[llvm] r300481 - AMDGPU: Change stack alignment

[Matt Arsenault via llvm-commits]

Author: arsenm
Date: Mon Apr 17 14:48:24 2017
New Revision: 300481

URL: http://llvm.org/viewvc/llvm-project?rev=300481&view=rev
Log:
AMDGPU: Change stack alignment

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.

Modified:
    llvm/trunk/lib/Target/AMDGPU/AMDGPUSubtarget.h

Modified: llvm/trunk/lib/Target/AMDGPU/AMDGPUSubtarget.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/AMDGPUSubtarget.h?rev=300481&r1=300480&r2=300481&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPUSubtarget.h (original)
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPUSubtarget.h Mon Apr 17 14:48:24 2017
@@ -415,9 +415,11 @@ public:
     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 {