Enable fp8 support (#1101)
* initial checkin
* resolve cr comments
* resolve the build issue
* fix the data correctless issue
* update fp8 header file and update the unit test for fp8 support
* remove fp16 from fp8 headers
* fix ut issue and catch up the latest code from develop
* udate according to cr comments
* update ut according to cr comments
* update num floats for each SumPostDiv from 4 to 6
* update fp8 header file name
* fix the typo
[ROCm/rccl commit: 6777e65c1d]
This commit is contained in:
@@ -414,7 +414,9 @@ __global__ void MSCCL_KERNEL_ENTRY_NAME(devredop, type, Simple, fullOps)(struct
|
||||
MSCCL_IMPL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, half, fullOps) \
|
||||
MSCCL_IMPL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, float, fullOps) \
|
||||
MSCCL_IMPL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, double, fullOps) \
|
||||
MSCCL_IMPL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, rccl_bfloat16, fullOps)
|
||||
MSCCL_IMPL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, rccl_bfloat16, fullOps) \
|
||||
MSCCL_IMPL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, rccl_float8, fullOps) \
|
||||
MSCCL_IMPL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, rccl_bfloat8, fullOps)
|
||||
|
||||
#define MSCCL_IMPL_KERNEL_ENTRY_FUNC_DEVREDOP_NOFLOAT(devredop, fullOps) \
|
||||
MSCCL_IMPL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, int8_t, fullOps) \
|
||||
|
||||
Referens i nytt ärende
Block a user