File: addf.mlir

package info (click to toggle)
llvm-toolchain-14 1%3A14.0.6-16
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 1,496,368 kB
  • sloc: cpp: 5,593,980; ansic: 986,873; asm: 585,869; python: 184,223; objc: 72,530; lisp: 31,119; f90: 27,793; javascript: 9,780; pascal: 9,762; sh: 9,482; perl: 7,468; ml: 5,432; awk: 3,523; makefile: 2,547; xml: 953; cs: 573; fortran: 567
file content (50 lines) | stat: -rw-r--r-- 2,175 bytes parent folder | download | duplicates (3)
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
// RUN: mlir-vulkan-runner %s --shared-libs=%vulkan_wrapper_library_dir/libvulkan-runtime-wrappers%shlibext,%linalg_test_lib_dir/libmlir_runner_utils%shlibext --entry-point-result=void | FileCheck %s

// CHECK: [3.3,  3.3,  3.3,  3.3,  3.3,  3.3,  3.3,  3.3]
module attributes {
  gpu.container_module,
  spv.target_env = #spv.target_env<
    #spv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>, {}>
} {
  gpu.module @kernels {
    gpu.func @kernel_add(%arg0 : memref<8xf32>, %arg1 : memref<8xf32>, %arg2 : memref<8xf32>)
      kernel attributes { spv.entry_point_abi = {local_size = dense<[1, 1, 1]>: vector<3xi32> }} {
      %0 = gpu.block_id x
      %1 = memref.load %arg0[%0] : memref<8xf32>
      %2 = memref.load %arg1[%0] : memref<8xf32>
      %3 = arith.addf %1, %2 : f32
      memref.store %3, %arg2[%0] : memref<8xf32>
      gpu.return
    }
  }

  func @main() {
    %arg0 = memref.alloc() : memref<8xf32>
    %arg1 = memref.alloc() : memref<8xf32>
    %arg2 = memref.alloc() : memref<8xf32>
    %0 = arith.constant 0 : i32
    %1 = arith.constant 1 : i32
    %2 = arith.constant 2 : i32
    %value0 = arith.constant 0.0 : f32
    %value1 = arith.constant 1.1 : f32
    %value2 = arith.constant 2.2 : f32
    %arg3 = memref.cast %arg0 : memref<8xf32> to memref<?xf32>
    %arg4 = memref.cast %arg1 : memref<8xf32> to memref<?xf32>
    %arg5 = memref.cast %arg2 : memref<8xf32> to memref<?xf32>
    call @fillResource1DFloat(%arg3, %value1) : (memref<?xf32>, f32) -> ()
    call @fillResource1DFloat(%arg4, %value2) : (memref<?xf32>, f32) -> ()
    call @fillResource1DFloat(%arg5, %value0) : (memref<?xf32>, f32) -> ()

    %cst1 = arith.constant 1 : index
    %cst8 = arith.constant 8 : index
    gpu.launch_func @kernels::@kernel_add
        blocks in (%cst8, %cst1, %cst1) threads in (%cst1, %cst1, %cst1)
        args(%arg0 : memref<8xf32>, %arg1 : memref<8xf32>, %arg2 : memref<8xf32>)
    %arg6 = memref.cast %arg5 : memref<?xf32> to memref<*xf32>
    call @print_memref_f32(%arg6) : (memref<*xf32>) -> ()
    return
  }
  func private @fillResource1DFloat(%0 : memref<?xf32>, %1 : f32)
  func private @print_memref_f32(%ptr : memref<*xf32>)
}