This series has been reciding on my computer for way to long,
so it's about time I get it out there for some feedback.
The rationale is that in the glsl compiler a lot of the overhead
is in cache misses due to the visitor pattern we're running.
This is run on my intel machine.
Here are some perf stat results before and after the series
on a shader-db run on a subset of my shader-db.
Before:
56 849 919 924 cycles:u # 2,894 GHz
21 803 529 990 stalled-cycles-frontend:u # 38,35% frontend cycles idle
82 463 039 717 instructions:u # 1,45 insn per cycle
# 0,26 stalled cycles per insn
16 796 501 647 branches:u # 855,182 M/sec
394 313 169 branch-misses:u # 2,35% of all branches
20,568256999 seconds time elapsed
After:
55 956 131 481 cycles:u # 2,884 GHz
21 889 872 343 stalled-cycles-frontend:u # 39,12% frontend cycles idle
80 666 584 607 instructions:u # 1,44 insn per cycle
# 0,27 stalled cycles per insn
16 349 063 938 branches:u # 842,630 M/sec
383 226 870 branch-misses:u # 2,34% of all branches
20,342067729 seconds time elapsed
So, some things to notice:
There's a decent drop in executed instructions.
There's an increase in stalled cycles, which is not what I expected.
We are still seeing an ever so slight reduction in runtime.
Fewer branches, and fewer branch-prediction misses.
The question is if this is a route we want to go down?
Personally I think the code reduction is nice in and by itself.
Feedback is welcome =)
Thomas Helland (4):
glsl: Consolidate opt_noop_swizzle, and opt_swizzle_swizzle
glsl: Merge if_simplification and nested-if-flattening
glsl: Merge if-simplification and conditional discard optimization
glsl: Fold constant folding of assignments into constant propagation
src/compiler/Makefile.sources | 4 -
src/compiler/glsl/glsl_parser_extras.cpp | 4 -
src/compiler/glsl/ir_optimization.h | 5 -
src/compiler/glsl/opt_conditional_discard.cpp | 88 ---------
src/compiler/glsl/opt_constant_folding.cpp | 211 ---------------------
src/compiler/glsl/opt_constant_propagation.cpp | 97 ++++++++++
src/compiler/glsl/opt_flatten_nested_if_blocks.cpp | 103 ----------
src/compiler/glsl/opt_if_simplification.cpp | 95 ++++++++--
src/compiler/glsl/opt_noop_swizzle.cpp | 43 ++++-
src/compiler/glsl/opt_swizzle_swizzle.cpp | 97 ----------
10 files changed, 223 insertions(+), 524 deletions(-)
delete mode 100644 src/compiler/glsl/opt_conditional_discard.cpp
delete mode 100644 src/compiler/glsl/opt_constant_folding.cpp
delete mode 100644 src/compiler/glsl/opt_flatten_nested_if_blocks.cpp
delete mode 100644 src/compiler/glsl/opt_swizzle_swizzle.cpp
--
2.11.1
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
