[llvm] [AMDGPU] Baseline gfx1250 speed model. (PR #145217)

[Georg Lehmann via llvm-commits]

================
@@ -455,3 +456,35 @@ def : HWWriteRes<WriteBarrier,           [HWBranch],       2000>;
 def : InstRW<[WriteCopy], (instrs COPY)>;
 
 }  // End SchedModel = GFX12SpeedModel
+
+multiclass GFX125xCommonWriteRes {
+
+def : HWWriteRes<Write32Bit,             [HWVALU, HWRC],   5>;
+def : HWWriteRes<WriteFloatCvt,          [HWVALU, HWRC],   5>;
+def : HWWriteRes<WriteTrans32,           [HWTransVALU, HWRC],   7>;
+def : HWWriteRes<WriteQuarterRate32,     [HWVALU, HWRC],   6>;
+def : HWWriteRes<WriteFloatFMA,          [HWVALU, HWRC],   5>;
+def : HWWriteRes<WritePseudoScalarTrans, [HWVALU, HWRC],   8>;
----------------
DadSchoorse wrote:

Why do WriteTrans32 and WritePseudoScalarTrans use different resources? And it seems unintuitive that the scalar trans cost is higher than trans32, is that correct?

https://github.com/llvm/llvm-project/pull/145217