Skip to content

GitLab

"git@developer.sourcefind.cn:OpenDAS/megatron-lm.git" did not exist on "3b29f0e79d48a531a93c769f0a928bf13847e853"
Unverified Commit ff24b537 authored by Jun Liu's avatar Jun Liu Committed by GitHub
Browse files

[SWDEV-435347] disable instances failed with mainlien compiler (#1077)

parent afe46220
Hide whitespace changes
Inline Side-by-side
Showing with 60 additions and 56 deletions
library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward_scaleadd_ab.hpp
View file @ ff24b537
......@@ -23,19 +23,20 @@ using ScaleAdd = ck::tensor_operation::element_wise::ScaleAdd;
#ifdef CK_ENABLE_BF16
// grouped conv3d forward multi AB scaleadd, NDHWGC/GKZYXC/NDHWGK
void add_device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
NDHWGC,
GKZYXC,
ck::Tuple<>,
NDHWGK,
ck::Tuple<BF16, BF16>,
ck::Tuple<BF16, BF16>,
ck::Tuple<>,
BF16,
ScaleAdd,
ScaleAdd,
PassThrough>>>& instances);
// TODO: Workaround for https://ontrack-internal.amd.com/browse/SWDEV-435347
// void add_device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
// std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
// NDHWGC,
// GKZYXC,
// ck::Tuple<>,
// NDHWGK,
// ck::Tuple<BF16, BF16>,
// ck::Tuple<BF16, BF16>,
// ck::Tuple<>,
// BF16,
// ScaleAdd,
// ScaleAdd,
// PassThrough>>>& instances);
#endif
#ifdef CK_ENABLE_FP16
......@@ -151,13 +152,15 @@ struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGroupe
}
#endif
#ifdef CK_ENABLE_BF16
if constexpr(is_same_v<InDataType, ck::Tuple<ck::bhalf_t, ck::bhalf_t>> &&
is_same_v<WeiDataType, ck::Tuple<ck::bhalf_t, ck::bhalf_t>> &&
is_same_v<OutDataType, ck::bhalf_t> && is_same_v<ComputeType, ck::bhalf_t>)
{
add_device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
op_ptrs);
}
// TODO: Workaround for https://ontrack-internal.amd.com/browse/SWDEV-435347
// if constexpr(is_same_v<InDataType, ck::Tuple<ck::bhalf_t, ck::bhalf_t>> &&
// is_same_v<WeiDataType, ck::Tuple<ck::bhalf_t, ck::bhalf_t>> &&
// is_same_v<OutDataType, ck::bhalf_t> && is_same_v<ComputeType,
// ck::bhalf_t>)
// {
// add_device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
// op_ptrs);
// }
#endif
#ifdef CK_ENABLE_INT8
if constexpr(is_same_v<InDataType, ck::Tuple<int8_t, int8_t>> &&
......
library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_scaleadd_ab/xdl/device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
View file @ ff24b537
......@@ -9,42 +9,43 @@ namespace tensor_operation {
namespace device {
namespace instance {
void add_device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
NDHWGC,
GKZYXC,
ck::Tuple<>,
NDHWGK,
ck::Tuple<BF16, BF16>,
ck::Tuple<BF16, BF16>,
ck::Tuple<>,
BF16,
ScaleAdd,
ScaleAdd,
PassThrough>>>& instances)
{
add_device_operation_instances(
instances,
device_grouped_conv_fwd_xdl_scaleadd_ab_bf16_instances<3,
NDHWGC,
GKZYXC,
NDHWGK,
ConvFwdDefault>{});
add_device_operation_instances(
instances,
device_grouped_conv_fwd_xdl_scaleadd_ab_bf16_instances<3,
NDHWGC,
GKZYXC,
NDHWGK,
ConvFwd1x1P0>{});
add_device_operation_instances(
instances,
device_grouped_conv_fwd_xdl_scaleadd_ab_bf16_instances<3,
NDHWGC,
GKZYXC,
NDHWGK,
ConvFwd1x1S1P0>{});
}
// TODO: Workaround for https://ontrack-internal.amd.com/browse/SWDEV-435347
// void add_device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
// std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
// NDHWGC,
// GKZYXC,
// ck::Tuple<>,
// NDHWGK,
// ck::Tuple<BF16, BF16>,
// ck::Tuple<BF16, BF16>,
// ck::Tuple<>,
// BF16,
// ScaleAdd,
// ScaleAdd,
// PassThrough>>>& instances)
// {
// add_device_operation_instances(
// instances,
// device_grouped_conv_fwd_xdl_scaleadd_ab_bf16_instances<3,
// NDHWGC,
// GKZYXC,
// NDHWGK,
// ConvFwdDefault>{});
// add_device_operation_instances(
// instances,
// device_grouped_conv_fwd_xdl_scaleadd_ab_bf16_instances<3,
// NDHWGC,
// GKZYXC,
// NDHWGK,
// ConvFwd1x1P0>{});
// add_device_operation_instances(
// instances,
// device_grouped_conv_fwd_xdl_scaleadd_ab_bf16_instances<3,
// NDHWGC,
// GKZYXC,
// NDHWGK,
// ConvFwd1x1S1P0>{});
// }
} // namespace instance
} // namespace device
......
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