|
@@ -67,7 +67,7 @@ able to submit and complete data transfers while kernels are executing, instead
|
|
|
kernel submission. The kernel just has to make sure that StarPU can use the
|
|
kernel submission. The kernel just has to make sure that StarPU can use the
|
|
|
local stream to synchronize with the kernel startup and completion.
|
|
local stream to synchronize with the kernel startup and completion.
|
|
|
|
|
|
|
|
-Using the STARPU_CUDA_ASYNC flag also permits to enabled concurrent kernel
|
|
|
|
|
|
|
+Using the STARPU_CUDA_ASYNC flag also permits to enable concurrent kernel
|
|
|
execution, on cards which support it (Kepler and later, notably). This is
|
|
execution, on cards which support it (Kepler and later, notably). This is
|
|
|
enabled by setting the STARPU_NWORKER_PER_CUDA environment variable to the
|
|
enabled by setting the STARPU_NWORKER_PER_CUDA environment variable to the
|
|
|
number of kernels to execute concurrently. This is useful when kernels are
|
|
number of kernels to execute concurrently. This is useful when kernels are
|
