[PATCH] D31482: [AMDGPU][GFX9] Set +fp32-denormals for >=gfx900 unless -cl-denorms-are-zero is set

[Konstantin Zhuravlyov via Phabricator via cfe-commits]

kzhuravl updated this revision to Diff 93422.
kzhuravl marked an inline comment as done.
kzhuravl added a comment.

Address review feedback.


https://reviews.llvm.org/D31482

Files:
  lib/Basic/Targets.cpp
  test/CodeGenOpenCL/gfx9-fp32-denorms.cl


Index: test/CodeGenOpenCL/gfx9-fp32-denorms.cl
===================================================================
--- test/CodeGenOpenCL/gfx9-fp32-denorms.cl
+++ test/CodeGenOpenCL/gfx9-fp32-denorms.cl
@@ -0,0 +1,13 @@
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx900 -S -emit-llvm -o - %s | FileCheck --check-prefix=DEFAULT %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx900 -S -emit-llvm -o - -target-feature +fp32-denormals %s | FileCheck --check-prefix=FEATURE_FP32_DENORMALS_ON %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx900 -S -emit-llvm -o - -target-feature -fp32-denormals %s | FileCheck --check-prefix=FEATURE_FP32_DENORMALS_OFF %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx900 -S -emit-llvm -o - -cl-denorms-are-zero %s | FileCheck --check-prefix=OPT_DENORMS_ARE_ZERO %s
+
+// DEFAULT: +fp32-denormals
+// FEATURE_FP32_DENORMALS_ON: +fp32-denormals
+// FEATURE_FP32_DENORMALS_OFF: -fp32-denormals
+// OPT_DENORMS_ARE_ZERO: -fp32-denormals
+
+kernel void gfx9_fp32_denorms() {}
Index: lib/Basic/Targets.cpp
===================================================================
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2109,9 +2109,12 @@
   bool hasFP64:1;
   bool hasFMAF:1;
   bool hasLDEXPF:1;
-  bool hasFullSpeedFP32Denorms:1;
   const AddrSpace AS;
 
+  static bool hasFullSpeedFMA(StringRef GPUName) {
+    return parseAMDGCNName(GPUName) >= GK_GFX9;
+  }
+
   static bool isAMDGCN(const llvm::Triple &TT) {
     return TT.getArch() == llvm::Triple::amdgcn;
   }
@@ -2127,7 +2130,6 @@
       hasFP64(false),
       hasFMAF(false),
       hasLDEXPF(false),
-      hasFullSpeedFP32Denorms(false),
       AS(isGenericZero(Triple)){
     if (getTriple().getArch() == llvm::Triple::amdgcn) {
       hasFP64 = true;
@@ -2196,7 +2198,8 @@
         hasFP64Denormals = true;
     }
     if (!hasFP32Denormals)
-      TargetOpts.Features.push_back((Twine(hasFullSpeedFP32Denorms &&
+      TargetOpts.Features.push_back(
+          (Twine(hasFullSpeedFMA(TargetOpts.CPU) &&
           !CGOpts.FlushDenorm ? '+' : '-') + Twine("fp32-denormals")).str());
     // Always do not flush fp64 or fp16 denorms.
     if (!hasFP64Denormals && hasFP64)


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D31482.93422.patch
Type: text/x-patch
Size: 2294 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20170329/fcd2c78f/attachment.bin>