search for: task_wait

...exactly as in Hal's proposal). Serial blocks reduce to a block conditional on the index inside the function being parallelly mapped. We lower critical and ordered regions into calls to `sync_region`. Tasks are lowered (recursively) this way: ``` TASK block more_code_may_contain_more_tasks TASK_WAIT ``` desugars to ``` @llvm.parallel_map(2, task_closure, task_priv) void task_closure(i32 index, i8* private) { if (index == 0) { more_code_may_contain_more_tasks } else { block } } ``` Parallel loops are basically `parallel_map`s. Thoughts? [1] http://lists.cs.uiuc.edu/pipermail...

On Tue, 14 Aug 2012 10:22:35 +0300 Pekka Jääskeläinen <pekka.jaaskelainen at tut.fi> wrote: > On 08/13/2012 10:54 PM, Hal Finkel wrote: > > I had thought about uses for shared-memory OpenCL implementations, > > but I don't know enough about the use cases to make a specific > > proposal. Is your metadata documented anywhere? > > It is now a quick "brute

...exactly as in Hal's proposal). Serial blocks reduce to a block conditional on the index inside the function being parallelly mapped. We lower critical and ordered regions into calls to `sync_region`. Tasks are lowered (recursively) this way: ``` TASK block more_code_may_contain_more_tasks TASK_WAIT ``` desugars to ``` @llvm.parallel_map(2, task_closure, task_priv) void task_closure(i32 index, i8* private) { if (index == 0) { more_code_may_contain_more_tasks } else { block } } ``` Parallel loops are basically `parallel_map`s. Thoughts? [1] http://lists.cs.uiuc.edu/pipermail...