This avoids emitting a few extra instructions required to take the
dispatch mask into account when it's known to be tightly packed.
---
src/mesa/drivers/dri/i965/brw_fs_generator.cpp | 4 +++-
src/mesa/drivers/dri/i965/brw_vec4_generator.cpp | 8 ++++++--
2 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
index c510f42..bdeda3b 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
@@ -2045,7 +2045,9 @@ fs_generator::generate_code(const cfg_t *cfg, int
dispatch_width)
case SHADER_OPCODE_FIND_LIVE_CHANNEL: {
const struct brw_reg mask =
- stage == MESA_SHADER_FRAGMENT ? brw_vmask_reg() : brw_dmask_reg();
+ brw_stage_has_packed_dispatch(stage, prog_data) ? brw_imm_ud(~0u) :
+ stage == MESA_SHADER_FRAGMENT ? brw_vmask_reg() :
+ brw_dmask_reg();
brw_find_live_channel(p, dst, mask);
break;
}
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
b/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
index f9e6d1c..2bef549 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
@@ -1862,9 +1862,13 @@ generate_code(struct brw_codegen *p,
brw_memory_fence(p, dst);
break;
- case SHADER_OPCODE_FIND_LIVE_CHANNEL:
- brw_find_live_channel(p, dst, brw_dmask_reg());
+ case SHADER_OPCODE_FIND_LIVE_CHANNEL: {
+ const struct brw_reg mask =
+ brw_stage_has_packed_dispatch(nir->stage, &prog_data->base) ?
+ brw_imm_ud(~0u) : brw_dmask_reg();
+ brw_find_live_channel(p, dst, mask);
break;
+ }
case SHADER_OPCODE_BROADCAST:
assert(inst->force_writemask_all);
--
2.9.0
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
