diff options
author | Soumith Chintala <soumith@gmail.com> | 2017-07-20 18:01:52 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2017-07-20 18:01:52 +0300 |
commit | e9d54e162b3628d5f8b4e4a0f6c2191f559ebc12 (patch) | |
tree | fe4619cb4ce405cb3b2dbde7130928b1930b44d2 | |
parent | a4381e1e4b2e07bfc5ecb73feab345ed8394fc04 (diff) | |
parent | 203a547198f6da67a6a1de7ec05c6985d9d04cf2 (diff) |
Merge pull request #478 from singam-sanjay/correct_README
Update README
-rw-r--r-- | README.md | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -87,7 +87,7 @@ local a = torch.CudaTensor(1000,1000):uniform() a:add(1) ``` ... the GPU kernel to add 1 will only be scheduled for launch by `a:add(1)`. It might not have completed yet, or -even have reached the GPU, at the time that the `a:add(1)` instructions has completed +even have reached the GPU, at the time that the `a:add(1)` returns * therefore for running wall-clock timings, you should call `cutorch.synchronize()` before each timecheck point: ```lua |