[llvm] [AMDGPU] Add image_atomic_fmin/fmax as aliases for GFX12 (PR #107242)

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Wed Sep 4 11:50:03 PDT 2024


================
@@ -1675,6 +1675,10 @@ defm IMAGE_ATOMIC_PK_ADD_BF16   : MIMG_Atomic <mimgopc<0x87, MIMG.NOP, MIMG.NOP,
 defm IMAGE_ATOMIC_ADD_FLT       : MIMG_Atomic <mimgopc<0x83, MIMG.NOP, MIMG.NOP, MIMG.NOP>, "image_atomic_add_flt", 0, 1>;
 defm IMAGE_ATOMIC_MIN_FLT       : MIMG_Atomic <mimgopc<0x84, MIMG.NOP, MIMG.NOP, MIMG.NOP>, "image_atomic_min_num_flt", 0, 1, "image_atomic_min_flt">;
 defm IMAGE_ATOMIC_MAX_FLT       : MIMG_Atomic <mimgopc<0x85, MIMG.NOP, MIMG.NOP, MIMG.NOP>, "image_atomic_max_num_flt", 0, 1, "image_atomic_max_flt">;
+let AssemblerPredicate = isGFX12Plus in {
+  def : AMDGPUMnemonicAlias<"image_atomic_fmin", "image_atomic_min_flt">;
----------------
arsenm wrote:

I don't doubt it's the same opcode, I'm questioning whether this is another surprise opcode behavior change 

https://github.com/llvm/llvm-project/pull/107242


More information about the llvm-commits mailing list