summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorEric Anholt <[email protected]>2015-02-06 16:24:36 -0800
committerEric Anholt <[email protected]>2015-08-14 11:39:18 -0700
commita6e75e3cd74fd60200cc8dddc672a2d88495eb06 (patch)
treea780ee18da9628394dbc51d3f67cf527a2857edc
parentfb2425a641dd7f891964e6f51b10cce63dff7d2c (diff)
nir: Add support for CSE on textures.
NIR instruction count results on i965: total instructions in shared programs: 1261954 -> 1261937 (-0.00%) instructions in affected programs: 455 -> 438 (-3.74%) One in yofrankie, two in tropics. Apparently i965 had also optimized all of these out anyway. Reviewed-by: Kenneth Graunke <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
-rw-r--r--src/glsl/nir/nir_opt_cse.c43
1 files changed, 39 insertions, 4 deletions
diff --git a/src/glsl/nir/nir_opt_cse.c b/src/glsl/nir/nir_opt_cse.c
index 553906e1291..864795ce5ed 100644
--- a/src/glsl/nir/nir_opt_cse.c
+++ b/src/glsl/nir/nir_opt_cse.c
@@ -86,8 +86,41 @@ nir_instrs_equal(nir_instr *instr1, nir_instr *instr2)
}
return true;
}
- case nir_instr_type_tex:
- return false;
+ case nir_instr_type_tex: {
+ nir_tex_instr *tex1 = nir_instr_as_tex(instr1);
+ nir_tex_instr *tex2 = nir_instr_as_tex(instr2);
+
+ if (tex1->op != tex2->op)
+ return false;
+
+ if (tex1->num_srcs != tex2->num_srcs)
+ return false;
+ for (unsigned i = 0; i < tex1->num_srcs; i++) {
+ if (tex1->src[i].src_type != tex2->src[i].src_type ||
+ !nir_srcs_equal(tex1->src[i].src, tex2->src[i].src)) {
+ return false;
+ }
+ }
+
+ if (tex1->coord_components != tex2->coord_components ||
+ tex1->sampler_dim != tex2->sampler_dim ||
+ tex1->is_array != tex2->is_array ||
+ tex1->is_shadow != tex2->is_shadow ||
+ tex1->is_new_style_shadow != tex2->is_new_style_shadow ||
+ memcmp(tex1->const_offset, tex2->const_offset,
+ sizeof(tex1->const_offset)) != 0 ||
+ tex1->component != tex2->component ||
+ tex1->sampler_index != tex2->sampler_index ||
+ tex1->sampler_array_size != tex2->sampler_array_size) {
+ return false;
+ }
+
+ /* Don't support un-lowered sampler derefs currently. */
+ if (tex1->sampler || tex2->sampler)
+ return false;
+
+ return true;
+ }
case nir_instr_type_load_const: {
nir_load_const_instr *load1 = nir_instr_as_load_const(instr1);
nir_load_const_instr *load2 = nir_instr_as_load_const(instr2);
@@ -181,11 +214,10 @@ nir_instr_can_cse(nir_instr *instr)
switch (instr->type) {
case nir_instr_type_alu:
+ case nir_instr_type_tex:
case nir_instr_type_load_const:
case nir_instr_type_phi:
return true;
- case nir_instr_type_tex:
- return false; /* TODO */
case nir_instr_type_intrinsic: {
const nir_intrinsic_info *info =
&nir_intrinsic_infos[nir_instr_as_intrinsic(instr)->intrinsic];
@@ -212,6 +244,9 @@ nir_instr_get_dest_ssa_def(nir_instr *instr)
case nir_instr_type_alu:
assert(nir_instr_as_alu(instr)->dest.dest.is_ssa);
return &nir_instr_as_alu(instr)->dest.dest.ssa;
+ case nir_instr_type_tex:
+ assert(nir_instr_as_tex(instr)->dest.is_ssa);
+ return &nir_instr_as_tex(instr)->dest.ssa;
case nir_instr_type_load_const:
return &nir_instr_as_load_const(instr)->def;
case nir_instr_type_phi: