[README] update matmul example

Author: kumasento

tools/polymer/README.md

@@ -103,18 +103,18 @@ Optimize MLIR code described in the Affine dialect by Pluto:
 ```mlir
 // File name: matmul.mlir
 func @matmul() {
-  %A = alloc() : memref<64x64xf32>
-  %B = alloc() : memref<64x64xf32>
-  %C = alloc() : memref<64x64xf32>
+  %A = memref.alloc() : memref<64x64xf32>
+  %B = memref.alloc() : memref<64x64xf32>
+  %C = memref.alloc() : memref<64x64xf32>
 
   affine.for %i = 0 to 64 {
     affine.for %j = 0 to 64 {
       affine.for %k = 0 to 64 {
         %0 = affine.load %A[%i, %k] : memref<64x64xf32>
         %1 = affine.load %B[%k, %j] : memref<64x64xf32>
-        %2 = mulf %0, %1 : f32
+        %2 = arith.mulf %0, %1 : f32
         %3 = affine.load %C[%i, %j] : memref<64x64xf32>
-        %4 = addf %2, %3 : f32
+        %4 = arith.addf %2, %3 : f32
         affine.store %4, %C[%i, %j] : memref<64x64xf32>
       }
     }
@@ -135,21 +135,29 @@ Output:
 
 ```mlir
 #map0 = affine_map<(d0) -> (d0 * 32)>
-#map1 = affine_map<(d0) -> (d0 * 32 + 31)>
+#map1 = affine_map<(d0) -> (d0 * 32 + 32)>
 module  {
-  func @main(%arg0: memref<?x?xf32>, %arg1: memref<?x?xf32>, %arg2: memref<?x?xf32>) {
-    affine.for %arg3 = 0 to 1 {
-      affine.for %arg4 = 0 to 1 {
-        affine.for %arg5 = 0 to 1 {
-          affine.for %arg6 = #map0(%arg3) to #map1(%arg3) {
-            affine.for %arg7 = #map0(%arg5) to #map1(%arg5) {
-              affine.for %arg8 = #map0(%arg4) to #map1(%arg4) {
-                %0 = affine.load %arg0[%arg6, %arg8] : memref<?x?xf32>
-                %1 = affine.load %arg2[%arg7, %arg8] : memref<?x?xf32>
-                %2 = affine.load %arg1[%arg6, %arg7] : memref<?x?xf32>
-                %3 = mulf %2, %1 : f32
-                %4 = addf %3, %0 : f32
-                affine.store %4, %arg0[%arg6, %arg8] : memref<?x?xf32>
+  func private @S0(%arg0: index, %arg1: index, %arg2: memref<64x64xf32>, %arg3: index, %arg4: memref<64x64xf32>, %arg5: memref<64x64xf32>) attributes {scop.stmt} {
+    %0 = affine.load %arg5[symbol(%arg0), symbol(%arg3)] : memref<64x64xf32>
+    %1 = affine.load %arg4[symbol(%arg3), symbol(%arg1)] : memref<64x64xf32>
+    %2 = arith.mulf %0, %1 : f32
+    %3 = affine.load %arg2[symbol(%arg0), symbol(%arg1)] : memref<64x64xf32>
+    %4 = arith.addf %2, %3 : f32
+    affine.store %4, %arg2[symbol(%arg0), symbol(%arg1)] : memref<64x64xf32>
+    return
+  }
+  
+  func @matmul() {
+    %0 = memref.alloc() : memref<64x64xf32>
+    %1 = memref.alloc() : memref<64x64xf32>
+    %2 = memref.alloc() : memref<64x64xf32>
+    affine.for %arg0 = 0 to 2 {
+      affine.for %arg1 = 0 to 2 {
+        affine.for %arg2 = 0 to 2 {
+          affine.for %arg3 = #map0(%arg0) to #map1(%arg0) {
+            affine.for %arg4 = #map0(%arg2) to #map1(%arg2) {
+              affine.for %arg5 = #map0(%arg1) to #map1(%arg1) {
+                call @S0(%arg3, %arg5, %0, %arg4, %1, %2) : (index, index, memref<64x64xf32>, index, memref<64x64xf32>, memref<64x64xf32>) -> ()
               }
             }
           }