8 x float> zeroinitializer, <8 x float>* %tmp, align 32 + return _mm256_cmp_ps(a, b, _CMP_FALSE_OQ); +} + +__m256 test_mm256_cmp_pd_false(__m256 a, __m256 b) { + // CHECK-LABEL: @test_mm256_cmp_pd_false + // CHECK: store <4 x double> zeroinitializer, <4 x double>* %tmp, align 32 + return _mm256_cmp_pd(a, b, _CMP_FALSE_OQ); +} + +__m256 test_mm256_cmp_ps_strue(__m256 a, __m256 b) { + // CHECK-LABEL: @test_mm256_cmp_ps_strue + // CHECK: store <8 x float> zeroinitializer, <8 x float>* %tmp, align 32 + return _mm256_cmp_ps(a, b, _CMP_FALSE_OS); +} + +__m256 test_mm256_cmp_pd_sfalse(__m256 a, __m256 b) { + // CHECK-LABEL: @test_mm256_cmp_pd_sfalse + // CHECK: store <4 x double> zeroinitializer, <4 x double>* %tmp, align 32 + return _mm256_cmp_pd(a, b, _CMP_FALSE_OS); +}