[PATCH] D39931: AMDGPU: Don't try to enable fp64 denormals on <SI

[Jan Vesely via Phabricator via llvm-commits]

jvesely created this revision.
Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, kzhuravl.

Passing +fp64-fp16-denormal feature enables fp64 even on asics that don't support it


Repository:
  rL LLVM

https://reviews.llvm.org/D39931

Files:
  lib/Target/AMDGPU/AMDGPUSubtarget.cpp


Index: lib/Target/AMDGPU/AMDGPUSubtarget.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUSubtarget.cpp
+++ lib/Target/AMDGPU/AMDGPUSubtarget.cpp
@@ -48,10 +48,20 @@
   // for SI has the unhelpful behavior that it unsets everything else if you
   // disable it.
 
-  SmallString<256> FullFS("+promote-alloca,+fp64-fp16-denormals,+dx10-clamp,+load-store-opt,");
+  SmallString<256> FullFS("+promote-alloca,+dx10-clamp,+load-store-opt,");
+
   if (isAmdHsaOS()) // Turn on FlatForGlobal for HSA.
     FullFS += "+flat-address-space,+flat-for-global,+unaligned-buffer-access,+trap-handler,";
 
+  // FIXME: I don't think think Evergreen has any useful support for
+  // denormals, but should be checked. Should we issue a warning somewhere
+  // if someone tries to enable these?
+  if (getGeneration() >= AMDGPUSubtarget::SOUTHERN_ISLANDS) {
+    FullFS += "+fp64-fp16-denormals,";
+  } else {
+    FullFS += "-fp64-fp16-denormals,-fp32-denormals,";
+  }
+
   FullFS += FS;
 
   ParseSubtargetFeatures(GPU, FullFS);
@@ -63,14 +73,6 @@
     FlatForGlobal = true;
   }
 
-  // FIXME: I don't think think Evergreen has any useful support for
-  // denormals, but should be checked. Should we issue a warning somewhere
-  // if someone tries to enable these?
-  if (getGeneration() <= AMDGPUSubtarget::NORTHERN_ISLANDS) {
-    FP64FP16Denormals = false;
-    FP32Denormals = false;
-  }
-
   // Set defaults if needed.
   if (MaxPrivateElementSize == 0)
     MaxPrivateElementSize = 4;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D39931.122558.patch
Type: text/x-patch
Size: 1531 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20171111/0168525b/attachment.bin>