Search found 6 matches

by xtian
Tue Sep 01, 2015 11:16 am
Forum: OpenMP 4.1 DRAFT - Public Comments
Topic: elemental functions
Replies: 4
Views: 24218

Re: elemental functions

The declare simd directive should be allowed in the pure/elemental function.
by xtian
Wed Mar 04, 2015 1:57 pm
Forum: Using OpenMP
Topic: OMP SIMD on GPU
Replies: 2
Views: 4678

Re: OMP SIMD on GPU

GPU's cores are handling a separate thread each. Threads are combined in groups of 32 threads (a single warp), and assigned to 32 cores for the purpose of the execution of a single instruction. But a SIMD is a subthreading term, meaning a single core should have a vector register, and be able to han...
by xtian
Wed Apr 24, 2013 5:05 pm
Forum: OpenMP 4.0 Public Review Release Candidates
Topic: #pragma omp simd
Replies: 4
Views: 23699

Re: #pragma omp simd

>>>>>>>>Is it intentional that there is nothing that talks about the list items mentioned in aligned clauses causing implicit reference in outer constructs (if any)? It makes sense, just wanted to make it clear that it is expected that if aligned clause mentions any variables that aren't actually us...
by xtian
Wed Apr 24, 2013 4:48 pm
Forum: OpenMP 4.0 Public Review Release Candidates
Topic: linear clause issues
Replies: 8
Views: 28826

Re: linear clause issues

J, N, O are not linear w.r.t to I-loop, J, N, O are private w.r.t to I-loop.
by xtian
Sat Apr 06, 2013 2:08 pm
Forum: OpenMP 4.0 Public Review Release Candidates
Topic: #pragma omp simd
Replies: 4
Views: 23699

Re: #pragma omp simd

We will clarify taht what can be specified in "align" clause. The "align" clause applys to "memory address", e.g. *p, a[100]; align(p:64), align(a:4). Note that, OpenMP does not allow &p or &a[0] in the clause.
by xtian
Sat Apr 06, 2013 2:03 pm
Forum: OpenMP 4.0 Public Review Release Candidates
Topic: #pragma omp simd
Replies: 4
Views: 23699

Re: #pragma omp simd

If the safelen is not specified, it implies the safelen = N, programmers need to make sure the entire loop is vectoriable (i.e. no loop-carried lexical backward dependency).