[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

llvm-svn: 314568

4 files changed, 69 insertions, 7 deletions

diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.h b/llvm/lib/Target/AMDGPU/AMDGPU.h
index 893e4cb2a15..6bf8cdcb849 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.h
@@ -23,6 +23,7 @@ class ModulePass;
 class Pass;
 class Target;
 class TargetMachine;
+class TargetOptions;
 class PassRegistry;
 class Module;
 
@@ -52,7 +53,7 @@ FunctionPass *createSIDebuggerInsertNopsPass();
 FunctionPass *createSIInsertWaitsPass();
 FunctionPass *createSIInsertWaitcntsPass();
 FunctionPass *createSIFixWWMLivenessPass();
-FunctionPass *createAMDGPUSimplifyLibCallsPass();
+FunctionPass *createAMDGPUSimplifyLibCallsPass(const TargetOptions &);
 FunctionPass *createAMDGPUUseNativeCallsPass();
 FunctionPass *createAMDGPUCodeGenPreparePass();
 FunctionPass *createAMDGPUMachineCFGStructurizerPass();
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp b/llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp
index d3d5c6dc9d9..e7e54750fe6 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp
@@ -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(CallInst *aCI, FuncInfo &FInfo) {
 }
 
 // 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::runOnFunction(Function &F) {
         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.
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index 25d3629cd69..8a6b5aeaebc 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -370,17 +370,18 @@ void AMDGPUTargetMachine::adjustPassManager(PassManagerBuilder &Builder) {
         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(
diff --git a/llvm/test/CodeGen/AMDGPU/inline-attr.ll b/llvm/test/CodeGen/AMDGPU/inline-attr.ll
new file mode 100644
index 00000000000..6f6b5f4c0b0
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/inline-attr.ll
@@ -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" }