[Mesa-dev] [PATCH 27/95] i965/vec4: make opt_vector_float ignore doubles

Iago Toral Quiroga itoral at igalia.com
Tue Jul 19 10:40:24 UTC 2016


The pass does not support doubles in its current form. I'm not even sure that
it should, since it would basically change the type of the operation and that
could have implications for things like SSBO writes, etc.
---
 src/mesa/drivers/dri/i965/brw_vec4.cpp | 1 +
 1 file changed, 1 insertion(+)

diff --git a/src/mesa/drivers/dri/i965/brw_vec4.cpp b/src/mesa/drivers/dri/i965/brw_vec4.cpp
index 05109a4..d806f41 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4.cpp
@@ -382,6 +382,7 @@ vec4_visitor::opt_vector_float()
           inst->src[0].file == IMM &&
           inst->predicate == BRW_PREDICATE_NONE &&
           inst->dst.writemask != WRITEMASK_XYZW &&
+          type_sz(inst->src[0].type) < 8 &&
           (inst->src[0].type == inst->dst.type || inst->src[0].d == 0)) {
 
          vf = brw_float_to_vf(inst->src[0].d);
-- 
2.7.4



More information about the mesa-dev mailing list