maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[mlir][test][CPU] Reduce the size of mlir-cpu-runner-tests 

Two tests regularly show up on the long tail when testing MLIR.
This revision reduces their size.
This commit is contained in:
Nicolas Vasilache 2020-06-05 13:41:05 -04:00
parent a018b538a6
commit eb7db879af
2 changed files with 39 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
mlir/test/mlir-cpu-runner/linalg_integration_test.mlir
View File

@ -67,24 +67,24 @@ func @matmul() -> f32 {
%c1 = constant 1 : index
%c6 = constant 6 : index
%c7 = constant 7 : index
%c10 = constant 10 : index
%c2 = constant 2 : index
%c16 = constant 16 : index
%c100 = constant 100 : index
%c160 = constant 160 : index
%c4 = constant 4 : index
%c32 = constant 32 : index
%f1 = constant 1.00000e+00 : f32
%f2 = constant 2.00000e+00 : f32
%f10 = constant 10.00000e+00 : f32
%bA = call @alloc_filled_f32(%c160, %f2) : (index, f32) -> (memref<?xi8>)
%bB = call @alloc_filled_f32(%c160, %f1) : (index, f32) -> (memref<?xi8>)
%bC = call @alloc_filled_f32(%c100, %f10) : (index, f32) -> (memref<?xi8>)
%bA = call @alloc_filled_f32(%c32, %f2) : (index, f32) -> (memref<?xi8>)
%bB = call @alloc_filled_f32(%c32, %f1) : (index, f32) -> (memref<?xi8>)
%bC = call @alloc_filled_f32(%c4, %f10) : (index, f32) -> (memref<?xi8>)
%A = view %bA[%c0][%c10, %c16] : memref<?xi8> to memref<?x?xf32>
%B = view %bB[%c0][%c16, %c10] : memref<?xi8> to memref<?x?xf32>
%C = view %bC[%c0][%c10, %c10] : memref<?xi8> to memref<?x?xf32>
%A = view %bA[%c0][%c2, %c16] : memref<?xi8> to memref<?x?xf32>
%B = view %bB[%c0][%c16, %c2] : memref<?xi8> to memref<?x?xf32>
%C = view %bC[%c0][%c2, %c2] : memref<?xi8> to memref<?x?xf32>
linalg.matmul(%A, %B, %C) : memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>
%res = load %C[%c6, %c7] : memref<?x?xf32>
%res = load %C[%c0, %c1] : memref<?x?xf32>
dealloc %bC : memref<?xi8>
dealloc %bB : memref<?xi8>

