OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

i965: Make brw_reg_from_fs_reg() halve exec_size when compressed.

Browse Source 
In a5d7e144ea, Connor generalized the
exec_size halving code to handle more cases.  As part of this, he made
it not halve anything if the region accessed falls completely in a
single register.

Unfortunately, it started producing some invalid regions:

-add(16)  g6<1>F  g10<8,8,1>UW    -g1<0,1,0>F    { align1 compr };
-add(16)  g8<1>F  g12<8,8,1>UW    -g1.1<0,1,0>F  { align1 compr };
+add(16)  g6<1>F  g10<16,16,1>UW  -g1<0,1,0>F    { align1 compr };
+add(16)  g8<1>F  g12<16,16,1>UW  -g1.1<0,1,0>F  { align1 compr };

Here, the UW source region completely fits within a register.  However,
we have to use instruction compression because the destination region
spans two registers.  <16,16,1> is invalid because it's compressed.

To handle this, skip the "everything fits in one register" case and
fall through to the exec_size halving case when compressed.

Fixes hundreds of Piglit regressions on GM965.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=95370
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
This commit is contained in:
Kenneth Graunke
2016-05-12 23:04:10 -07:00
parent 062ad81669
commit dc657a8201
1 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/mesa/drivers/dri/i965/brw_fs_generator.cpp
View File

@@ -54,7 +54,8 @@ brw_file_from_reg(fs_reg *reg)
}
static struct brw_reg
brw_reg_from_fs_reg(fs_inst *inst, fs_reg *reg, unsigned gen)
brw_reg_from_fs_reg(const struct brw_codegen *p,
fs_inst *inst, fs_reg *reg, unsigned gen)
{
struct brw_reg brw_reg;
@@ -65,7 +66,8 @@ brw_reg_from_fs_reg(fs_inst *inst, fs_reg *reg, unsigned gen)
case VGRF:
if (reg->stride == 0) {
brw_reg = brw_vec1_reg(brw_file_from_reg(reg), reg->nr, 0);
} else if (inst->exec_size * reg->stride * type_sz(reg->type) <= 32) {
} else if (!p->compressed &&
inst->exec_size * reg->stride * type_sz(reg->type) <= 32) {
brw_reg = brw_vecn_reg(inst->exec_size, brw_file_from_reg(reg),
reg->nr, 0);
brw_reg = stride(brw_reg, inst->exec_size * reg->stride,
@@ -1763,7 +1765,7 @@ fs_generator::generate_code(const cfg_t *cfg, int dispatch_width)
}
for (unsigned int i = 0; i < inst->sources; i++) {
src[i] = brw_reg_from_fs_reg(inst, &inst->src[i], devinfo->gen);
src[i] = brw_reg_from_fs_reg(p, inst, &inst->src[i], devinfo->gen);
/* The accumulator result appears to get used for the
* conditional modifier generation. When negating a UD
@@ -1775,7 +1777,7 @@ fs_generator::generate_code(const cfg_t *cfg, int dispatch_width)
inst->src[i].type != BRW_REGISTER_TYPE_UD ||
!inst->src[i].negate);
}
dst = brw_reg_from_fs_reg(inst, &inst->dst, devinfo->gen);
dst = brw_reg_from_fs_reg(p, inst, &inst->dst, devinfo->gen);
brw_set_default_predicate_control(p, inst->predicate);
brw_set_default_predicate_inverse(p, inst->predicate_inverse);