mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 12:41:49 +01:00
[DAGCombine] Optimize pow(X, 0.75) to sqrt(X) * sqrt(sqrt(X))
The sqrt case is faster and we already do this for the case where the exponent is 0.25. This adds the 0.75 case which is also not sensitive to signed zeros. Patch by Whitney Tsang (Whitney) Differential revision: https://reviews.llvm.org/D57434 llvm-svn: 353557
This commit is contained in:
Nemanja Ivanovic
parent
1cbeacb1ea
commit
fd45134124
@ -11912,18 +11912,24 @@ SDValue DAGCombiner::visitFPOW(SDNode *N) {
|
||||
return DAG.getNode(ISD::FCBRT, SDLoc(N), VT, N->getOperand(0), Flags);
|
||||
}
|
||||
|
||||
// Try to convert x ** (1/4) into square roots.
|
||||
// Try to convert x ** (1/4) and x ** (3/4) into square roots.
|
||||
// x ** (1/2) is canonicalized to sqrt, so we do not bother with that case.
|
||||
// TODO: This could be extended (using a target hook) to handle smaller
|
||||
// power-of-2 fractional exponents.
|
||||
if (ExponentC->getValueAPF().isExactlyValue(0.25)) {
|
||||
bool ExponentIs025 = ExponentC->getValueAPF().isExactlyValue(0.25);
|
||||
bool ExponentIs075 = ExponentC->getValueAPF().isExactlyValue(0.75);
|
||||
if (ExponentIs025 || ExponentIs075) {
|
||||
// pow(-0.0, 0.25) = +0.0; sqrt(sqrt(-0.0)) = -0.0.
|
||||
// pow(-inf, 0.25) = +inf; sqrt(sqrt(-inf)) = NaN.
|
||||
// pow(-0.0, 0.75) = +0.0; sqrt(-0.0) * sqrt(sqrt(-0.0)) = +0.0.
|
||||
// pow(-inf, 0.75) = +inf; sqrt(-inf) * sqrt(sqrt(-inf)) = NaN.
|
||||
// For regular numbers, rounding may cause the results to differ.
|
||||
// Therefore, we require { nsz ninf afn } for this transform.
|
||||
// TODO: We could select out the special cases if we don't have nsz/ninf.
|
||||
SDNodeFlags Flags = N->getFlags();
|
||||
if (!Flags.hasNoSignedZeros() || !Flags.hasNoInfs() ||
|
||||
|
||||
// We only need no signed zeros for the 0.25 case.
|
||||
if ((!Flags.hasNoSignedZeros() && ExponentIs025) || !Flags.hasNoInfs() ||
|
||||
!Flags.hasApproximateFuncs())
|
||||
return SDValue();
|
||||
|
||||
@ -11939,7 +11945,11 @@ SDValue DAGCombiner::visitFPOW(SDNode *N) {
|
||||
// pow(X, 0.25) --> sqrt(sqrt(X))
|
||||
SDLoc DL(N);
|
||||
SDValue Sqrt = DAG.getNode(ISD::FSQRT, DL, VT, N->getOperand(0), Flags);
|
||||
return DAG.getNode(ISD::FSQRT, DL, VT, Sqrt, Flags);
|
||||
SDValue SqrtSqrt = DAG.getNode(ISD::FSQRT, DL, VT, Sqrt, Flags);
|
||||
if (ExponentIs025)
|
||||
return SqrtSqrt;
|
||||
// pow(X, 0.75) --> sqrt(X) * sqrt(sqrt(X))
|
||||
return DAG.getNode(ISD::FMUL, DL, VT, Sqrt, SqrtSqrt, Flags);
|
||||
}
|
||||
|
||||
return SDValue();
|
||||
|
||||
48
test/CodeGen/AArch64/pow.75.ll
Normal file
48
test/CodeGen/AArch64/pow.75.ll
Normal file
@ -0,0 +1,48 @@
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=aarch64-- -debug 2>&1 | FileCheck %s
|
||||
; REQUIRES: asserts
|
||||
|
||||
declare float @llvm.pow.f32(float, float)
|
||||
declare <4 x float> @llvm.pow.v4f32(<4 x float>, <4 x float>)
|
||||
declare double @llvm.pow.f64(double, double)
|
||||
declare <2 x double> @llvm.pow.v2f64(<2 x double>, <2 x double>)
|
||||
|
||||
define float @pow_f32_three_fourth_fmf(float %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: f32 = fpow ninf nsz afn [[X:t[0-9]+]], ConstantFP:f32<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f32 = fsqrt ninf nsz afn [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f32 = fsqrt ninf nsz afn [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f32 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f32 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call nsz ninf afn float @llvm.pow.f32(float %x, float 7.5e-01)
|
||||
ret float %r
|
||||
}
|
||||
|
||||
define double @pow_f64_three_fourth_fmf(double %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: f64 = fpow ninf nsz afn [[X:t[0-9]+]], ConstantFP:f64<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f64 = fsqrt ninf nsz afn [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f64 = fsqrt ninf nsz afn [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f64 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f64 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call nsz ninf afn double @llvm.pow.f64(double %x, double 7.5e-01)
