[PATCH] D73471: Fixed tanh lowering from Standard dialect to NVVM and ROCDL.

[Julian Gross via Phabricator via llvm-commits]

dfki-jugr created this revision.
Herald added subscribers: llvm-commits, liufengdb, herhut, lucyrfox, mgester, arpith-jacob, csigg, antiagainst, shauheen, burmako, jpienaar, rriddle, mehdi_amini, jholewinski.
Herald added a reviewer: nicolasvasilache.
Herald added a project: LLVM.

The tanh lowering from Standard dialect to NVVM and ROCDL was not working.
The conversion pattern are inserted in the lowering files.
The test cases for the lowerings were added in the test files.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D73471

Files:
  mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
  mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
  mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
  mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir


Index: mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir
===================================================================
--- mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir
+++ mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir
@@ -83,6 +83,20 @@
 
 // -----
 
+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-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
+    %result64 = std.tanh %arg_f64 : f64
+    // 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
Index: mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
===================================================================
--- mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
+++ mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
@@ -156,6 +156,20 @@
 
 // -----
 
+gpu.module @test_module {
+  // CHECK: llvm.func @__nv_tanhf(!llvm.float) -> !llvm.float
+  // CHECK: llvm.func @__nv_tanh(!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 @__nv_tanhf(%{{.*}}) : (!llvm.float) -> !llvm.float
+    %result64 = std.tanh %arg_f64 : f64
+    // CHECK: llvm.call @__nv_tanh(%{{.*}}) : (!llvm.double) -> !llvm.double
+    std.return
+  }
+}
+
+// -----
 gpu.module @test_module {
   // CHECK: llvm.func @__nv_expf(!llvm.float) -> !llvm.float
   // CHECK: llvm.func @__nv_exp(!llvm.double) -> !llvm.double
Index: mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
===================================================================
--- mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
+++ mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
@@ -58,6 +58,8 @@
                                                  "_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>();
Index: mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
===================================================================
--- mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
+++ mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
@@ -746,6 +746,8 @@
                                                "__nv_cos");
   patterns.insert<OpToFuncCallLowering<ExpOp>>(converter, "__nv_expf",
                                                "__nv_exp");
+  patterns.insert<OpToFuncCallLowering<TanhOp>>(converter, "__nv_tanhf",
+                                               "__nv_tanh");
 }
 
 std::unique_ptr<OpPassBase<gpu::GPUModuleOp>>


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D73471.240556.patch
Type: text/x-patch
Size: 3291 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200127/70a995b3/attachment.bin>