[llvm] r293024 - DAG: Recognize no-signed-zeros-fp-math attribute
Matt Arsenault via llvm-commits
llvm-commits at lists.llvm.org
Tue Jan 24 22:08:43 PST 2017
Author: arsenm
Date: Wed Jan 25 00:08:42 2017
New Revision: 293024
URL: http://llvm.org/viewvc/llvm-project?rev=293024&view=rev
Log:
DAG: Recognize no-signed-zeros-fp-math attribute
clang already emits this with -cl-no-signed-zeros, but codegen
doesn't do anything with it. Treat it like the other fast math
attributes, and change one place to use it.
Added:
llvm/trunk/test/CodeGen/AMDGPU/enable-no-signed-zeros-fp-math.ll
Modified:
llvm/trunk/include/llvm/CodeGen/CommandFlags.h
llvm/trunk/include/llvm/Target/TargetOptions.h
llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
llvm/trunk/lib/Target/TargetMachine.cpp
llvm/trunk/test/CodeGen/AMDGPU/fsub.ll
llvm/trunk/test/CodeGen/X86/negative-sin.ll
Modified: llvm/trunk/include/llvm/CodeGen/CommandFlags.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/CodeGen/CommandFlags.h?rev=293024&r1=293023&r2=293024&view=diff
==============================================================================
--- llvm/trunk/include/llvm/CodeGen/CommandFlags.h (original)
+++ llvm/trunk/include/llvm/CodeGen/CommandFlags.h Wed Jan 25 00:08:42 2017
@@ -144,6 +144,12 @@ EnableNoNaNsFPMath("enable-no-nans-fp-ma
cl::init(false));
cl::opt<bool>
+EnableNoSignedZerosFPMath("enable-no-signed-zeros-fp-math",
+ cl::desc("Enable FP math optimizations that assume "
+ "the sign of 0 is insignificant"),
+ cl::init(false));
+
+cl::opt<bool>
EnableNoTrappingFPMath("enable-no-trapping-fp-math",
cl::desc("Enable setting the FP exceptions build "
"attribute not to use exceptions"),
@@ -282,6 +288,7 @@ static inline TargetOptions InitTargetOp
Options.UnsafeFPMath = EnableUnsafeFPMath;
Options.NoInfsFPMath = EnableNoInfsFPMath;
Options.NoNaNsFPMath = EnableNoNaNsFPMath;
+ Options.NoSignedZerosFPMath = EnableNoSignedZerosFPMath;
Options.NoTrappingFPMath = EnableNoTrappingFPMath;
Options.FPDenormalMode = DenormalMode;
Options.HonorSignDependentRoundingFPMathOption =
Modified: llvm/trunk/include/llvm/Target/TargetOptions.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Target/TargetOptions.h?rev=293024&r1=293023&r2=293024&view=diff
==============================================================================
--- llvm/trunk/include/llvm/Target/TargetOptions.h (original)
+++ llvm/trunk/include/llvm/Target/TargetOptions.h Wed Jan 25 00:08:42 2017
@@ -153,11 +153,17 @@ namespace llvm {
/// assume the FP arithmetic arguments and results are never NaNs.
unsigned NoNaNsFPMath : 1;
- /// NoTrappingFPMath - This flag is enabled when the
- /// -enable-no-trapping-fp-math is specified on the command line. This
+ /// NoTrappingFPMath - This flag is enabled when the
+ /// -enable-no-trapping-fp-math is specified on the command line. This
/// specifies that there are no trap handlers to handle exceptions.
unsigned NoTrappingFPMath : 1;
+ /// NoSignedZerosFPMath - This flag is enabled when the
+ /// -enable-no-signed-zeros-fp-math is specified on the command line. This
+ /// specifies that optimizations are allowed to treat the sign of a zero
+ /// argument or result as insignificant.
+ unsigned NoSignedZerosFPMath : 1;
+
/// HonorSignDependentRoundingFPMath - This returns true when the
/// -enable-sign-dependent-rounding-fp-math is specified. If this returns
/// false (the default), the code generator is allowed to assume that the
Modified: llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp?rev=293024&r1=293023&r2=293024&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp (original)
+++ llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp Wed Jan 25 00:08:42 2017
@@ -635,7 +635,8 @@ static char isNegatibleForFree(SDValue O
Depth + 1);
case ISD::FSUB:
// We can't turn -(A-B) into B-A when we honor signed zeros.
