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

intel/fs: Add support for copy-propagating a block of multiple FIXED_GRFs.

Browse Source 
In cases where a LOAD_PAYLOAD instruction copies a single block of
sequential GRF registers into the destination (see
is_identity_payload()), splitting the block copy into a number of ACP
entries (one for each LOAD_PAYLOAD source) is undesirable, because
that prevents copy propagation into any instructions which read
multiple components at once with the same source (the barycentric
source of the LINTERP instruction is going to be the overwhelmingly
most common example).

Technically it would also be possible to do this for VGRF sources, but
there is little benefit from that since register coalesce already
covers many of those cases -- There is no way for a block of
FIXED_GRFs to be coalesced into a VGRF though.

This prevents the following shader-db regressions (including SIMD32
programs) in combination with the interpolation rework part of this
series.  On SKL:

   total instructions in shared programs: 18595160 -> 18828562 (1.26%)
   instructions in affected programs: 13374946 -> 13608348 (1.75%)
   helped: 7
   HURT: 108977

   total spills in shared programs: 9116 -> 9106 (-0.11%)
   spills in affected programs: 404 -> 394 (-2.48%)
   helped: 7
   HURT: 9

   total fills in shared programs: 8994 -> 9176 (2.02%)
   fills in affected programs: 898 -> 1080 (20.27%)
   helped: 7
   HURT: 9

   LOST:   469
   GAINED: 220

On SNB:

   total instructions in shared programs: 13996898 -> 14096222 (0.71%)
   instructions in affected programs: 8088546 -> 8187870 (1.23%)
   helped: 2
   HURT: 66520

   total spills in shared programs: 2985 -> 2961 (-0.80%)
   spills in affected programs: 632 -> 608 (-3.80%)
   helped: 2
   HURT: 0

   total fills in shared programs: 3144 -> 3128 (-0.51%)
   fills in affected programs: 1515 -> 1499 (-1.06%)
   helped: 2
   HURT: 0

   LOST:   0
   GAINED: 4

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This commit is contained in:
Francisco Jerez
2019-12-30 00:36:48 -08:00
parent e328fbd9f8
commit 8eb4f2092a
1 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/intel/compiler/brw_fs_copy_propagation.cpp
View File

@@ -48,8 +48,8 @@ struct acp_entry : public exec_node {
fs_reg dst;
fs_reg src;
unsigned global_idx;
uint8_t size_written;
uint8_t size_read;
unsigned size_written;
unsigned size_read;
enum opcode opcode;
bool saturate;
};
@@ -895,7 +895,8 @@ can_propagate_from(fs_inst *inst)
(inst->src[0].file == FIXED_GRF &&
inst->src[0].is_contiguous())) &&
inst->src[0].type == inst->dst.type &&
!inst->is_partial_write());
!inst->is_partial_write()) ||
is_identity_payload(FIXED_GRF, inst);
}
/* Walks a basic block and does copy propagation on it using the acp
@@ -948,11 +949,12 @@ fs_visitor::opt_copy_propagation_local(void *copy_prop_ctx, bblock_t *block,
* operand of another instruction, add it to the ACP.
*/
if (can_propagate_from(inst)) {
acp_entry *entry = ralloc(copy_prop_ctx, acp_entry);
acp_entry *entry = rzalloc(copy_prop_ctx, acp_entry);
entry->dst = inst->dst;
entry->src = inst->src[0];
entry->size_written = inst->size_written;
entry->size_read = inst->size_read(0);
for (unsigned i = 0; i < inst->sources; i++)
entry->size_read += inst->size_read(i);
entry->opcode = inst->opcode;
entry->saturate = inst->saturate;
acp[entry->dst.nr % ACP_HASH_SIZE].push_tail(entry);