[llvm-branch-commits] [llvm] [AMDGPU] Dynamic VGPR support for llvm.amdgcn.cs.chain (PR #130094)

Matt Arsenault via llvm-branch-commits llvm-branch-commits at lists.llvm.org
Fri Mar 14 06:07:01 PDT 2025


================
@@ -0,0 +1,11 @@
+; RUN: not --crash llc -mtriple=amdgcn--amdpal -mcpu=gfx1200 -global-isel=1 -mattr=+wavefrontsize64 -verify-machineinstrs=0 < %s 2>&1 | FileCheck %s
+; RUN: not llc -mtriple=amdgcn--amdpal -mcpu=gfx1200 -global-isel=0 -mattr=+wavefrontsize64 -verify-machineinstrs=0 < %s 2>&1 | FileCheck %s
+
+declare amdgpu_cs_chain void @callee() nounwind
+
+; CHECK: in function test_dvgpr void (): Dynamic VGPR mode is only supported for wave32
----------------
arsenm wrote:

```suggestion
; CHECK: in function test_dvgpr void (): dynamic VGPR mode is only supported for wave32
```

These should both be lowercase 

https://github.com/llvm/llvm-project/pull/130094


More information about the llvm-branch-commits mailing list