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

Changed wrong ROCDL instructions in GPU lowering. 

Summary:
In the scope of the lowering phase from GPU to ROCDL, the intructions for the conversion patterns seems to be wrong.
According to https://github.com/ROCm-Developer-Tools/HIP/blob/master/include/hip/hcc_detail/math_fwd.h the instructions need two underscores in the beginning instead of one.

Reviewers: nicolasvasilache, herhut, rriddle

Reviewed By: herhut, rriddle

Subscribers: merge_guards_bot, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, csigg, arpith-jacob, mgester, lucyrfox, herhut, liufengdb, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D73535
This commit is contained in:
Julian Gross 2020-01-28 11:09:13 +01:00
parent 6cc6e89c11
commit addc27bc43
2 changed files with 36 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
View File

@ -50,16 +50,16 @@ public:
GPUIndexIntrinsicOpLowering<gpu::GridDimOp, ROCDL::GridDimXOp,
ROCDL::GridDimYOp, ROCDL::GridDimZOp>>(
converter);
patterns.insert<OpToFuncCallLowering<AbsFOp>>(converter, "_ocml_fabs_f32",
"_ocml_fabs_f64");
patterns.insert<OpToFuncCallLowering<CeilFOp>>(converter, "_ocml_ceil_f32",
"_ocml_ceil_f64");
patterns.insert<OpToFuncCallLowering<CosOp>>(converter, "_ocml_cos_f32",
"_ocml_cos_f64");
patterns.insert<OpToFuncCallLowering<ExpOp>>(converter, "_ocml_exp_f32",
"_ocml_exp_f64");
patterns.insert<OpToFuncCallLowering<TanhOp>>(converter, "_ocml_tanh_f32",
"_ocml_tanh_f64");
patterns.insert<OpToFuncCallLowering<AbsFOp>>(converter, "__ocml_fabs_f32",
"__ocml_fabs_f64");
patterns.insert<OpToFuncCallLowering<CeilFOp>>(converter, "__ocml_ceil_f32",
"__ocml_ceil_f64");
patterns.insert<OpToFuncCallLowering<CosOp>>(converter, "__ocml_cos_f32",
"__ocml_cos_f64");
patterns.insert<OpToFuncCallLowering<ExpOp>>(converter, "__ocml_exp_f32",
"__ocml_exp_f64");
patterns.insert<OpToFuncCallLowering<TanhOp>>(converter, "__ocml_tanh_f32",
"__ocml_tanh_f64");
ConversionTarget target(getContext());
target.addLegalDialect<LLVM::LLVMDialect, ROCDL::ROCDLDialect>();

