[llvm-branch-commits] [llvm-branch] r339103 - Merging r338569:

[Hans Wennborg via llvm-branch-commits]

Author: hans
Date: Tue Aug  7 00:01:41 2018
New Revision: 339103

URL: http://llvm.org/viewvc/llvm-project?rev=339103&view=rev
Log:
Merging r338569:
------------------------------------------------------------------------
r338569 | jvesely | 2018-08-01 17:04:36 +0200 (Wed, 01 Aug 2018) | 5 lines

AMDGPU: Allow fp32-denormals feature for r600 targets

This was accidentally removed in r335942.

Differential Revision: https://reviews.llvm.org/D49934
------------------------------------------------------------------------

Modified:
    llvm/branches/release_70/   (props changed)
    llvm/branches/release_70/lib/Target/AMDGPU/AMDGPU.td
    llvm/branches/release_70/lib/Target/AMDGPU/AMDGPUFeatures.td

Propchange: llvm/branches/release_70/
------------------------------------------------------------------------------
--- svn:mergeinfo (original)
+++ svn:mergeinfo Tue Aug  7 00:01:41 2018
@@ -1,3 +1,3 @@
 /llvm/branches/Apple/Pertwee:110850,110961
 /llvm/branches/type-system-rewrite:133420-134817
-/llvm/trunk:155241,338552,338554,338599,338658,338665,338682,338703,338709,338751,338762,338817,338968
+/llvm/trunk:155241,338552,338554,338569,338599,338658,338665,338682,338703,338709,338751,338762,338817,338968

Modified: llvm/branches/release_70/lib/Target/AMDGPU/AMDGPU.td
URL: http://llvm.org/viewvc/llvm-project/llvm/branches/release_70/lib/Target/AMDGPU/AMDGPU.td?rev=339103&r1=339102&r2=339103&view=diff
==============================================================================
--- llvm/branches/release_70/lib/Target/AMDGPU/AMDGPU.td (original)
+++ llvm/branches/release_70/lib/Target/AMDGPU/AMDGPU.td Tue Aug  7 00:01:41 2018
@@ -267,15 +267,6 @@ def FeatureD16PreservesUnusedBits : Subt
 // Subtarget Features (options and debugging)
 //===------------------------------------------------------------===//
 
-// Some instructions do not support denormals despite this flag. Using
-// fp32 denormals also causes instructions to run at the double
-// precision rate for the device.
-def FeatureFP32Denormals : SubtargetFeature<"fp32-denormals",
-  "FP32Denormals",
-  "true",
-  "Enable single precision denormal handling"
->;
-
 // Denormal handling for fp64 and fp16 is controlled by the same
 // config register when fp16 supported.
 // TODO: Do we need a separate f16 setting when not legal?

Modified: llvm/branches/release_70/lib/Target/AMDGPU/AMDGPUFeatures.td
URL: http://llvm.org/viewvc/llvm-project/llvm/branches/release_70/lib/Target/AMDGPU/AMDGPUFeatures.td?rev=339103&r1=339102&r2=339103&view=diff
==============================================================================
--- llvm/branches/release_70/lib/Target/AMDGPU/AMDGPUFeatures.td (original)
+++ llvm/branches/release_70/lib/Target/AMDGPU/AMDGPUFeatures.td Tue Aug  7 00:01:41 2018
@@ -19,6 +19,15 @@ def FeatureFMA : SubtargetFeature<"fmaf"
   "Enable single precision FMA (not as fast as mul+add, but fused)"
 >;
 
+// Some instructions do not support denormals despite this flag. Using
+// fp32 denormals also causes instructions to run at the double
+// precision rate for the device.
+def FeatureFP32Denormals : SubtargetFeature<"fp32-denormals",
+  "FP32Denormals",
+  "true",
+  "Enable single precision denormal handling"
+>;
+
 class SubtargetFeatureLocalMemorySize <int Value> : SubtargetFeature<
   "localmemorysize"#Value,
   "LocalMemorySize",