vector-transferops.mlir
2.7 KB
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
75
76
// RUN: mlir-rocm-runner %s --shared-libs=%rocm_wrapper_library_dir/librocm-runtime-wrappers%shlibext,%linalg_test_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s
func @vectransferx2(%arg0 : memref<?xf32>, %arg1 : memref<?xf32>) {
%cst = constant 1 : index
gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %cst, %grid_y = %cst, %grid_z = %cst)
threads(%tx, %ty, %tz) in (%block_x = %cst, %block_y = %cst, %block_z = %cst) {
%f0 = constant 0.0: f32
%base = constant 0 : index
%f = vector.transfer_read %arg0[%base], %f0
{permutation_map = affine_map<(d0) -> (d0)>} :
memref<?xf32>, vector<2xf32>
%c = addf %f, %f : vector<2xf32>
%base1 = constant 1 : index
vector.transfer_write %c, %arg1[%base1]
{permutation_map = affine_map<(d0) -> (d0)>} :
vector<2xf32>, memref<?xf32>
gpu.terminator
}
return
}
func @vectransferx4(%arg0 : memref<?xf32>, %arg1 : memref<?xf32>) {
%cst = constant 1 : index
gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %cst, %grid_y = %cst, %grid_z = %cst)
threads(%tx, %ty, %tz) in (%block_x = %cst, %block_y = %cst, %block_z = %cst) {
%f0 = constant 0.0: f32
%base = constant 0 : index
%f = vector.transfer_read %arg0[%base], %f0
{permutation_map = affine_map<(d0) -> (d0)>} :
memref<?xf32>, vector<4xf32>
%c = addf %f, %f : vector<4xf32>
vector.transfer_write %c, %arg1[%base]
{permutation_map = affine_map<(d0) -> (d0)>} :
vector<4xf32>, memref<?xf32>
gpu.terminator
}
return
}
func @main() {
%cf1 = constant 1.0 : f32
%arg0 = alloc() : memref<4xf32>
%arg1 = alloc() : memref<4xf32>
%22 = memref_cast %arg0 : memref<4xf32> to memref<?xf32>
%23 = memref_cast %arg1 : memref<4xf32> to memref<?xf32>
%cast0 = memref_cast %22 : memref<?xf32> to memref<*xf32>
%cast1 = memref_cast %23 : memref<?xf32> to memref<*xf32>
call @mgpuMemHostRegisterFloat(%cast0) : (memref<*xf32>) -> ()
call @mgpuMemHostRegisterFloat(%cast1) : (memref<*xf32>) -> ()
%24 = call @mgpuMemGetDeviceMemRef1dFloat(%22) : (memref<?xf32>) -> (memref<?xf32>)
%26 = call @mgpuMemGetDeviceMemRef1dFloat(%23) : (memref<?xf32>) -> (memref<?xf32>)
// CHECK: [1.23, 2.46, 2.46, 1.23]
call @vectransferx2(%24, %26) : (memref<?xf32>, memref<?xf32>) -> ()
call @print_memref_f32(%cast1) : (memref<*xf32>) -> ()
// CHECK: [2.46, 2.46, 2.46, 2.46]
call @vectransferx4(%24, %26) : (memref<?xf32>, memref<?xf32>) -> ()
call @print_memref_f32(%cast1) : (memref<*xf32>) -> ()
return
}
func @mgpuMemHostRegisterFloat(%ptr : memref<*xf32>)
func @mgpuMemGetDeviceMemRef1dFloat(%ptr : memref<?xf32>) -> (memref<?xf32>)
func @print_memref_f32(%ptr : memref<*xf32>)