Ran
|
Files
151
|
Run time
4s
|
Badge
Embed ▾
README BADGES
|
push
github
llvm/execution/cuda: Always use pycuda ArgumentHandler as cached buffer (#3010) Only the ArgumentHandler class provides the .array member that is used to check if a gpu_buffer is not stale. Fixes: 36e52b8ce ("llvm/execution/cuda: Use numpy argument handlers to access compiled structures") Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
11624 of 14851 branches covered (78.27%)
Branch coverage included in aggregate %.
31798 of 36717 relevant lines covered (86.6%)
0.87 hits per line
Coverage | ∆ | File | Lines | Relevant | Covered | Missed | Hits/Line | Branch Hits | Branch Misses |
---|