[PATCH] D73535: Changed wrong ROCDL instructions in GPU lowering.

[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.
Herald added a reviewer: nicolasvasilache.
Herald added a project: LLVM.

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.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D73535

Files:
  mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp


Index: mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
===================================================================
--- mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
+++ mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
@@ -50,16 +50,16 @@
         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>();


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D73535.240810.patch
Type: text/x-patch
Size: 2053 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200128/e4fa97c0/attachment-0001.bin>