Transform
sqrt a, b
rcp c, a
into
sqrt a, b
rsq c, b
The improvement here is that we've broken a dependency between these
instructions. Leads to 330 fewer INV instructions and 330 more RSQ.
---
src/mesa/drivers/dri/i965/brw_fs.cpp | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp
b/src/mesa/drivers/dri/i965/brw_fs.cpp
index ffe8ba8..8241f67 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -2091,6 +2091,17 @@ fs_visitor::opt_algebraic()
}
}
break;
+ case SHADER_OPCODE_RCP: {
+ fs_inst *prev = (fs_inst *)inst->prev;
+ if (prev->opcode == SHADER_OPCODE_SQRT) {
+ if (inst->src[0].equals(prev->dst)) {
+ inst->opcode = SHADER_OPCODE_RSQ;
+ inst->src[0] = prev->src[0];
+ progress = true;
+ }
+ }
+ break;
+ }
default:
break;
}
--
1.8.5.5
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
