Fix the tt to linalg error in matmul converter,

the tt.dot with accumulator will lower to linalg.matmul and arith.add,
and the arith.add will further lower to linalg.generic,
generic will take the lhs of add as the DPS init, so the lhs of add
must be the accmulator.

include/triton-shared/Conversion/TritonArithToLinalg/ConversionPatterns.hpp

@@ -1027,9 +1027,9 @@ struct MatmulConverter : public OpConversionPattern<triton::DotOp> {
 
     if (!skipC) {
       if (integers) {
-        res = rewriter.create<arith::AddIOp>(loc, res, opc);
+        res = rewriter.create<arith::AddIOp>(loc, opc, res);
       } else {
-        res = rewriter.create<arith::AddFOp>(loc, res, opc);
+        res = rewriter.create<arith::AddFOp>(loc, opc, res);
       }
     }
 

test/Conversion/StructuredToMemref/dot.mlir

@@ -74,7 +74,7 @@ module {
 // CHECK-DAG:       [[VAR_4_:%.+]] = tensor.empty() : tensor<128x256xbf16>
 // CHECK:           [[VAR_5_:%.+]] = linalg.fill ins([[CST_0_dot_000000_]] : bf16) outs([[VAR_4_]] : tensor<128x256xbf16>) -> tensor<128x256xbf16>
 // CHECK:           [[VAR_6_:%.+]] = linalg.matmul ins([[VAR_0_]], [[VAR_transposed_]] : tensor<128x64xbf16>, tensor<64x256xbf16>) outs([[VAR_5_]] : tensor<128x256xbf16>) -> tensor<128x256xbf16>
-// CHECK:           [[VAR_7_:%.+]] = linalg.generic {indexing_maps = [#map, #map, #map], iterator_types = ["parallel", "parallel"]} ins([[VAR_6_]], [[VAR_3_]] : tensor<128x256xbf16>, tensor<128x256xbf16>) outs([[VAR_6_]] : tensor<128x256xbf16>) {
+// CHECK:           [[VAR_7_:%.+]] = linalg.generic {indexing_maps = [#map, #map, #map], iterator_types = ["parallel", "parallel"]} ins([[VAR_6_]], [[VAR_3_]] : tensor<128x256xbf16>, tensor<128x256xbf16>) outs([[VAR_3_]] : tensor<128x256xbf16>) {
 // CHECK:           ^bb0([[IN_0_:%.+]]: bf16, [[IN_1_:%.+]]: bf16, [[IN_2_:%.+]]: bf16):
 // CHECK:             [[VAR_8_:%.+]] = arith.addf [[IN_0_]], [[IN_1_]] : bf16
 // CHECK:             linalg.yield [[VAR_8_]] : bf16