[llvm] r314568 - [AMDGPU] Set fast-math flags on functions given the options
Stanislav Mekhanoshin via llvm-commits
llvm-commits at lists.llvm.org
Fri Sep 29 16:40:20 PDT 2017
Author: rampitec
Date: Fri Sep 29 16:40:19 2017
New Revision: 314568
URL: http://llvm.org/viewvc/llvm-project?rev=314568&view=rev
Log:
[AMDGPU] Set fast-math flags on functions given the options
We have a single library build without relaxation options.
When inlined library functions remove fast math attributes
from the functions they are integrated into.
This patch sets relaxation attributes on the functions after
linking provided corresponding relaxation options are given.
Math instructions inside the inlined functions remain to have
no fast flags, but inlining does not prevent fast math
transformations of a surrounding caller code anymore.
Differential Revision: https://reviews.llvm.org/D38325
Added:
llvm/trunk/test/CodeGen/AMDGPU/inline-attr.ll
Modified:
llvm/trunk/lib/Target/AMDGPU/AMDGPU.h
llvm/trunk/lib/Target/AMDGPU/AMDGPULibCalls.cpp
llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
Modified: llvm/trunk/lib/Target/AMDGPU/AMDGPU.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/AMDGPU.h?rev=314568&r1=314567&r2=314568&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPU.h (original)
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPU.h Fri Sep 29 16:40:19 2017
@@ -23,6 +23,7 @@ class ModulePass;
class Pass;
class Target;
class TargetMachine;
+class TargetOptions;
class PassRegistry;
class Module;
@@ -52,7 +53,7 @@ FunctionPass *createSIDebuggerInsertNops
FunctionPass *createSIInsertWaitsPass();
FunctionPass *createSIInsertWaitcntsPass();
FunctionPass *createSIFixWWMLivenessPass();
-FunctionPass *createAMDGPUSimplifyLibCallsPass();
+FunctionPass *createAMDGPUSimplifyLibCallsPass(const TargetOptions &);
FunctionPass *createAMDGPUUseNativeCallsPass();
FunctionPass *createAMDGPUCodeGenPreparePass();
FunctionPass *createAMDGPUMachineCFGStructurizerPass();
Modified: llvm/trunk/lib/Target/AMDGPU/AMDGPULibCalls.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/AMDGPULibCalls.cpp?rev=314568&r1=314567&r2=314568&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPULibCalls.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPULibCalls.cpp Fri Sep 29 16:40:19 2017
@@ -30,6 +30,7 @@
#include "llvm/IR/ValueSymbolTable.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
+#include "llvm/Target/TargetOptions.h"
#include <vector>
#include <cmath>
@@ -168,10 +169,13 @@ namespace {
AMDGPULibCalls Simplifier;
+ const TargetOptions Options;
+
public:
static char ID; // Pass identification
- AMDGPUSimplifyLibCalls() : FunctionPass(ID) {
+ AMDGPUSimplifyLibCalls(const TargetOptions &Opt = TargetOptions())
+ : FunctionPass(ID), Options(Opt) {
initializeAMDGPUSimplifyLibCallsPass(*PassRegistry::getPassRegistry());
}
@@ -1680,14 +1684,34 @@ bool AMDGPULibCalls::evaluateCall(CallIn
}
// Public interface to the Simplify LibCalls pass.
-FunctionPass *llvm::createAMDGPUSimplifyLibCallsPass() {
- return new AMDGPUSimplifyLibCalls();
+FunctionPass *llvm::createAMDGPUSimplifyLibCallsPass(const TargetOptions &Opt) {
+ return new AMDGPUSimplifyLibCalls(Opt);
}
FunctionPass *llvm::createAMDGPUUseNativeCallsPass() {
return new AMDGPUUseNativeCalls();
}
+static bool setFastFlags(Function &F, const TargetOptions &Options) {
+ AttrBuilder B;
+
+ if (Options.UnsafeFPMath || Options.NoInfsFPMath)
+ B.addAttribute("no-infs-fp-math", "true");
+ if (Options.UnsafeFPMath || Options.NoNaNsFPMath)
+ B.addAttribute("no-nans-fp-math", "true");
+ if (Options.UnsafeFPMath) {
+ B.addAttribute("less-precise-fpmad", "true");
+ B.addAttribute("unsafe-fp-math", "true");
+ }
+
+ if (!B.hasAttributes())
+ return false;
+
+ F.addAttributes(AttributeList::FunctionIndex, B);
+
+ return true;
+}
+
bool AMDGPUSimplifyLibCalls::runOnFunction(Function &F) {
if (skipFunction(F))
return false;
@@ -1699,6 +1723,9 @@ bool AMDGPUSimplifyLibCalls::runOnFuncti
F.printAsOperand(dbgs(), false, F.getParent());
dbgs() << '\n';);
+ if (!EnablePreLink)
+ Changed |= setFastFlags(F, Options);
+
for (auto &BB : F) {
for (BasicBlock::iterator I = BB.begin(), E = BB.end(); I != E; ) {
// Ignore non-calls.