|
||||
ret double %r
|
||||
}
|
||||
|
||||
define <4 x float> @pow_v4f32_three_fourth_fmf(<4 x float> %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: v4f32 = fpow nnan ninf nsz arcp contract afn reassoc [[X:t[0-9]+]], {{.*}}
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: v4f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: v4f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: v4f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: v4f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call fast <4 x float> @llvm.pow.v4f32(<4 x float> %x, <4 x float> <float 7.5e-1, float 7.5e-1, float 7.5e-01, float 7.5e-01>)
|
||||
ret <4 x float> %r
|
||||
}
|
||||
|
||||
define <2 x double> @pow_v2f64_three_fourth_fmf(<2 x double> %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: v2f64 = fpow nnan ninf nsz arcp contract afn reassoc [[X:t[0-9]+]], {{.*}}
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: v2f64 = fsqrt nnan ninf nsz arcp contract afn reassoc [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: v2f64 = fsqrt nnan ninf nsz arcp contract afn reassoc [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: v2f64 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: v2f64 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call fast <2 x double> @llvm.pow.v2f64(<2 x double> %x, <2 x double> <double 7.5e-1, double 7.5e-1>)
|
||||
ret <2 x double> %r
|
||||
}
|
||||
70
test/CodeGen/ARM/pow.75.ll
Normal file
70
test/CodeGen/ARM/pow.75.ll
Normal file
@ -0,0 +1,70 @@
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=thumbv8-linux-gnueabihf -mattr=neon -debug 2>&1 | FileCheck %s
|
||||
; REQUIRES: asserts
|
||||
|
||||
declare float @llvm.pow.f32(float, float)
|
||||
declare <4 x float> @llvm.pow.v4f32(<4 x float>, <4 x float>)
|
||||
declare double @llvm.pow.f64(double, double)
|
||||
declare <2 x double> @llvm.pow.v2f64(<2 x double>, <2 x double>)
|
||||
|
||||
define float @pow_f32_three_fourth_fmf(float %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: f32 = fpow ninf nsz afn [[X:t[0-9]+]], ConstantFP:f32<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f32 = fsqrt ninf nsz afn [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f32 = fsqrt ninf nsz afn [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f32 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f32 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call nsz ninf afn float @llvm.pow.f32(float %x, float 7.5e-01)
|
||||
ret float %r
|
||||
}
|
||||
|
||||
define double @pow_f64_three_fourth_fmf(double %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: f64 = fpow ninf nsz afn t2, ConstantFP:f64<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f64 = fsqrt ninf nsz afn [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f64 = fsqrt ninf nsz afn [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f64 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f64 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call nsz ninf afn double @llvm.pow.f64(double %x, double 7.5e-01)
|
||||
ret double %r
|
||||
}
|
||||
|
||||
define <4 x float> @pow_v4f32_three_fourth_fmf(<4 x float> %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: v4f32 = BUILD_VECTOR [[FORTH:t[0-9]+]], [[THIRD:t[0-9]+]], [[SECOND:t[0-9]+]], [[FIRST:t[0-9]+]]
|
||||
; CHECK: Combining: [[FIRST]]: f32 = fpow nnan ninf nsz arcp contract afn reassoc [[X:t[0-9]+]], ConstantFP:f32<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK: Combining: [[SECOND]]: f32 = fpow nnan ninf nsz arcp contract afn reassoc [[X:t[0-9]+]], ConstantFP:f32<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK: Combining: [[THIRD]]: f32 = fpow nnan ninf nsz arcp contract afn reassoc [[X:t[0-9]+]], ConstantFP:f32<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK: Combining: [[FORTH]]: f32 = fpow nnan ninf nsz arcp contract afn reassoc [[X:t[0-9]+]], ConstantFP:f32<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call fast <4 x float> @llvm.pow.v4f32(<4 x float> %x, <4 x float> <float 7.5e-1, float 7.5e-1, float 7.5e-01, float 7.5e-01>)
