[clang] [llvm] AMDGPU: Add MC layer support for load transpose instructions for gfx1250 (PR #146024)

[Changpeng Fang via cfe-commits]

================
@@ -1092,19 +1092,23 @@ let SubtargetPredicate = isGFX12Plus in {
   }
 
   let WaveSizePredicate = isWave32 in {
-    let Mnemonic = "global_load_tr_b128" in
-    defm GLOBAL_LOAD_TR_B128_w32  : FLAT_Global_Load_Pseudo 
<"global_load_tr_b128_w32", VReg_128>;
-    let Mnemonic = "global_load_tr_b64" in
-    defm GLOBAL_LOAD_TR_B64_w32   : FLAT_Global_Load_Pseudo 
<"global_load_tr_b64_w32", VReg_64>;
-  }
-  let WaveSizePredicate = isWave64 in {
-    let Mnemonic = "global_load_tr_b128" in
-    defm GLOBAL_LOAD_TR_B128_w64  : FLAT_Global_Load_Pseudo 
<"global_load_tr_b128_w64", VReg_64>;
-    let Mnemonic = "global_load_tr_b64" in
-    defm GLOBAL_LOAD_TR_B64_w64   : FLAT_Global_Load_Pseudo 
<"global_load_tr_b64_w64", VGPR_32>;
+    defm GLOBAL_LOAD_TR_B128_w32  : FLAT_Global_Load_Pseudo 
<"global_load_tr_b128", VReg_128>;
+    defm GLOBAL_LOAD_TR_B64_w32   : FLAT_Global_Load_Pseudo 
<"global_load_tr_b64", VReg_64>;
   }
 } // End SubtargetPredicate = isGFX12Plus
 
+let WaveSizePredicate = isWave64, SubtargetPredicate = isGFX12PlusNot12_50 in {
+  let Mnemonic = "global_load_tr_b128" in
+  defm GLOBAL_LOAD_TR_B128_w64  : FLAT_Global_Load_Pseudo 
<"global_load_tr_b128_w64", VReg_64>;
+  let Mnemonic = "global_load_tr_b64" in
+  defm GLOBAL_LOAD_TR_B64_w64   : FLAT_Global_Load_Pseudo 
<"global_load_tr_b64_w64", VGPR_32>;
+}
+
+let WaveSizePredicate = isWave32, SubtargetPredicate = isGFX1250Plus in {
----------------
changpeng wrote:

This was later changed to HasTransposeLoadF4F6Insts. When I made that change, I 
also submitted  the change to downsream. Unfortunately, you are merging an 
older point from upstream to ToT downstream branch. 

https://github.com/llvm/llvm-project/pull/146024
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits