[MLIR][Arith] Fix arith::AtomicRMWKind::maximumf's identity value (#70312)

-- In order to compute maximum, we should always initialise the
   result with the largest negative value possible for the concerned
   element type, instead of the smallest.
-- This commit essentially adds a fix to this issue.

Signed-off-by: Abhishek Varma <[email protected]>

Author: Abhishek-Varma

mlir/lib/Dialect/Arith/IR/ArithOps.cpp

@@ -2412,7 +2412,7 @@ TypedAttr mlir::arith::getIdentityValueAttr(AtomicRMWKind kind, Type resultType,
     const llvm::fltSemantics &semantic =
         llvm::cast<FloatType>(resultType).getFloatSemantics();
     APFloat identity = useOnlyFiniteValue
-                           ? APFloat::getSmallest(semantic, /*Negative=*/true)
+                           ? APFloat::getLargest(semantic, /*Negative=*/true)
                            : APFloat::getInf(semantic, /*Negative=*/true);
     return builder.getFloatAttr(resultType, identity);
   }

mlir/test/Dialect/Linalg/transform-op-decompose.mlir

@@ -210,7 +210,7 @@ func.func @softmax(%arg0: tensor<2x16x32xf32>, %dst: tensor<2x16x32xf32>) -> ten
 // CHECK-LABEL:      func.func @softmax(
 // CHECK-SAME:           %[[ARG0:[a-zA-Z0-9_]+]]: tensor<2x16x32xf32>, %[[DST:[a-zA-Z0-9_]+]]: tensor<2x16x32xf32>) -> tensor<2x16x32xf32> {
 // CHECK-DAG:        %[[D1:.+]] = tensor.empty() : tensor<2x16xf32>
-// CHECK-DAG:        %[[CST:.+]] = arith.constant -1.401300e-45 : f32
+// CHECK-DAG:        %[[CST:.+]] = arith.constant -3.40282347E+38 : f32
 // CHECK:        %[[D2:.+]] = linalg.fill ins(%[[CST]] : f32) outs(%[[D1]] : tensor<2x16xf32>) -> tensor<2x16xf32>
 // CHECK:        %[[D3:.+]] = linalg.generic {indexing_maps = [#[[$MAP]], #[[$MAP1]]], iterator_types = ["parallel",
 // CHECK-SAME:     "parallel", "reduction"]} ins(%[[ARG0]] : tensor<2x16x32xf32>) outs(%[[D2]] : tensor<2x16xf32>) {

mlir/test/Dialect/Linalg/transform-op-split-reduction.mlir

@@ -176,7 +176,7 @@ func.func @generic_split_3d_ninf(%input: tensor<32x2xf32>, %input_2: tensor<5x32
 //  CHECK-DAG: #[[$MAP3:.*]] = affine_map<(d0, d1, d2) -> (d0, d1, d2)>
 //  CHECK-DAG: #[[$MAP4:.*]] = affine_map<(d0, d1, d2) -> (d0, d1)>
 // CHECK-LABEL:  func @generic_split_3d_ninf
-//  CHECK-DAG: %[[ID:.*]] = arith.constant -1.401300e-45 : f32
+//  CHECK-DAG: %[[ID:.*]] = arith.constant -3.40282347E+38 : f32
 //  CHECK-DAG: %[[I1:.*]] = tensor.expand_shape %{{.*}}[0, 1], [2]] : tensor<32x2xf32> into tensor<4x8x2xf32>
 //  CHECK-DAG: %[[I2:.*]] = tensor.expand_shape %{{.*}}[0], [1, 2]] : tensor<5x32xf32> into tensor<5x4x8xf32>
 //  CHECK-DAG: %[[INI:.*]] = tensor.empty() : tensor<5x2x4xf32>