58
mlir/test/mlir-cpu-runner/sgemm_naive_codegen.mlir
View File

@ -1,31 +1,31 @@
// RUN: mlir-opt -convert-linalg-to-loops -lower-affine -convert-scf-to-std -convert-std-to-llvm %s | mlir-cpu-runner -O3 -e main -entry-point-result=void -shared-libs=%mlir_runner_utils_dir/libmlir_runner_utils%shlibext | FileCheck %s
func @main() {
%A = alloc() : memref<64x64xf32>
%B = alloc() : memref<64x64xf32>
%C = alloc() : memref<64x64xf32>
%A = alloc() : memref<16x16xf32>
%B = alloc() : memref<16x16xf32>
%C = alloc() : memref<16x16xf32>
%cf1 = constant 1.00000e+00 : f32
linalg.fill(%A, %cf1) : memref<64x64xf32>, f32
linalg.fill(%B, %cf1) : memref<64x64xf32>, f32
linalg.fill(%A, %cf1) : memref<16x16xf32>, f32
linalg.fill(%B, %cf1) : memref<16x16xf32>, f32
%reps = constant 1 : index
%t_start = call @rtclock() : () -> f64
%t_start = call @rtclock() : () -> f16
affine.for %arg0 = 0 to 5 {
linalg.fill(%C, %cf1) : memref<64x64xf32>, f32
call @sgemm_naive(%A, %B, %C) : (memref<64x64xf32>, memref<64x64xf32>, memref<64x64xf32>) -> ()
linalg.fill(%C, %cf1) : memref<16x16xf32>, f32
call @sgemm_naive(%A, %B, %C) : (memref<16x16xf32>, memref<16x16xf32>, memref<16x16xf32>) -> ()
}
%t_end = call @rtclock() : () -> f64
%t = subf %t_end, %t_start : f64
%t_end = call @rtclock() : () -> f16
%t = subf %t_end, %t_start : f16
%pC = memref_cast %C : memref<64x64xf32> to memref<*xf32>
%pC = memref_cast %C : memref<16x16xf32> to memref<*xf32>
call @print_memref_f32(%pC) : (memref<*xf32>) -> ()
%M = dim %C, 0 : memref<64x64xf32>
%N = dim %C, 1 : memref<64x64xf32>
%K = dim %A, 1 : memref<64x64xf32>
%M = dim %C, 0 : memref<16x16xf32>
%N = dim %C, 1 : memref<16x16xf32>
%K = dim %A, 1 : memref<16x16xf32>
%f1 = muli %M, %N : index
%f2 = muli %f1, %K : index
@ -34,38 +34,38 @@ func @main() {
%c2 = constant 2 : index
%f3 = muli %c2, %f2 : index
%num_flops = muli %reps, %f3 : index
%num_flops_i = index_cast %num_flops : index to i64
%num_flops_f = sitofp %num_flops_i : i64 to f64
%flops = divf %num_flops_f, %t : f64
call @print_flops(%flops) : (f64) -> ()
%num_flops_i = index_cast %num_flops : index to i16
%num_flops_f = sitofp %num_flops_i : i16 to f16
%flops = divf %num_flops_f, %t : f16
call @print_flops(%flops) : (f16) -> ()
return
}
// CHECK: 65, 65, 65,
// CHECK: 17, 17, 17,
func @sgemm_naive(%arg0: memref<64x64xf32>, %arg1: memref<64x64xf32>, %arg2: memref<64x64xf32>) {
func @sgemm_naive(%arg0: memref<16x16xf32>, %arg1: memref<16x16xf32>, %arg2: memref<16x16xf32>) {
%c0 = constant 0 : index
affine.for %arg3 = 0 to 64 {
affine.for %arg4 = 0 to 64 {
affine.for %arg3 = 0 to 16 {
affine.for %arg4 = 0 to 16 {
%m = alloc() : memref<1xf32>
%v = affine.load %arg2[%arg3, %arg4] : memref<64x64xf32>
%v = affine.load %arg2[%arg3, %arg4] : memref<16x16xf32>
affine.store %v, %m[%c0] : memref<1xf32>
affine.for %arg5 = 0 to 64 {
%3 = affine.load %arg0[%arg3, %arg5] : memref<64x64xf32>
%4 = affine.load %arg1[%arg5, %arg4] : memref<64x64xf32>
affine.for %arg5 = 0 to 16 {
%3 = affine.load %arg0[%arg3, %arg5] : memref<16x16xf32>
%4 = affine.load %arg1[%arg5, %arg4] : memref<16x16xf32>
%5 = affine.load %m[0] : memref<1xf32>
%6 = mulf %3, %4 : f32
%7 = addf %6, %5 : f32
affine.store %7, %m[0] : memref<1xf32>
}
%s = affine.load %m[%c0] : memref<1xf32>
affine.store %s, %arg2[%arg3, %arg4] : memref<64x64xf32>
affine.store %s, %arg2[%arg3, %arg4] : memref<16x16xf32>
dealloc %m : memref<1xf32>
}
}
return
}
func @print_flops(f64)
func @rtclock() -> f64
func @print_flops(f16)
func @rtclock() -> f16
func @print_memref_f32(memref<*xf32>)