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:
Andy li
2024-03-09 07:17:53 +08:00
committed by GitHub
parent 2354601589
commit e373bd44bf
29 changed files with 1243 additions and 48 deletions
@@ -26,7 +26,9 @@ __global__ void MSCCL_KERNEL_ENTRY_NAME(devredop, type, proto, fullOps)(struct n
MSCCL_DECL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, half, fullOps) \
MSCCL_DECL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, float, fullOps) \
MSCCL_DECL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, double, fullOps) \
MSCCL_DECL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, rccl_bfloat16, fullOps)
MSCCL_DECL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, rccl_bfloat16, fullOps) \
MSCCL_DECL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, rccl_float8, fullOps) \
MSCCL_DECL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, rccl_bfloat8, fullOps)
#define MSCCL_DECL_KERNEL_ENTRY_FUNC_DEVREDOP_NOFLOAT(devredop, fullOps) \
MSCCL_DECL_KERNEL_ENTRY_FUNC_DEVREDOP_TYPE(devredop, int8_t, fullOps) \