1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
|
// RUN: mlir-opt %s \
// RUN: | mlir-opt -gpu-kernel-outlining \
// RUN: | mlir-opt -pass-pipeline='builtin.module(gpu.module(strip-debuginfo,convert-gpu-to-nvvm,gpu-to-cubin{chip=sm_70}))' \
// RUN: | mlir-opt --convert-scf-to-cf -gpu-to-llvm \
// RUN: | mlir-cpu-runner \
// RUN: --shared-libs=%mlir_lib_dir/libmlir_cuda_runtime%shlibext \
// RUN: --shared-libs=%mlir_lib_dir/libmlir_runner_utils%shlibext \
// RUN: --entry-point-result=void \
// RUN: | FileCheck %s
func.func @main() {
%0 = memref.alloc() : memref<16x16xf16>
%22 = memref.alloc() : memref<16x16xf32>
%1 = memref.alloc() : memref<16x16xf32>
%f1 = arith.constant 1.0e+00 : f16
%f0 = arith.constant 0.0e+00 : f32
%c0 = arith.constant 0 : index
%c16 = arith.constant 16 : index
%c32 = arith.constant 32 : index
%c1 = arith.constant 1 : index
// Intialize the Input matrix with ones.
scf.for %arg0 = %c0 to %c16 step %c1 {
scf.for %arg1 = %c0 to %c16 step %c1 {
memref.store %f1, %0[%arg0, %arg1] : memref<16x16xf16>
}
}
// Intialize the accumulator matrix with zeros.
scf.for %arg0 = %c0 to %c16 step %c1 {
scf.for %arg1 = %c0 to %c16 step %c1 {
memref.store %f0, %22[%arg0, %arg1] : memref<16x16xf32>
}
}
%2 = memref.cast %0 : memref<16x16xf16> to memref<*xf16>
%33 = memref.cast %22 : memref<16x16xf32> to memref<*xf32>
%3 = memref.cast %1 : memref<16x16xf32> to memref<*xf32>
gpu.host_register %2 : memref<*xf16>
gpu.host_register %33 : memref<*xf32>
gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %c1, %grid_y = %c1, %grid_z = %c1)
threads(%tx, %ty, %tz) in (%block_x = %c32, %block_y = %c1, %block_z = %c1) {
%A = gpu.subgroup_mma_load_matrix %0[%c0, %c0] {leadDimension = 16 : index} : memref<16x16xf16> -> !gpu.mma_matrix<16x16xf16, "AOp">
%B = gpu.subgroup_mma_load_matrix %0[%c0, %c0] {leadDimension = 16 : index} : memref<16x16xf16> -> !gpu.mma_matrix<16x16xf16, "BOp">
%C = gpu.subgroup_mma_load_matrix %22[%c0, %c0] {leadDimension = 16 : index} : memref<16x16xf32> -> !gpu.mma_matrix<16x16xf32, "COp">
%R = gpu.subgroup_mma_compute %A, %B, %C : !gpu.mma_matrix<16x16xf16, "AOp">, !gpu.mma_matrix<16x16xf16, "BOp"> -> !gpu.mma_matrix<16x16xf32, "COp">
gpu.subgroup_mma_store_matrix %R, %22[%c0, %c0] {leadDimension = 16 : index}: !gpu.mma_matrix<16x16xf32, "COp">, memref<16x16xf32>
gpu.terminator
}
// Print the memref after computation.
call @printMemrefF32(%33) : (memref<*xf32>) -> ()
// CHECK: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16],
// CHECK-NEXT: [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16]
return
}
func.func private @printMemrefF32(memref<*xf32>)
|
