[PATCH] D31517: AMDGPU: Change stack alignment

[Matt Arsenault via Phabricator via llvm-commits]

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

While the incoming stack for a kernel is 256-byte aligned,
this refers to the base address of the entire wave. This isn't
useful information for most of codegen. Fixes unnecessarily
aligning stack objects in callees.


https://reviews.llvm.org/D31517

Files:
  lib/Target/AMDGPU/AMDGPUSubtarget.h


Index: lib/Target/AMDGPU/AMDGPUSubtarget.h
===================================================================
--- lib/Target/AMDGPU/AMDGPUSubtarget.h
+++ lib/Target/AMDGPU/AMDGPUSubtarget.h
@@ -415,9 +415,11 @@
     return 0;
   }
 
+  // Scratch is allocated in 256 dword per wave blocks for the entire
+  // wavefront. When viewed from the perspecive of an arbitrary workitem, this
+  // is 4-byte aligned.
   unsigned getStackAlignment() const {
-    // Scratch is allocated in 256 dword per wave blocks.
-    return 4 * 256 / getWavefrontSize();
+    return 4;
   }
 
   bool enableMachineScheduler() const override {


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D31517.93564.patch
Type: text/x-patch
Size: 623 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170330/88ee762c/attachment.bin>