[Mlir-commits] [mlir] [mlir][gpu] Add support for lowering math.erf to __nv_erf (PR #79848)

[David Majnemer]

https://github.com/majnemer created https://github.com/llvm/llvm-project/pull/79848

None

>From c7aecf77dff3f845d823195e9294f0a264f1152e Mon Sep 17 00:00:00 2001
From: David Majnemer <david.majnemer at gmail.com>
Date: Mon, 29 Jan 2024 15:18:31 +0000
Subject: [PATCH] [mlir][gpu] Add support for lowering math.erf to __nv_erf

---
 mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
index a7ac2332961ae2..d6a5d8cd74d5f2 100644
--- a/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
+++ b/mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
@@ -367,6 +367,7 @@ void mlir::populateGpuToNVVMConversionPatterns(LLVMTypeConverter &converter,
   populateOpPatterns<math::CeilOp>(converter, patterns, "__nv_ceilf",
                                    "__nv_ceil");
   populateOpPatterns<math::CosOp>(converter, patterns, "__nv_cosf", "__nv_cos");
+  populateOpPatterns<math::ErfOp>(converter, patterns, "__nv_erff", "__nv_erf");
   populateOpPatterns<math::ExpOp>(converter, patterns, "__nv_expf", "__nv_exp");
   populateOpPatterns<math::Exp2Op>(converter, patterns, "__nv_exp2f",
                                    "__nv_exp2");