- if (!Options->UnsafeFPMath && !Op.getNode()->getFlags()->hasNoSignedZeros())
+ if (!Options->NoSignedZerosFPMath &&
+ !Op.getNode()->getFlags()->hasNoSignedZeros())
return 0;
// fold (fneg (fsub A, B)) -> (fsub B, A)
Modified: llvm/trunk/lib/Target/TargetMachine.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/TargetMachine.cpp?rev=293024&r1=293023&r2=293024&view=diff
==============================================================================
--- llvm/trunk/lib/Target/TargetMachine.cpp (original)
+++ llvm/trunk/lib/Target/TargetMachine.cpp Wed Jan 25 00:08:42 2017
@@ -84,6 +84,7 @@ void TargetMachine::resetTargetOptions(c
RESET_OPTION(UnsafeFPMath, "unsafe-fp-math");
RESET_OPTION(NoInfsFPMath, "no-infs-fp-math");
RESET_OPTION(NoNaNsFPMath, "no-nans-fp-math");
+ RESET_OPTION(NoSignedZerosFPMath, "no-signed-zeros-fp-math");
RESET_OPTION(NoTrappingFPMath, "no-trapping-math");
StringRef Denormal =
Added: llvm/trunk/test/CodeGen/AMDGPU/enable-no-signed-zeros-fp-math.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/enable-no-signed-zeros-fp-math.ll?rev=293024&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/enable-no-signed-zeros-fp-math.ll (added)
+++ llvm/trunk/test/CodeGen/AMDGPU/enable-no-signed-zeros-fp-math.ll Wed Jan 25 00:08:42 2017
@@ -0,0 +1,22 @@
+; RUN: llc -march=amdgcn -enable-no-signed-zeros-fp-math=0 < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-SAFE %s
+; RUN: llc -march=amdgcn -enable-no-signed-zeros-fp-math=1 < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-UNSAFE %s
+; RUN: llc -march=amdgcn -enable-unsafe-fp-math < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-UNSAFE %s
+
+; Test that the -enable-no-signed-zeros-fp-math flag works
+
+; GCN-LABEL: {{^}}fneg_fsub_f32:
+; GCN: v_subrev_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
+; GCN-SAFE: v_xor_b32_e32 v{{[0-9]+}}, 0x80000000, [[SUB]]
+
+; GCN-UNSAFE-NOT: xor
+define void @fneg_fsub_f32(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
+ %b_ptr = getelementptr float, float addrspace(1)* %in, i32 1
+ %a = load float, float addrspace(1)* %in, align 4
+ %b = load float, float addrspace(1)* %b_ptr, align 4
+ %result = fsub float %a, %b
+ %neg.result = fsub float -0.0, %result
+ store float %neg.result, float addrspace(1)* %out, align 4
+ ret void
+}
+
+attributes #0 = { nounwind }
Modified: llvm/trunk/test/CodeGen/AMDGPU/fsub.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/fsub.ll?rev=293024&r1=293023&r2=293024&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/fsub.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/fsub.ll Wed Jan 25 00:08:42 2017
@@ -69,3 +69,61 @@ define void @s_fsub_v4f32(<4 x float> ad
store <4 x float> %result, <4 x float> addrspace(1)* %out, align 16
ret void
}
+
+; FUNC-LABEL: {{^}}v_fneg_fsub_f32:
+; SI: v_subrev_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
+; SI: v_xor_b32_e32 v{{[0-9]+}}, 0x80000000, [[SUB]]
+define void @v_fneg_fsub_f32(float addrspace(1)* %out, float addrspace(1)* %in) {
+ %b_ptr = getelementptr float, float addrspace(1)* %in, i32 1
+ %a = load float, float addrspace(1)* %in, align 4
+ %b = load float, float addrspace(1)* %b_ptr, align 4
+ %result = fsub float %a, %b
+ %neg.result = fsub float -0.0, %result
+ store float %neg.result, float addrspace(1)* %out, align 4
+ ret void
+}
+
+; FUNC-LABEL: {{^}}v_fneg_fsub_nsz_f32:
+; SI: v_subrev_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
+; SI-NOT: xor
+define void @v_fneg_fsub_nsz_f32(float addrspace(1)* %out, float addrspace(1)* %in) {
+ %b_ptr = getelementptr float, float addrspace(1)* %in, i32 1
+ %a = load float, float addrspace(1)* %in, align 4
+ %b = load float, float addrspace(1)* %b_ptr, align 4
+ %result = fsub nsz float %a, %b
+ %neg.result = fsub float -0.0, %result
+ store float %neg.result, float addrspace(1)* %out, align 4
+ ret void
+}
+
+; FUNC-LABEL: {{^}}v_fneg_fsub_nsz_attribute_f32:
+; SI: v_subrev_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
+; SI-NOT: xor
+define void @v_fneg_fsub_nsz_attribute_f32(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
+ %b_ptr = getelementptr float, float addrspace(1)* %in, i32 1
+ %a = load float, float addrspace(1)* %in, align 4
+ %b = load float, float addrspace(1)* %b_ptr, align 4
+ %result = fsub float %a, %b
+ %neg.result = fsub float -0.0, %result
+ store float %neg.result, float addrspace(1)* %out, align 4
+ ret void
+}
+
+; For some reason the attribute has a string "true" or "false", so
+; make sure it is disabled and the fneg is not folded if it is not
+; "true".
+; FUNC-LABEL: {{^}}v_fneg_fsub_nsz_false_attribute_f32:
+; SI: v_subrev_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
+; SI: v_xor_b32_e32 v{{[0-9]+}}, 0x80000000, [[SUB]]
+define void @v_fneg_fsub_nsz_false_attribute_f32(float addrspace(1)* %out, float addrspace(1)* %in) #1 {
+ %b_ptr = getelementptr float, float addrspace(1)* %in, i32 1
+ %a = load float, float addrspace(1)* %in, align 4
+ %b = load float, float addrspace(1)* %b_ptr, align 4
+ %result = fsub float %a, %b
+ %neg.result = fsub float -0.0, %result
+ store float %neg.result, float addrspace(1)* %out, align 4
+ ret void
+}
+
+attributes #0 = { nounwind "no-signed-zeros-fp-math"="true" }
+attributes #1 = { nounwind "no-signed-zeros-fp-math"="false" }
Modified: llvm/trunk/test/CodeGen/X86/negative-sin.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/negative-sin.ll?rev=293024&r1=293023&r2=293024&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/negative-sin.ll (original)
+++ llvm/trunk/test/CodeGen/X86/negative-sin.ll Wed Jan 25 00:08:42 2017
@@ -101,5 +101,5 @@ define double @fn_attr(double %e) nounwi
ret double %h
}
-attributes #0 = { "unsafe-fp-math"="true" }
+attributes #0 = { "unsafe-fp-math"="true" "no-signed-zeros-fp-math"="true" }
More information about the llvm-commits
mailing list