From 650109a3483908f0ae7533f10916667f8cd7abdf Mon Sep 17 00:00:00 2001
From: "assistant-librarian[bot]"
 <assistant-librarian[bot]@users.noreply.github.com>
Date: Fri, 7 Nov 2025 04:14:29 +0000
Subject: [PATCH] Merge commit 'e31a7a4f29b371c32ea9daf9211b6ae1fed2fa40' into
 develop

---
 .../gpu/grid/gridwise_gemm_xdl_cshuffle_v3_mx_bpreshuffle.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_mx_bpreshuffle.hpp b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_mx_bpreshuffle.hpp
index 3d2ef9b6c4..7c5bd606b2 100644
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_mx_bpreshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_mx_bpreshuffle.hpp
@@ -429,8 +429,8 @@ struct GridwiseGemmMX_xdl_cshuffle_v3_bpreshuffle
         constexpr index_t MWave           = MPerBlock / (MXdlPerWave * MPerXdl);
         constexpr index_t WaveSize        = BlockSize / (MWave * NWave);
         constexpr index_t NkSwizzleNumber = Number<WaveSize * KPack>{};
-        return make_naive_tensor_descriptor_packed(
-            make_tuple(N0 / NWave / NXdlPack, NWave, NXdlPack, K0, NkSwizzleNumber));
+        return make_naive_tensor_descriptor_packed(make_tuple(
+            math::integer_divide_ceil(N0, NWave * NXdlPack), NWave, NXdlPack, K0, NkSwizzleNumber));
     }
 
     __host__ __device__ static auto MakeBGridDescriptor_BK0_N_BK1(