|
||||
ret <4 x float> %r
|
||||
}
|
||||
|
||||
define <2 x double> @pow_v2f64_three_fourth_fmf(<2 x double> %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: v2f64 = BUILD_VECTOR [[SECOND:t[0-9]+]], [[FIRST:t[0-9]+]]
|
||||
; CHECK: Combining: [[FIRST]]: f64 = fpow nnan ninf nsz arcp contract afn reassoc [[X:t[0-9]+]], ConstantFP:f64<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f64 = fsqrt nnan ninf nsz arcp contract afn reassoc [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f64 = fsqrt nnan ninf nsz arcp contract afn reassoc [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f64 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f64 = fmul nnan ninf nsz arcp contract afn reassoc t16, t17
|
||||
; CHECK: Combining: [[SECOND]]: f64 = fpow nnan ninf nsz arcp contract afn reassoc [[X:t[0-9]+]], ConstantFP:f64<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f64 = fsqrt nnan ninf nsz arcp contract afn reassoc [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f64 = fsqrt nnan ninf nsz arcp contract afn reassoc [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f64 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f64 = fmul nnan ninf nsz arcp contract afn reassoc t19, t20
|
||||
%r = call fast <2 x double> @llvm.pow.v2f64(<2 x double> %x, <2 x double> <double 7.5e-1, double 7.5e-1>)
|
||||
ret <2 x double> %r
|
||||
}
|
||||
48
test/CodeGen/PowerPC/pow.75.ll
Normal file
48
test/CodeGen/PowerPC/pow.75.ll
Normal file
@ -0,0 +1,48 @@
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=powerpc64le-unknown-unknown -debug 2>&1 | FileCheck %s
|
||||
; REQUIRES: asserts
|
||||
|
||||
declare float @llvm.pow.f32(float, float)
|
||||
declare <4 x float> @llvm.pow.v4f32(<4 x float>, <4 x float>)
|
||||
declare double @llvm.pow.f64(double, double)
|
||||
declare <2 x double> @llvm.pow.v2f64(<2 x double>, <2 x double>)
|
||||
|
||||
define float @pow_f32_three_fourth_fmf(float %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: f32 = fpow ninf nsz afn [[X:t[0-9]+]], ConstantFP:f32<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f32 = fsqrt ninf nsz afn [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f32 = fsqrt ninf nsz afn [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f32 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f32 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call nsz ninf afn float @llvm.pow.f32(float %x, float 7.5e-01)
|
||||
ret float %r
|
||||
}
|
||||
|
||||
define double @pow_f64_three_fourth_fmf(double %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: f64 = fpow ninf nsz afn [[X:t[0-9]+]], ConstantFP:f64<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f64 = fsqrt ninf nsz afn [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f64 = fsqrt ninf nsz afn [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f64 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f64 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call nsz ninf afn double @llvm.pow.f64(double %x, double 7.5e-01)
|
||||
ret double %r
|
||||
}
|
||||
|
||||
define <4 x float> @pow_v4f32_three_fourth_fmf(<4 x float> %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: v4f32 = fpow nnan ninf nsz arcp contract afn reassoc [[X:t[0-9]+]], {{.*}}
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: v4f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: v4f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: v4f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: v4f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call fast <4 x float> @llvm.pow.v4f32(<4 x float> %x, <4 x float> <float 7.5e-1, float 7.5e-1, float 7.5e-01, float 7.5e-01>)
|
||||
ret <4 x float> %r
|
||||
}
