Add tanh lowering from Standard dialect to NVVM and ROCDL.

dfki-jugr · dfki-jugr · commit 664d2f5bad3e · 2020-01-28T11:01:10.000+01:00
Summary: 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. Reviewers: nicolasvasilache, ftynse, herhut Reviewed By: ftynse, herhut Subscribers: merge_guards_bot, ftynse, jholewinski, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, csigg, arpith-jacob, mgester, lucyrfox, herhut, liufengdb, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D73471
diff --git a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
@@ -746,6 +746,8 @@ void mlir::populateGpuToNVVMConversionPatterns(
                                                "__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>>
diff --git a/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp b/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
@@ -58,6 +58,8 @@ class LowerGpuOpsToROCDLOpsPass
                                                  "_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>();
diff --git a/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir b/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
@@ -156,6 +156,20 @@ gpu.module @test_module {
 
 // -----
 
+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
diff --git a/mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir b/mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir
@@ -83,6 +83,20 @@ 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-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

Original file line number	Diff line number	Diff line change
`@@ -746,6 +746,8 @@ void mlir::populateGpuToNVVMConversionPatterns(`
`746`	`746`	`"__nv_cos");`
`747`	`747`	`patterns.insert<OpToFuncCallLowering<ExpOp>>(converter, "__nv_expf",`
`748`	`748`	`"__nv_exp");`
	`749`	`+ patterns.insert<OpToFuncCallLowering<TanhOp>>(converter, "__nv_tanhf",`
	`750`	`+ "__nv_tanh");`
`749`	`751`	`}`
`750`	`752`
`751`	`753`	`std::unique_ptr<OpPassBase<gpu::GPUModuleOp>>`