================ @@ -1,80 +1,58 @@ -; RUN: llc -mtriple=amdgcn -mcpu=gfx600 -disable-promote-alloca-to-vector < %s | FileCheck %s - -declare ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr() #1 - -declare i32 @llvm.amdgcn.workitem.id.x() #1 - -; CI+ intrinsic -declare void @llvm.amdgcn.s.dcache.inv.vol() #0 - -; VI+ intrinsic -declare void @llvm.amdgcn.s.dcache.wb() #0 +; RUN: llc -mtriple=amdgpu9 < %s | FileCheck %s ---------------- arsenm wrote:
The main thing would be if there was a check for the produced target ID, which I forgot to add in https://github.com/llvm/llvm-project/pull/206485 _______________________________________________ llvm-branch-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
