aboutsummaryrefslogtreecommitdiffstats
path: root/src/mesa/drivers/dri/i965/brw_fs.cpp
diff options
context:
space:
mode:
authorFrancisco Jerez <[email protected]>2015-07-27 18:42:31 +0300
committerFrancisco Jerez <[email protected]>2015-07-29 19:30:11 +0300
commit4529916dfd227af6c4e151f45261db22157fe45f (patch)
tree59826f327c1db978a8a0a946b81915e24987b212 /src/mesa/drivers/dri/i965/brw_fs.cpp
parenteaba922582cfdccc7b198f9b23d8bd3c26197d03 (diff)
i965/fs: Don't set exec_all on instructions wider than the original in lower_simd_width.
This could have led to somewhat increased bandwidth usage for lowered texturing instructions on Gen4 (which is the only case in which lower_width may be greater than inst->exec_size). After the previous patches the invariant mentioned in the comment should no longer be assumed by any of the other optimization and lowering passes, so the exec_all() call shouldn't be necessary anymore. Reviewed-by: Jason Ekstrand <[email protected]>
Diffstat (limited to 'src/mesa/drivers/dri/i965/brw_fs.cpp')
-rw-r--r--src/mesa/drivers/dri/i965/brw_fs.cpp20
1 files changed, 11 insertions, 9 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index 57e4dd783ea..4947f24dc44 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -4163,10 +4163,15 @@ fs_visitor::lower_simd_width()
const unsigned lower_width = get_lowered_simd_width(devinfo, inst);
if (lower_width != inst->exec_size) {
- /* Builder matching the original instruction. */
+ /* Builder matching the original instruction. We may also need to
+ * emit an instruction of width larger than the original, set the
+ * execution size of the builder to the highest of both for now so
+ * we're sure that both cases can be handled.
+ */
const fs_builder ibld = bld.at(block, inst)
.exec_all(inst->force_writemask_all)
- .group(inst->exec_size, inst->force_sechalf);
+ .group(MAX2(inst->exec_size, lower_width),
+ inst->force_sechalf);
/* Split the copies in chunks of the execution width of either the
* original or the lowered instruction, whichever is lower.
@@ -4189,14 +4194,11 @@ fs_visitor::lower_simd_width()
split_inst.exec_size = lower_width;
split_inst.eot = inst->eot && i == n - 1;
- /* Set exec_all if the lowered width is higher than the original
- * to avoid breaking the compiler invariant that no control
- * flow-masked instruction is wider than the shader's
- * dispatch_width. Then transform the sources and destination and
- * emit the lowered instruction.
+ /* Select the correct channel enables for the i-th group, then
+ * transform the sources and destination and emit the lowered
+ * instruction.
*/
- const fs_builder lbld = ibld.exec_all(lower_width > inst->exec_size)
- .group(lower_width, i);
+ const fs_builder lbld = ibld.group(lower_width, i);
for (unsigned j = 0; j < inst->sources; j++) {
if (inst->src[j].file != BAD_FILE &&