From c143bf30a53dd046a05f12b98fa5cecf595df3be Mon Sep 17 00:00:00 2001
From: Anton Gorenko <anton@streamhpc.com>
Date: Thu, 22 May 2025 16:24:43 +0500
Subject: [PATCH] Fix cache flushing for pk_i4

---
 .../gpu/device/impl/device_gemm_wmma_cshuffle_v3.hpp      | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma_cshuffle_v3.hpp b/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma_cshuffle_v3.hpp
index be7c733ed8..90afc467d4 100644
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma_cshuffle_v3.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma_cshuffle_v3.hpp
@@ -278,10 +278,10 @@ struct DeviceGemm_Wmma_CShuffleV3 : public DeviceGemmV2<ALayout,
                     const auto b_grid_desc_bk0_n_bk1 = GridwiseGemm::MakeBGridDescriptor_BK0_N_BK1(
                         arg_.K, arg_.KPadded, arg_.N, arg_.NPadded, arg_.StrideB, arg_.BK0);
 
-                    auto size_a_buffer =
-                        a_grid_desc_ak0_m_ak1.GetElementSpaceSize() * sizeof(ADataType);
-                    auto size_b_buffer =
-                        b_grid_desc_bk0_n_bk1.GetElementSpaceSize() * sizeof(BDataType);
+                    auto size_a_buffer = a_grid_desc_ak0_m_ak1.GetElementSpaceSize() *
+                                         sizeof(ADataType) / GridwiseGemm::APackedSize;
+                    auto size_b_buffer = b_grid_desc_bk0_n_bk1.GetElementSpaceSize() *
+                                         sizeof(BDataType) / GridwiseGemm::BPackedSize;
 
                     ck::utility::RotatingMemWrapper<Argument> rotating_mem(
                         arg_, stream_config.rotating_count, size_a_buffer, size_b_buffer);