forked from OSchip/llvm-project
[PowerPC] Replace subtract-from-zero float in version with fneg in PowerPC special fma compiler builtins
This is a re-revert with a corrected test. This patch adds a test for the PowerPC fma compiler builtins, some variations of which negate inputs and outputs. The code to generate IR for these builtins was untested before this patch. Originally, the code used the outdated method of subtracting floating point values from -0.0 as floating point negation. This patch remedies that. Patch by: Drew Wock <drew.wock@sas.com> Differential Revision: https://reviews.llvm.org/D76949
This commit is contained in:
Andrew Wock
Kevin P. Neal
parent
a3220dffcb
commit
15a1780a10
|
|
@ -14056,7 +14056,6 @@ Value *CodeGenFunction::EmitPPCBuiltinExpr(unsigned BuiltinID,
|
|||
Value *X = EmitScalarExpr(E->getArg(0));
|
||||
Value *Y = EmitScalarExpr(E->getArg(1));
|
||||
Value *Z = EmitScalarExpr(E->getArg(2));
|
||||
Value *Zero = llvm::ConstantFP::getZeroValueForNegation(ResultType);
|
||||
llvm::Function *F = CGM.getIntrinsic(Intrinsic::fma, ResultType);
|
||||
switch (BuiltinID) {
|
||||
case PPC::BI__builtin_vsx_xvmaddadp:
|
||||
|
|
@ -14064,17 +14063,14 @@ Value *CodeGenFunction::EmitPPCBuiltinExpr(unsigned BuiltinID,
|
|||
return Builder.CreateCall(F, {X, Y, Z});
|
||||
case PPC::BI__builtin_vsx_xvnmaddadp:
|
||||
case PPC::BI__builtin_vsx_xvnmaddasp:
|
||||
return Builder.CreateFSub(Zero,
|
||||
Builder.CreateCall(F, {X, Y, Z}), "sub");
|
||||
return Builder.CreateFNeg(Builder.CreateCall(F, {X, Y, Z}), "neg");
|
||||
case PPC::BI__builtin_vsx_xvmsubadp:
|
||||
case PPC::BI__builtin_vsx_xvmsubasp:
|
||||
return Builder.CreateCall(F,
|
||||
{X, Y, Builder.CreateFSub(Zero, Z, "sub")});
|
||||
return Builder.CreateCall(F, {X, Y, Builder.CreateFNeg(Z, "neg")});
|
||||
case PPC::BI__builtin_vsx_xvnmsubadp:
|
||||
case PPC::BI__builtin_vsx_xvnmsubasp:
|
||||
Value *FsubRes =
|
||||
Builder.CreateCall(F, {X, Y, Builder.CreateFSub(Zero, Z, "sub")});
|
||||
return Builder.CreateFSub(Zero, FsubRes, "sub");
|
||||
return Builder.CreateFNeg(
|
||||
Builder.CreateCall(F, {X, Y, Builder.CreateFNeg(Z, "neg")}), "neg");
|
||||
}
|
||||
llvm_unreachable("Unknown FMA operation");
|
||||
return nullptr; // Suppress no-return warning
|
||||
|
|
|
|||
|
|
@ -0,0 +1,43 @@
|
|||
// RUN: %clang_cc1 -triple powerpc64le-gnu-linux \
|
||||
// RUN: -target-feature +altivec -Wall -Wno-unused -Werror -emit-llvm %s -o - | FileCheck \
|
||||
// RUN: %s
|
||||
|
||||
typedef __attribute__((vector_size(4 * sizeof(float)))) float vec_float;
|
||||
typedef __attribute__((vector_size(2 * sizeof(double)))) double vec_double;
|
||||
|
||||
volatile vec_double vd;
|
||||
volatile vec_float vf;
|
||||
|
||||
void test_fma(void) {
|
||||
vf = __builtin_vsx_xvmaddasp(vf, vf, vf);
|
||||
// CHECK: @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
