[Mlir-commits] [mlir] [MLIR] Correct Initial TMA Descriptor Values (PR #67397)

[Guray Ozen]

https://github.com/grypp created https://github.com/llvm/llvm-project/pull/67397

This PR fixes inaccurate initial values in the TMA (Tensor Memory Allocator) descriptor creation process.

>From 8c3818e5a92ee78bf71492fe9846252c9b9d550b Mon Sep 17 00:00:00 2001
From: Guray Ozen <guray.ozen at gmail.com>
Date: Tue, 26 Sep 2023 09:20:07 +0200
Subject: [PATCH] [MLIR] Correct Initial TMA Descriptor Values

This PR fixes inaccurate initial values in the TMA (Tensor Memory Allocator) descriptor creation process.
---
 mlir/lib/ExecutionEngine/CudaRuntimeWrappers.cpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mlir/lib/ExecutionEngine/CudaRuntimeWrappers.cpp b/mlir/lib/ExecutionEngine/CudaRuntimeWrappers.cpp
index 3dbbc674128732e..2c04821303a49f9 100644
--- a/mlir/lib/ExecutionEngine/CudaRuntimeWrappers.cpp
+++ b/mlir/lib/ExecutionEngine/CudaRuntimeWrappers.cpp
@@ -376,8 +376,8 @@ extern "C" MLIR_CUDA_WRAPPERS_EXPORT void *mgpuTensorMapEncodeTiledMemref(
   CUtensorMap tensorMap;
 
   auto *globalAddress = descriptor->data;
-  uint32_t boxDim[5] = {0}, elementStrides[5] = {0};
-  uint64_t globalDim[5] = {0}, globalStrides[5] = {0};
+  uint32_t boxDim[5] = {1, 1, 1, 1, 1}, elementStrides[5] = {1, 1, 1, 1, 1};
+  uint64_t globalDim[5] = {1, 1, 1, 1, 1}, globalStrides[5] = {0};
   uint32_t tensorRank32 = uint32_t(tensorRank);
 
   static const int elementSizeInBytes[] = {1, 2, 4, 4, 8, 8, 2,