19 lines · plain
1// RUN: mlir-opt %s -test-nvgpu-mmasync-f32-to-tf32-patterns="precision=tf32x3" -split-input-file | FileCheck %s2 3// CHECK-LABEL: m16n8k4_tf324func.func @m16n8k4_tf32(%arg0: vector<2x1xf32>, %arg1: vector<1x1xf32>, %arg2: vector<2x2xf32>) -> vector<2x2xf32> {5 // expected-error @+1 {{TF32x3 is not supported at the moment for nvgpu.mma.sync on f32 datatype}}6 %d = nvgpu.mma.sync (%arg0, %arg1, %arg2) {mmaShape = [16, 8, 4]} : (vector<2x1xf32>, vector<1x1xf32>, vector<2x2xf32>) -> vector<2x2xf32>7 return %d : vector<2x2xf32>8}9 10// -----11 12// CHECK-LABEL: m16n8k8_tf3213func.func @m16n8k8_tf32(%arg0: vector<4x1xf32>, %arg1: vector<2x1xf32>, %arg2: vector<2x2xf32>) -> vector<2x2xf32> {14 // expected-error @+1 {{TF32x3 is not supported at the moment for nvgpu.mma.sync on f32 datatype}}15 %d = nvgpu.mma.sync (%arg0, %arg1, %arg2) {mmaShape = [16, 8, 8]} : (vector<4x1xf32>, vector<2x1xf32>, vector<2x2xf32>) -> vector<2x2xf32>16 return %d : vector<2x2xf32>17}18// -----19