[OpenCL] Add 'denorms-are-zero' function attribute

Summary:
Generate attribute 'denorms-are-zero'='true' if '-cl-denorms-are-zero'
compile option was specified and 'denorms-are-zero'='false' otherwise.

Patch by krisb

Reviewers: Anastasia, yaxunl

Reviewed By:  yaxunl

Subscribers: cfe-commits

Differential Revision: https://reviews.llvm.org/D45808

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@330404 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/CGCall.cpp b/lib/CodeGen/CGCall.cpp
index 27aa69dfc0afe1072abe6350d40eb4960533bbba..392c7b1ded5f0b56327338951bdd62ca7e7f704e 100644 (file)
--- a/lib/CodeGen/CGCall.cpp
+++ b/lib/CodeGen/CGCall.cpp
@@ -1745,6 +1745,10 @@ void CodeGenModule::ConstructDefaultFnAttrList(StringRef Name, bool HasOptnone,
         "correctly-rounded-divide-sqrt-fp-math",
         llvm::toStringRef(CodeGenOpts.CorrectlyRoundedDivSqrt));
 
+    if (getLangOpts().OpenCL)
+      FuncAttrs.addAttribute("denorms-are-zero",
+                             llvm::toStringRef(CodeGenOpts.FlushDenorm));
+
     // TODO: Reciprocal estimate codegen options should apply to instructions?
     const std::vector<std::string> &Recips = CodeGenOpts.Reciprocals;
     if (!Recips.empty())

diff --git a/test/CodeGenOpenCL/denorms-are-zero.cl b/test/CodeGenOpenCL/denorms-are-zero.cl
index ca7969ad5f4031b7b70675a32f01e81ed0f73e46..27ec336990cff057c0238a04bad85f70c85b2fb9 100644 (file)
--- a/test/CodeGenOpenCL/denorms-are-zero.cl
+++ b/test/CodeGenOpenCL/denorms-are-zero.cl
@@ -1,19 +1,25 @@
-// RUN: %clang_cc1 -S -cl-denorms-are-zero -o - %s 2>&1
-// RUN: %clang_cc1 -emit-llvm -cl-denorms-are-zero -o - -triple amdgcn--amdhsa -target-cpu fiji %s | FileCheck %s
-// RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn--amdhsa -target-cpu fiji %s | FileCheck %s --check-prefix=CHECK-DENORM
-// RUN: %clang_cc1 -emit-llvm -target-feature +fp32-denormals -target-feature -fp64-fp16-denormals -cl-denorms-are-zero -o - -triple amdgcn--amdhsa -target-cpu fiji %s | FileCheck --check-prefix=CHECK-FEATURE %s
+// RUN: %clang_cc1 -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -emit-llvm -cl-denorms-are-zero -o - %s | FileCheck %s --check-prefix=DENORM-ZERO
+// RUN: %clang_cc1 -emit-llvm -cl-denorms-are-zero -o - -triple amdgcn--amdhsa -target-cpu fiji %s | FileCheck %s --check-prefix=AMDGCN
+// RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn--amdhsa -target-cpu fiji %s | FileCheck %s --check-prefix=AMDGCN-DENORM
+// RUN: %clang_cc1 -emit-llvm -target-feature +fp32-denormals -target-feature -fp64-fp16-denormals -cl-denorms-are-zero -o - -triple amdgcn--amdhsa -target-cpu fiji %s | FileCheck --check-prefix=AMDGCN-FEATURE %s
 
-// For non-amdgcn targets, this test just checks that the -cl-denorms-are-zero argument is accepted
-// by clang.  This option is currently a no-op, which is allowed by the
-// OpenCL specification.
+// For all targets 'denorms-are-zero' attribute is set to 'true'
+// if '-cl-denorms-are-zero' was specified and  to 'false' otherwise.
+
+// CHECK-LABEL: define void @f()
+// CHECK: attributes #{{[0-9]*}} = {{{[^}]*}} "denorms-are-zero"="false"
+//
+// DENORM-ZERO-LABEL: define void @f()
+// DENORM-ZERO: attributes #{{[0-9]*}} = {{{[^}]*}} "denorms-are-zero"="true"
 
 // For amdgcn target cpu fiji, fp32 should be flushed since fiji does not support fp32 denormals, unless +fp32-denormals is
 // explicitly set. amdgcn target always do not flush fp64 denormals. The control for fp64 and fp16 denormals is the same.
 
-// CHECK-DENORM-LABEL: define void @f()
-// CHECK-DENORM: attributes #{{[0-9]*}} = {{{[^}]*}} "target-features"="{{[^"]*}}+fp64-fp16-denormals,{{[^"]*}}-fp32-denormals{{[^"]*}}"
-// CHECK-LABEL: define void @f()
-// CHECK: attributes #{{[0-9]*}} = {{{[^}]*}} "target-features"="{{[^"]*}}+fp64-fp16-denormals,{{[^"]*}}-fp32-denormals{{[^"]*}}"
-// CHECK-FEATURE-LABEL: define void @f()
-// CHECK-FEATURE: attributes #{{[0-9]*}} = {{{[^}]*}} "target-features"="{{[^"]*}}+fp32-denormals,{{[^"]*}}-fp64-fp16-denormals{{[^"]*}}"
+// AMDGCN-LABEL: define void @f()
+// AMDGCN: attributes #{{[0-9]*}} = {{{[^}]*}} "denorms-are-zero"="true" {{.*}} "target-features"="{{[^"]*}}+fp64-fp16-denormals,{{[^"]*}}-fp32-denormals{{[^"]*}}"
+// AMDGCN-DENORM-LABEL: define void @f()
+// AMDGCN-DENORM: attributes #{{[0-9]*}} = {{{[^}]*}} "denorms-are-zero"="false" {{.*}} "target-features"="{{[^"]*}}+fp64-fp16-denormals,{{[^"]*}}-fp32-denormals{{[^"]*}}"
+// AMDGCN-FEATURE-LABEL: define void @f()
+// AMDGCN-FEATURE: attributes #{{[0-9]*}} = {{{[^}]*}} "denorms-are-zero"="true" {{.*}} "target-features"="{{[^"]*}}+fp32-denormals,{{[^"]*}}-fp64-fp16-denormals{{[^"]*}}"
 void f() {}