Fix LSU bug. (#778)

tensilelite/Tensile/Components/GlobalWriteBatch.py

@@ -1225,6 +1225,11 @@ def _emitNonatomicAdd(self, module: Module):
       else:
         gradientInput = self.ss.elementSumIdx[elementIdx]
         enableValuC   = True
+        if self.kernel["LocalSplitU"] > 1:
+          # When LSU > 1, the VGPRs are from LSU output.
+          # the elementSumIdx has indicated the VGPRs from LSU.
+          # Don't use the ValuC prefix here.
+          enableValuC = False
       if self.kernel["ActivationFuncCall"]:
         if (activationCDataType == self.kernel["ProblemType"]["DestDataType"]) and \
           (activationCDataType != self.kernel["ProblemType"]["ComputeDataType"]) and ((self.kernel["ProblemType"]["UseScaleCD"] == False) or (self.kernel["ProblemType"]["UseScaleAlphaVec"] == False)):

tensilelite/Tensile/Tests/common/gemm/lsu.yaml

@@ -384,6 +384,7 @@ BenchmarkProblems:
         - GlobalSplitU: [1,2,9]
         - GlobalSplitUAlgorithm: ["MultipleBuffer", "MultipleBufferSingleKernel"]
         - SourceSwap: [0, 1]
+        - ActivationFuncCall: [0, 1]
       BenchmarkJoinParameters:
       BenchmarkFinalParameters:
         - ProblemSizes:
@@ -409,6 +410,9 @@ BenchmarkProblems:
       TransposeB: 0
       UseBeta: True
       Batched: True
+      Activation: True
+      ActivationHPA: True
+      UseScaleAlphaVec: True
     - # BenchmarkProblemSizeGroup - Standard - All problem
       InitialSolutionParameters:
       BenchmarkCommonParameters:
@@ -450,7 +454,10 @@ BenchmarkProblems:
         - GlobalSplitU: [1]
         - GlobalSplitUAlgorithm: ["MultipleBuffer"]
         - SourceSwap: [1]
+        - ActivationFuncCall: [0, 1]
       BenchmarkJoinParameters:
       BenchmarkFinalParameters:
         - ProblemSizes:
-          - Exact: [128,   128,  1, 128]
+          - Exact: [128,   128,  1, 128]
+        - ActivationArgs:
+          - [Enum: tanh]