|
||||
|
||||
define <2 x double> @pow_v2f64_three_fourth_fmf(<2 x double> %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: v2f64 = fpow nnan ninf nsz arcp contract afn reassoc [[X:t[0-9]+]], {{.*}}
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: v2f64 = fsqrt nnan ninf nsz arcp contract afn reassoc [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: v2f64 = fsqrt nnan ninf nsz arcp contract afn reassoc [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: v2f64 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: v2f64 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call fast <2 x double> @llvm.pow.v2f64(<2 x double> %x, <2 x double> <double 7.5e-1, double 7.5e-1>)
|
||||
ret <2 x double> %r
|
||||
}
|
||||
48
test/CodeGen/X86/pow.75.ll
Normal file
48
test/CodeGen/X86/pow.75.ll
Normal file
@ -0,0 +1,48 @@
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=x86_64-- -debug 2>&1 | FileCheck %s
|
||||
; REQUIRES: asserts
|
||||
|
||||
declare float @llvm.pow.f32(float, float)
|
||||
declare <4 x float> @llvm.pow.v4f32(<4 x float>, <4 x float>)
|
||||
declare double @llvm.pow.f64(double, double)
|
||||
declare <2 x double> @llvm.pow.v2f64(<2 x double>, <2 x double>)
|
||||
|
||||
define float @pow_f32_three_fourth_fmf(float %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: f32 = fpow ninf nsz afn [[X:t[0-9]+]], ConstantFP:f32<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f32 = fsqrt ninf nsz afn [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f32 = fsqrt ninf nsz afn [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f32 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f32 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call nsz ninf afn float @llvm.pow.f32(float %x, float 7.5e-01)
|
||||
ret float %r
|
||||
}
|
||||
|
||||
define double @pow_f64_three_fourth_fmf(double %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: f64 = fpow ninf nsz afn [[X:t[0-9]+]], ConstantFP:f64<7.500000e-01>
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: f64 = fsqrt ninf nsz afn [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: f64 = fsqrt ninf nsz afn [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: f64 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: f64 = fmul ninf nsz afn [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call nsz ninf afn double @llvm.pow.f64(double %x, double 7.5e-01)
|
||||
ret double %r
|
||||
}
|
||||
|
||||
define <4 x float> @pow_v4f32_three_fourth_fmf(<4 x float> %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: v4f32 = fpow nnan ninf nsz arcp contract afn reassoc [[X:t[0-9]+]], {{.*}}
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: v4f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: v4f32 = fsqrt nnan ninf nsz arcp contract afn reassoc [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: v4f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: v4f32 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call fast <4 x float> @llvm.pow.v4f32(<4 x float> %x, <4 x float> <float 7.5e-1, float 7.5e-1, float 7.5e-01, float 7.5e-01>)
|
||||
ret <4 x float> %r
|
||||
}
|
||||
|
||||
define <2 x double> @pow_v2f64_three_fourth_fmf(<2 x double> %x) nounwind {
|
||||
; CHECK: Combining: {{.*}}: v2f64 = fpow nnan ninf nsz arcp contract afn reassoc [[X:t[0-9]+]], {{.*}}
|
||||
; CHECK-NEXT: Creating new node: [[SQRT:t[0-9]+]]: v2f64 = fsqrt nnan ninf nsz arcp contract afn reassoc [[X]]
|
||||
; CHECK-NEXT: Creating new node: [[SQRTSQRT:t[0-9]+]]: v2f64 = fsqrt nnan ninf nsz arcp contract afn reassoc [[SQRT]]
|
||||
; CHECK-NEXT: Creating new node: [[R:t[0-9]+]]: v2f64 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
; CHECK-NEXT: ... into: [[R]]: v2f64 = fmul nnan ninf nsz arcp contract afn reassoc [[SQRT]], [[SQRTSQRT]]
|
||||
%r = call fast <2 x double> @llvm.pow.v2f64(<2 x double> %x, <2 x double> <double 7.5e-1, double 7.5e-1>)
|
||||
ret <2 x double> %r
|
||||
}
|
||||
Loading…
x
Reference in New Issue
Block a user