[llvm] [AMDGPU] Do not scale private alloca size when using flat-scratch (PR #201142)

[Matt Arsenault via llvm-commits]

Juan Manuel Martinez =?utf-8?q?Caama=C3=B1o?=
Message-ID:
In-Reply-To: <llvm.org/llvm/llvm-project/pull/201142 at github.com>


================
@@ -1174,6 +1174,10 @@ bool AMDGPURegisterBankInfo::applyMappingDynStackAlloc(
   Register AllocSize = MI.getOperand(1).getReg();
   Align Alignment = assumeAligned(MI.getOperand(2).getImm());
 
+  // When using flat-scratch, the stack offset unscaled.
----------------
arsenm wrote:

```suggestion
  // When using flat-scratch, the stack offset is unscaled.
```

https://github.com/llvm/llvm-project/pull/201142