1.3.2 release

Broadcast tuning
Better checking of inputs
Copy/reduce code simplification


[ROCm/rccl commit: 34d27771c6]
This commit is contained in:
Sylvain Jeaugey
2016-12-01 15:17:50 -08:00
parent 9ec80e0873
commit db3103d96a
10 changed files with 120 additions and 279 deletions
+1 -1
View File
@@ -52,7 +52,7 @@ endif
NCCL_MAJOR := 1
NCCL_MINOR := 3
NCCL_PATCH := 1
NCCL_PATCH := 2
CXXFLAGS += -DNCCL_MAJOR=$(NCCL_MAJOR) -DNCCL_MINOR=$(NCCL_MINOR) -DNCCL_PATCH=$(NCCL_PATCH)
CUDA_VERSION ?= $(shell ls $(CUDA_LIB)/libcudart.so.* | head -1 | rev | cut -d "." -f -2 | rev)