[Mesa-dev] [PATCH v2 21/52] intel/cs: Drop min_dispatch_width checks from compile_cs
Michael Schellenberger
mschellenbergercosta at googlemail.com
Fri Oct 13 09:54:12 UTC 2017
Hi Jason, you actually dropped max_dispatch_width so you might want to
update the commit message.
Michael
Am 13.10.2017 08:13 schrieb "Jason Ekstrand" <jason at jlekstrand.net>:
The only things that adjust min_dispatch_width are render target writes
which don't happen in compute shaders so they're pointless.
---
src/intel/compiler/brw_fs.cpp | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/src/intel/compiler/brw_fs.cpp b/src/intel/compiler/brw_fs.cpp
index 676496f..1a44d00 100644
--- a/src/intel/compiler/brw_fs.cpp
+++ b/src/intel/compiler/brw_fs.cpp
@@ -6816,8 +6816,7 @@ brw_compile_cs(const struct brw_compiler *compiler,
void *log_data,
NULL, /* Never used in core profile */
shader, 16, shader_time_index);
if (likely(!(INTEL_DEBUG & DEBUG_NO16)) &&
- !fail_msg && v8.max_dispatch_width >= 16 &&
- min_dispatch_width <= 16) {
+ !fail_msg && min_dispatch_width <= 16) {
/* Try a SIMD16 compile */
if (min_dispatch_width <= 8)
v16.import_uniforms(&v8);
@@ -6841,8 +6840,7 @@ brw_compile_cs(const struct brw_compiler *compiler,
void *log_data,
fs_visitor v32(compiler, log_data, mem_ctx, key, &prog_data->base,
NULL, /* Never used in core profile */
shader, 32, shader_time_index);
- if (!fail_msg && v8.max_dispatch_width >= 32 &&
- (min_dispatch_width > 16 || (INTEL_DEBUG & DEBUG_DO32))) {
+ if (!fail_msg && (min_dispatch_width > 16 || (INTEL_DEBUG &
DEBUG_DO32))) {
/* Try a SIMD32 compile */
if (min_dispatch_width <= 8)
v32.import_uniforms(&v8);
--
2.5.0.400.gff86faf
_______________________________________________
mesa-dev mailing list
mesa-dev at lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/mesa-dev/attachments/20171013/fe26b078/attachment.html>
More information about the mesa-dev
mailing list