diff options
| author | Francisco Jerez <currojerez@riseup.net> | 2015-11-23 19:18:26 +0200 |
|---|---|---|
| committer | Francisco Jerez <currojerez@riseup.net> | 2015-11-26 14:07:58 +0200 |
| commit | 55ffa64daf765b1229364518106a4124bd84b9a7 (patch) | |
| tree | bbc31d37dc2eebaf480f08a1b3ba55ba4162d9f7 /src/mesa/drivers/dri/i965/brw_eu.h | |
| parent | bc8182808aea111aea3cfcba4da3dd861689d890 (diff) | |
| download | external_mesa3d-55ffa64daf765b1229364518106a4124bd84b9a7.zip external_mesa3d-55ffa64daf765b1229364518106a4124bd84b9a7.tar.gz external_mesa3d-55ffa64daf765b1229364518106a4124bd84b9a7.tar.bz2 | |
i965/gen9+: Switch thread scratch space to non-coherent stateless access.
The thread scratch space is thread-local so using the full IA-coherent
stateless surface index (255 since Gen8) is unnecessary and
potentially expensive. On Gen8 and early steppings of Gen9 this is
not a functional change because the kernel already sets bit 4 of
HDC_CHICKEN0 which overrides all HDC memory access to be non-coherent
in order to workaround a hardware bug.
This happens to fix a full system hang when running any spilling code
on a pre-production SKL GT4e machine I have on my desk (forcing all
HDC access to non-coherent from the kernel up to stepping F0 might be
a good idea though regardless of this patch), and improves performance
of the OglPSBump2 SynMark benchmark run with INTEL_DEBUG=spill_fs by
33% (11 runs, 5% significance) on a production SKL GT2 (on which HDC
IA-coherency is apparently functional so it wouldn't make sense to
disable globally).
Reviewed-by: Kristian Høgsberg <krh@bitplanet.net>
Diffstat (limited to 'src/mesa/drivers/dri/i965/brw_eu.h')
| -rw-r--r-- | src/mesa/drivers/dri/i965/brw_eu.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_eu.h b/src/mesa/drivers/dri/i965/brw_eu.h index ef94347..686b42b 100644 --- a/src/mesa/drivers/dri/i965/brw_eu.h +++ b/src/mesa/drivers/dri/i965/brw_eu.h @@ -315,6 +315,8 @@ void brw_oword_block_read(struct brw_codegen *p, uint32_t offset, uint32_t bind_table_index); +unsigned brw_scratch_surface_idx(const struct brw_codegen *p); + void brw_oword_block_read_scratch(struct brw_codegen *p, struct brw_reg dest, struct brw_reg mrf, |