Modified: llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp?rev=314568&r1=314567&r2=314568&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp Fri Sep 29 16:40:19 2017
@@ -370,17 +370,18 @@ void AMDGPUTargetMachine::adjustPassMana
PM.add(createAMDGPUAlwaysInlinePass(false));
});
+ const auto &Opt = Options;
Builder.addExtension(
PassManagerBuilder::EP_EarlyAsPossible,
- [AMDGPUAA, LibCallSimplify](const PassManagerBuilder &,
- legacy::PassManagerBase &PM) {
+ [AMDGPUAA, LibCallSimplify, &Opt](const PassManagerBuilder &,
+ legacy::PassManagerBase &PM) {
if (AMDGPUAA) {
PM.add(createAMDGPUAAWrapperPass());
PM.add(createAMDGPUExternalAAWrapperPass());
}
PM.add(llvm::createAMDGPUUseNativeCallsPass());
if (LibCallSimplify)
- PM.add(llvm::createAMDGPUSimplifyLibCallsPass());
+ PM.add(llvm::createAMDGPUSimplifyLibCallsPass(Opt));
});
Builder.addExtension(
Added: llvm/trunk/test/CodeGen/AMDGPU/inline-attr.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/inline-attr.ll?rev=314568&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/inline-attr.ll (added)
+++ llvm/trunk/test/CodeGen/AMDGPU/inline-attr.ll Fri Sep 29 16:40:19 2017
@@ -0,0 +1,33 @@
+; RUN: opt -mtriple=amdgcn--amdhsa -S -O3 -enable-unsafe-fp-math %s | FileCheck -check-prefix=GCN -check-prefix=UNSAFE %s
+; RUN: opt -mtriple=amdgcn--amdhsa -S -O3 -enable-no-nans-fp-math %s | FileCheck -check-prefix=GCN -check-prefix=NONANS %s
+; RUN: opt -mtriple=amdgcn--amdhsa -S -O3 -enable-no-infs-fp-math %s | FileCheck -check-prefix=GCN -check-prefix=NOINFS %s
+
+; GCN: define float @foo(float %x) local_unnamed_addr #0 {
+; GCN: define amdgpu_kernel void @caller(float addrspace(1)* nocapture %p) local_unnamed_addr #1 {
+; GCN: %mul.i = fmul float %load, 1.500000e+01
+
+; UNSAFE: attributes #0 = { norecurse nounwind readnone "less-precise-fpmad"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" }
+; UNSAFE: attributes #1 = { norecurse nounwind "less-precise-fpmad"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" }
+
+; NOINFS: attributes #0 = { norecurse nounwind readnone "no-infs-fp-math"="true" }
+; NOINFS: attributes #1 = { norecurse nounwind "less-precise-fpmad"="false" "no-infs-fp-math"="true" "no-nans-fp-math"="false" "unsafe-fp-math"="false" }
+
+; NONANS: attributes #0 = { norecurse nounwind readnone "no-nans-fp-math"="true" }
+; NONANS: attributes #1 = { norecurse nounwind "less-precise-fpmad"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="true" "unsafe-fp-math"="false" }
+
+define float @foo(float %x) #0 {
+entry:
+ %mul = fmul float %x, 1.500000e+01
+ ret float %mul
+}
+
+define amdgpu_kernel void @caller(float addrspace(1)* %p) #1 {
+entry:
+ %load = load float, float addrspace(1)* %p, align 4
+ %call = call fast float @foo(float %load) #0
+ store float %call, float addrspace(1)* %p, align 4
+ ret void
+}
+
+attributes #0 = { nounwind }
+attributes #1 = { nounwind "less-precise-fpmad"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" }
More information about the llvm-commits
mailing list