[clang] [llvm] [AMDGPU] Add builtins for FMA mix instructions (PR #214814)

[Yaxun Liu via llvm-commits]

================
@@ -0,0 +1,57 @@
+; NOTE: Checks are intentionally hand-written to verify only instruction selection.
+; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 < %s | FileCheck %s
+; RUN: llc -global-isel=1 -global-isel-abort=1 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 < %s | FileCheck %s
+; RUN: not llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=null < %s 2>&1 | FileCheck --check-prefix=ERR %s
+; RUN: not llc -global-isel=1 -global-isel-abort=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=null < %s 2>&1 | FileCheck --check-prefix=ERR %s
----------------
yxsamliu wrote:

Thanks, fixed by using `amdgpu12.50-amd-amdhsa` / `amdgpu9.00-amd-amdhsa` in the RUN lines.

https://github.com/llvm/llvm-project/pull/214814