52
mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir
View File

@ -39,14 +39,14 @@ gpu.module @kernel_module {
// -----
gpu.module @kernel_module {
// CHECK: llvm.func @_ocml_fabs_f32(!llvm.float) -> !llvm.float
// CHECK: llvm.func @_ocml_fabs_f64(!llvm.double) -> !llvm.double
// CHECK: llvm.func @__ocml_fabs_f32(!llvm.float) -> !llvm.float
// CHECK: llvm.func @__ocml_fabs_f64(!llvm.double) -> !llvm.double
// CHECK-LABEL: func @gpu_fabs
func @gpu_fabs(%arg_f32 : f32, %arg_f64 : f64) {
%result32 = std.absf %arg_f32 : f32
// CHECK: llvm.call @_ocml_fabs_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
// CHECK: llvm.call @__ocml_fabs_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
%result64 = std.absf %arg_f64 : f64
// CHECK: llvm.call @_ocml_fabs_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
// CHECK: llvm.call @__ocml_fabs_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
std.return
}
}
@ -54,14 +54,14 @@ gpu.module @kernel_module {
// -----
gpu.module @kernel_module {
// CHECK: llvm.func @_ocml_ceil_f32(!llvm.float) -> !llvm.float
// CHECK: llvm.func @_ocml_ceil_f64(!llvm.double) -> !llvm.double
// CHECK: llvm.func @__ocml_ceil_f32(!llvm.float) -> !llvm.float
// CHECK: llvm.func @__ocml_ceil_f64(!llvm.double) -> !llvm.double
// CHECK-LABEL: func @gpu_ceil
func @gpu_ceil(%arg_f32 : f32, %arg_f64 : f64) {
%result32 = std.ceilf %arg_f32 : f32
// CHECK: llvm.call @_ocml_ceil_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
// CHECK: llvm.call @__ocml_ceil_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
%result64 = std.ceilf %arg_f64 : f64
// CHECK: llvm.call @_ocml_ceil_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
// CHECK: llvm.call @__ocml_ceil_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
std.return
}
}
@ -69,14 +69,14 @@ gpu.module @kernel_module {
// -----
gpu.module @kernel_module {
// CHECK: llvm.func @_ocml_cos_f32(!llvm.float) -> !llvm.float
// CHECK: llvm.func @_ocml_cos_f64(!llvm.double) -> !llvm.double
// CHECK: llvm.func @__ocml_cos_f32(!llvm.float) -> !llvm.float
// CHECK: llvm.func @__ocml_cos_f64(!llvm.double) -> !llvm.double
// CHECK-LABEL: func @gpu_cos
func @gpu_cos(%arg_f32 : f32, %arg_f64 : f64) {
%result32 = std.cos %arg_f32 : f32
// CHECK: llvm.call @_ocml_cos_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
// CHECK: llvm.call @__ocml_cos_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
%result64 = std.cos %arg_f64 : f64
// CHECK: llvm.call @_ocml_cos_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
// CHECK: llvm.call @__ocml_cos_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
std.return
}
}
@ -84,30 +84,30 @@ gpu.module @kernel_module {
// -----
gpu.module @kernel_module {
// CHECK: llvm.func @_ocml_tanh_f32(!llvm.float) -> !llvm.float
// CHECK: llvm.func @_ocml_tanh_f64(!llvm.double) -> !llvm.double
// CHECK: llvm.func @__ocml_tanh_f32(!llvm.float) -> !llvm.float
// CHECK: llvm.func @__ocml_tanh_f64(!llvm.double) -> !llvm.double
// CHECK-LABEL: func @gpu_tanh
func @gpu_tanh(%arg_f32 : f32, %arg_f64 : f64) {
%result32 = std.tanh %arg_f32 : f32
// CHECK: llvm.call @_ocml_tanh_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
// CHECK: llvm.call @__ocml_tanh_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
%result64 = std.tanh %arg_f64 : f64
// CHECK: llvm.call @_ocml_tanh_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
// CHECK: llvm.call @__ocml_tanh_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
std.return
}
}
// -----
gpu.module @kernel_module {
// CHECK: llvm.func @_ocml_exp_f32(!llvm.float) -> !llvm.float
// CHECK: llvm.func @_ocml_exp_f64(!llvm.double) -> !llvm.double
// CHECK: llvm.func @__ocml_exp_f32(!llvm.float) -> !llvm.float
// CHECK: llvm.func @__ocml_exp_f64(!llvm.double) -> !llvm.double
// CHECK-LABEL: func @gpu_exp
func @gpu_exp(%arg_f32 : f32, %arg_f64 : f64) {
%exp_f32 = std.exp %arg_f32 : f32
// CHECK: llvm.call @_ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
// CHECK: llvm.call @__ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
%result_f32 = std.exp %exp_f32 : f32
// CHECK: llvm.call @_ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
// CHECK: llvm.call @__ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
%result64 = std.exp %arg_f64 : f64
// CHECK: llvm.call @_ocml_exp_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
// CHECK: llvm.call @__ocml_exp_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
std.return
}
}
@ -119,16 +119,16 @@ gpu.module @kernel_module {
gpu.module @kernel_module {
"test.symbol_scope"() ({
// CHECK: test.symbol_scope
// CHECK: llvm.func @_ocml_exp_f32(!llvm.float) -> !llvm.float
// CHECK: llvm.func @_ocml_exp_f64(!llvm.double) -> !llvm.double
// CHECK: llvm.func @__ocml_exp_f32(!llvm.float) -> !llvm.float
// CHECK: llvm.func @__ocml_exp_f64(!llvm.double) -> !llvm.double
// CHECK-LABEL: func @gpu_exp
func @gpu_exp(%arg_f32 : f32, %arg_f64 : f64) {
%exp_f32 = std.exp %arg_f32 : f32
// CHECK: llvm.call @_ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
// CHECK: llvm.call @__ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
%result_f32 = std.exp %exp_f32 : f32
// CHECK: llvm.call @_ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
// CHECK: llvm.call @__ocml_exp_f32(%{{.*}}) : (!llvm.float) -> !llvm.float
%result64 = std.exp %arg_f64 : f64
// CHECK: llvm.call @_ocml_exp_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
// CHECK: llvm.call @__ocml_exp_f64(%{{.*}}) : (!llvm.double) -> !llvm.double
std.return
}
"test.finish" () : () -> ()