|
||||
|
||||
vd = __builtin_vsx_xvmaddadp(vd, vd, vd);
|
||||
// CHECK: @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
|
||||
|
||||
vf = __builtin_vsx_xvnmaddasp(vf, vf, vf);
|
||||
// CHECK: [[RESULT:%[^ ]+]] = call <4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
|
||||
// CHECK: fneg <4 x float> [[RESULT]]
|
||||
|
||||
vd = __builtin_vsx_xvnmaddadp(vd, vd, vd);
|
||||
// CHECK: [[RESULT:%[^ ]+]] = call <2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
|
||||
// CHECK: fneg <2 x double> [[RESULT]]
|
||||
|
||||
vf = __builtin_vsx_xvmsubasp(vf, vf, vf);
|
||||
// CHECK: [[RESULT:%[^ ]+]] = fneg <4 x float> %{{.*}}
|
||||
// CHECK: @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> [[RESULT]])
|
||||
|
||||
vd = __builtin_vsx_xvmsubadp(vd, vd, vd);
|
||||
// CHECK: [[RESULT:%[^ ]+]] = fneg <2 x double> %{{.*}}
|
||||
// CHECK: <2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> [[RESULT]])
|
||||
|
||||
vf = __builtin_vsx_xvnmsubasp(vf, vf, vf);
|
||||
// CHECK: [[RESULT:%[^ ]+]] = fneg <4 x float> %{{.*}}
|
||||
// CHECK: [[RESULT2:%[^ ]+]] = call <4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> [[RESULT]])
|
||||
// CHECK: fneg <4 x float> [[RESULT2]]
|
||||
|
||||
vd = __builtin_vsx_xvnmsubadp(vd, vd, vd);
|
||||
// CHECK: [[RESULT:%[^ ]+]] = fneg <2 x double> %{{.*}}
|
||||
// CHECK: [[RESULT2:%[^ ]+]] = call <2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> [[RESULT]])
|
||||
// CHECK: fneg <2 x double> [[RESULT2]]
|
||||
}
|
||||
|
|
@ -713,15 +713,15 @@ void test1() {
|
|||
|
||||
/* vec_msub */
|
||||
res_vf = vec_msub(vf, vf, vf);
|
||||
// CHECK: fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{[0-9]+}}
|
||||
// CHECK: fneg <4 x float> %{{[0-9]+}}
|
||||
// CHECK-NEXT: call <4 x float> @llvm.fma.v4f32(<4 x float> %{{[0-9]+}}, <4 x float> %{{[0-9]+}}, <4 x float>
|
||||
// CHECK-LE: fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{[0-9]+}}
|
||||
// CHECK-LE: fneg <4 x float> %{{[0-9]+}}
|
||||
// CHECK-LE-NEXT: call <4 x float> @llvm.fma.v4f32(<4 x float> %{{[0-9]+}}, <4 x float> %{{[0-9]+}}, <4 x float>
|
||||
|
||||
res_vd = vec_msub(vd, vd, vd);
|
||||
// CHECK: fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{[0-9]+}}
|
||||
// CHECK: fneg <2 x double> %{{[0-9]+}}
|
||||
// CHECK-NEXT: call <2 x double> @llvm.fma.v2f64(<2 x double> %{{[0-9]+}}, <2 x double> %{{[0-9]+}}, <2 x double>
|
||||
// CHECK-LE: fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{[0-9]+}}
|
||||
// CHECK-LE: fneg <2 x double> %{{[0-9]+}}
|
||||
// CHECK-LE-NEXT: call <2 x double> @llvm.fma.v2f64(<2 x double> %{{[0-9]+}}, <2 x double> %{{[0-9]+}}, <2 x double>
|
||||
|
||||
res_vsll = vec_mul(vsll, vsll);
|
||||
|
|
@ -750,31 +750,31 @@ void test1() {
|
|||
|
||||
res_vf = vec_nmadd(vf, vf, vf);
|
||||
