Jordan Justen <[email protected]> writes: > On 2016-05-26 20:46:29, Francisco Jerez wrote: >> This should have the side effect of enabling the ARB_compute_shader >> extension on Gen8+ hardware and all Gen7 platforms that didn't >> previously expose it (VLV and IVB GT1) due to the number of hardware >> threads per subslice being insufficient in SIMD16 mode. >> --- >> src/mesa/drivers/dri/i965/brw_context.c | 2 +- >> 1 file changed, 1 insertion(+), 1 deletion(-) >> >> diff --git a/src/mesa/drivers/dri/i965/brw_context.c >> b/src/mesa/drivers/dri/i965/brw_context.c >> index 1ab02ae..1121728 100644 >> --- a/src/mesa/drivers/dri/i965/brw_context.c >> +++ b/src/mesa/drivers/dri/i965/brw_context.c >> @@ -717,7 +717,7 @@ brw_initialize_cs_context_constants(struct brw_context >> *brw, unsigned max_thread >> * is not always true. This allows us to run more test cases, and will be >> * required based on desktop GL compute shader requirements. >> */ >> - const int simd_size = ctx->API == API_OPENGL_CORE ? 16 : 8; >> + const int simd_size = ctx->API == API_OPENGL_CORE ? 32 : 8; > > The only reason I put 8 for ES was some lingering doubts about no16() > back then. Maybe we can just use 32 in the calculation now. > Yeah, that would make sense. These days the only no16() calls left in the back-end are fragment shader-specific, I think it should be safe to bump the workgroup size limit for GLES too -- I'll do that, update the comment above and add your R-b.
> Or, maybe just set max_invocations below to 1024 or 128 based on the > API. > > Any of these seem fine to me, > > Reviewed-by: Jordan Justen <[email protected]> > Thanks! >> >> const uint32_t max_invocations = simd_size * max_threads; >> ctx->Const.MaxComputeWorkGroupSize[0] = max_invocations; >> -- >> 2.7.3 >> >> _______________________________________________ >> mesa-dev mailing list >> [email protected] >> https://lists.freedesktop.org/mailman/listinfo/mesa-dev
signature.asc
Description: PGP signature
_______________________________________________ mesa-dev mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/mesa-dev
