diff options
| author | Matt Turner <mattst88@gmail.com> | 2015-10-20 18:23:50 -0700 |
|---|---|---|
| committer | Matt Turner <mattst88@gmail.com> | 2015-10-22 12:26:54 -0700 |
| commit | e2344e11ce8ddefb89a222bbf63a7c60e8ba5655 (patch) | |
| tree | 58767764343979f84c76741d2fcccca815020ce9 | |
| parent | e10fc055e7dc5281f03a77088a24392098e3473b (diff) | |
i965/fs: Trim unneeded channels in SampleID setup.
The AND and SHR produce a scalar value that we had been replicating
across $dispatch_width channels. The immediate MOV produces only four
useful channels of data.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Anuj Phogat <anuj.phogat@gmail.com>
| -rw-r--r-- | src/mesa/drivers/dri/i965/brw_fs.cpp | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp index 3cb8190b02a..71da9d9f7b6 100644 --- a/src/mesa/drivers/dri/i965/brw_fs.cpp +++ b/src/mesa/drivers/dri/i965/brw_fs.cpp @@ -1282,9 +1282,9 @@ fs_visitor::emit_sampleid_setup() fs_reg *reg = new(this->mem_ctx) fs_reg(vgrf(glsl_type::int_type)); if (key->compute_sample_id) { - fs_reg t1 = vgrf(glsl_type::int_type); - fs_reg t2 = vgrf(glsl_type::int_type); - t2.type = BRW_REGISTER_TYPE_W; + fs_reg t1(GRF, alloc.allocate(1), BRW_REGISTER_TYPE_D); + t1.set_smear(0); + fs_reg t2(GRF, alloc.allocate(1), BRW_REGISTER_TYPE_W); /* The PS will be run in MSDISPMODE_PERSAMPLE. For example with * 8x multisampling, subspan 0 will represent sample N (where N @@ -1305,13 +1305,13 @@ fs_visitor::emit_sampleid_setup() * are sample 1 of subspan 0; the third group is sample 0 of * subspan 1, and finally sample 1 of subspan 1. */ - abld.exec_all() + abld.exec_all().group(1, 0) .AND(t1, fs_reg(retype(brw_vec1_grf(0, 0), BRW_REGISTER_TYPE_D)), fs_reg(0xc0)); - abld.exec_all().SHR(t1, t1, fs_reg(5)); + abld.exec_all().group(1, 0).SHR(t1, t1, fs_reg(5)); /* This works for both SIMD8 and SIMD16 */ - abld.exec_all() + abld.exec_all().group(4, 0) .MOV(t2, brw_imm_v(key->persample_2x ? 0x1010 : 0x3210)); /* This special instruction takes care of setting vstride=1, |