// CHECK: [[FM:[0-9]+]] = call <4 x float> @llvm.fma.v4f32(<4 x float> %{{[0-9]+}}, <4 x float> %{{[0-9]+}}, <4 x float> %{{[0-9]+}})
|
||||
// CHECK-NEXT: fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %[[FM]]
|
||||
// CHECK-NEXT: fneg <4 x float> %[[FM]]
|
||||
// CHECK-LE: [[FM:[0-9]+]] = call <4 x float> @llvm.fma.v4f32(<4 x float> %{{[0-9]+}}, <4 x float> %{{[0-9]+}}, <4 x float> %{{[0-9]+}})
|
||||
// CHECK-LE-NEXT: fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %[[FM]]
|
||||
// CHECK-LE-NEXT: fneg <4 x float> %[[FM]]
|
||||
|
||||
res_vd = vec_nmadd(vd, vd, vd);
|
||||
// CHECK: [[FM:[0-9]+]] = call <2 x double> @llvm.fma.v2f64(<2 x double> %{{[0-9]+}}, <2 x double> %{{[0-9]+}}, <2 x double> %{{[0-9]+}})
|
||||
// CHECK-NEXT: fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %[[FM]]
|
||||
// CHECK-NEXT: fneg <2 x double> %[[FM]]
|
||||
// CHECK-LE: [[FM:[0-9]+]] = call <2 x double> @llvm.fma.v2f64(<2 x double> %{{[0-9]+}}, <2 x double> %{{[0-9]+}}, <2 x double> %{{[0-9]+}})
|
||||
// CHECK-LE-NEXT: fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %[[FM]]
|
||||
// CHECK-LE-NEXT: fneg <2 x double> %[[FM]]
|
||||
|
||||
res_vf = vec_nmsub(vf, vf, vf);
|
||||
// CHECK: fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{[0-9]+}}
|
||||
// CHECK: fneg <4 x float> %{{[0-9]+}}
|
||||
// CHECK-NEXT: call <4 x float> @llvm.fma.v4f32(<4 x float> %{{[0-9]+}}, <4 x float> %{{[0-9]+}}, <4 x float>
|
||||
// CHECK: fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{[0-9]+}}
|
||||
// CHECK-LE: fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{[0-9]+}}
|
||||
// CHECK: fneg <4 x float> %{{[0-9]+}}
|
||||
// CHECK-LE: fneg <4 x float> %{{[0-9]+}}
|
||||
// CHECK-LE-NEXT: call <4 x float> @llvm.fma.v4f32(<4 x float> %{{[0-9]+}}, <4 x float> %{{[0-9]+}}, <4 x float>
|
||||
// CHECK-LE: fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %{{[0-9]+}}
|
||||
// CHECK-LE: fneg <4 x float> %{{[0-9]+}}
|
||||
|
||||
res_vd = vec_nmsub(vd, vd, vd);
|
||||
// CHECK: fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{[0-9]+}}
|
||||
// CHECK: fneg <2 x double> %{{[0-9]+}}
|
||||
// CHECK-NEXT: [[FM:[0-9]+]] = call <2 x double> @llvm.fma.v2f64(<2 x double> %{{[0-9]+}}, <2 x double> %{{[0-9]+}}, <2 x double>
|
||||
// CHECK-NEXT: fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %[[FM]]
|
||||
// CHECK-LE: fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %{{[0-9]+}}
|
||||
// CHECK-NEXT: fneg <2 x double> %[[FM]]
|
||||
// CHECK-LE: fneg <2 x double> %{{[0-9]+}}
|
||||
// CHECK-LE-NEXT: [[FM:[0-9]+]] = call <2 x double> @llvm.fma.v2f64(<2 x double> %{{[0-9]+}}, <2 x double> %{{[0-9]+}}, <2 x double>
|
||||
// CHECK-LE-NEXT: fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %[[FM]]
|
||||
// CHECK-LE-NEXT: fneg <2 x double> %[[FM]]
|
||||
|
||||
/* vec_nor */
|
||||
res_vsll = vec_nor(vsll, vsll);
|
||||
|
|
|
|||
Loading…
Reference in New Issue