i965: Drop perf_debug about rasterizer discard in SOL vs. clipper.

I recently experimented with performing rasterizer discard in the SOL
unit instead of the clipper, and as far as I can tell, it's basically
the same performance.  The clipper comes directly after SOL anyway,
and setting the clipper to REJECT_ALL should be pretty darn cheap.

Keep the perf_debug on Sandybridge, where the GS actually does work.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
This commit is contained in:
Kenneth Graunke 2016-05-10 17:54:45 -07:00
parent 32b1c0b694
commit 1f9445ff57

View file

@ -165,9 +165,11 @@ upload_clip_state(struct brw_context *brw)
/* BRW_NEW_RASTERIZER_DISCARD */ /* BRW_NEW_RASTERIZER_DISCARD */
if (ctx->RasterDiscard) { if (ctx->RasterDiscard) {
dw2 |= GEN6_CLIP_MODE_REJECT_ALL; dw2 |= GEN6_CLIP_MODE_REJECT_ALL;
perf_debug("Rasterizer discard is currently implemented via the clipper; " if (brw->gen == 6) {
"%s be faster.\n", brw->gen >= 7 ? "using the SOL unit may" : perf_debug("Rasterizer discard is currently implemented via the "
"having the GS not write primitives would likely"); "clipper; having the GS not write primitives would "
"likely be faster.\n");
}
} }
uint32_t enable; uint32_t enable;