From: Julian Gross <julian.gross@dfki.de>
Date: Tue, 28 Jan 2020 10:09:13 +0000 (+0100)
Subject: Changed wrong ROCDL instructions in GPU lowering.
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=addc27bc437d2fb1f31d88294b227ac32be63cc5;p=platform%2Fupstream%2Fllvm.git

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
---

diff --git a/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp b/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
index 602068d..d74fcdb 100644
--- a/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
+++ b/mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
@@ -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>();
diff --git a/mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir b/mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir
index b2d9f73..b733e9b 100644
--- a/mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir
+++ b/mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir
@@ -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" () : () -> ()