Skip to content

GitLab

Commit f1d8217d authored by Jing Zhang's avatar Jing Zhang
Browse files

debuggging

parent fe728dc5
Hide whitespace changes
Inline Side-by-side
Showing with 48 additions and 45 deletions
example/01_gemm/gemm_wmma_fp16.cpp
View file @ f1d8217d
......@@ -19,48 +19,51 @@ using AElementOp = PassThrough;
using BElementOp = PassThrough;
using CElementOp = PassThrough;
static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemmWmma_CShuffle<ALayout,
BLayout,
CLayout,
ADataType,
BDataType,
CDataType,
AccDataType,
CShuffleDataType,
AElementOp,
BElementOp,
CElementOp,
GemmDefault,
1,
32,
16,
32,
64,
8,
16,
16,
1,
2,
S<2, 16, 1>,
S<1, 0, 2>,
S<1, 0, 2>,
2,
8,
8,
true,
S<2, 16, 1>,
S<1, 0, 2>,
S<1, 0, 2>,
2,
8,
8,
true,
1,
1,
S<1, 16, 1, 2>,
8>;
// clang-format off
using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemmWmma_CShuffle
< ALayout,
BLayout,
CLayout,
ADataType,
BDataType,
CDataType,
AccDataType,
CShuffleDataType,
AElementOp,
BElementOp,
CElementOp,
GemmDefault,
1, // Prefetch stage
128, // BlockSize
64, // MPerBlock
128, // NPerBlock
64, // KPerBlock
8, // K1
16, // MPerWmma
16, // NPerWmma
2, // M-Repeat // M-PerWmma / M-Repeat = M-Wave
4, // N-Repeat // N-PerWmma / N-Repeat = N-Wave
S<4, 32, 1>,
S<1, 0, 2>,
S<1, 0, 2>,
2,
8,
8,
true,
S<4, 32, 1>,
S<1, 0, 2>,
S<1, 0, 2>,
2,
8,
8,
true,
1, // C shuffle (M Repeat) Per store
1, // C shuffle (N Repeat) Per store
S<1, 32, 1, 4>,
8>;
// clang-format on
using ReferenceGemmInstance = ck::tensor_operation::host::
ReferenceGemm<ADataType, BDataType, CDataType, AccDataType, AElementOp, BElementOp, CElementOp>;
......
example/29_batched_gemm_bias_e_permute/batched_gemm_bias_e_permute_wmma_fp16.cpp
View file @ f1d8217d
......@@ -83,14 +83,14 @@ using DeviceOpInstanceKKNN =
2,
4,
4,
true,
false,
S<4, 32, 1>,
S<1, 0, 2>,
S<1, 0, 2>,
2,
4,
4,
true,
false,
1,
1,
S<1, 64, 1, 2>,
......
include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp
View file @ f1d8217d
......@@ -137,8 +137,8 @@ struct DeviceBatchedContractionMultipleD_Wmma_CShuffle
static constexpr auto BEnableLds_auto = MWaves == 1 ? false : true;
// If true, LDS is used unconditionally
static constexpr auto AEnableLds_manu = true;
static constexpr auto BEnableLds_manu = true;
static constexpr auto AEnableLds_manu = false;
static constexpr auto BEnableLds_manu = false;
static constexpr auto AEnableLds = AEnableLds_auto || AEnableLds_manu || (NumPrefetch > 1);
static constexpr auto BEnableLds = BEnableLds_auto || BEnableLds_manu || (NumPrefetch > 1);
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment