summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorKenneth Graunke <kenneth@whitecape.org>2012-01-26 05:38:28 -0800
committerIan Romanick <ian.d.romanick@intel.com>2012-01-27 18:02:43 -0800
commit4aa158d09aab294845d33027dc1ef42056dec90a (patch)
treeaabb598fc07ab1120eedfa90c36b70728b13129d
parent38b76cf8319168c3628cc18c6231e9a081a2481b (diff)
i965/vs: Use the sampler for VS pull constant loading on Ivybridge.
Substantially increases performance in GLBenchmark PRO: - 320x240 => 3.28x - 1920x1080 => 1.47x - 2560x1440 => 1.27x The LD message ignores the sampler unit index and SAMPLER_STATE pointer, instead relying on hard-wired default state. Thus, there's no need to worry about running out of sampler units or providing SAMPLER_STATE; this small patch should be all that's required. NOTE: This is a candidate for release branches. (It requires the preceding commit to compile.) Signed-off-by: Kenneth Graunke <kenneth@whitecape.org> Reviewed-by: Eric Anholt <eric@anholt.net> (cherry picked from commit 259b65e2e7938de4aab323033cfe2b33369ddb07)
-rw-r--r--src/mesa/drivers/dri/i965/brw_vec4_emit.cpp17
1 files changed, 17 insertions, 0 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_emit.cpp b/src/mesa/drivers/dri/i965/brw_vec4_emit.cpp
index dbe4dd093dd..917c927a125 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_emit.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_emit.cpp
@@ -647,6 +647,23 @@ vec4_visitor::generate_pull_constant_load(vec4_instruction *inst,
struct brw_reg dst,
struct brw_reg index)
{
+ if (intel->gen == 7) {
+ gen6_resolve_implied_move(p, &index, inst->base_mrf);
+ brw_instruction *insn = brw_next_insn(p, BRW_OPCODE_SEND);
+ brw_set_dest(p, insn, dst);
+ brw_set_src0(p, insn, index);
+ brw_set_sampler_message(p, insn,
+ SURF_INDEX_VERT_CONST_BUFFER,
+ 0, /* LD message ignores sampler unit */
+ GEN5_SAMPLER_MESSAGE_SAMPLE_LD,
+ 1, /* rlen */
+ 1, /* mlen */
+ false, /* no header */
+ BRW_SAMPLER_SIMD_MODE_SIMD4X2,
+ 0);
+ return;
+ }
+
struct brw_reg header = brw_vec8_grf(0, 0);
gen6_resolve_implied_move(p, &header, inst->base_mrf);