Mesa (main): pan/bi: Fuse result types
GitLab Mirror
gitlab-mirror at kemper.freedesktop.org
Fri May 27 12:30:38 UTC 2022
Module: Mesa
Branch: main
Commit: 501a66cb5ce76ffca6aa663ea9f8b31d2cd71f07
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=501a66cb5ce76ffca6aa663ea9f8b31d2cd71f07
Author: Alyssa Rosenzweig <alyssa at collabora.com>
Date: Thu Jan 6 17:12:56 2022 -0500
pan/bi: Fuse result types
In NIR, comparison instructions always produce 0/~0 results. For other result
types, a separate b2f32 or b2i32 instruction is used to transform the result.
However, Mali's comparison instructions have modifiers for these alternate
result types, so we can implement expressions like int(a < b) and float(a ==
b) in single instruction. Add a peephole optimization to fuse comparisons
with result type transformations.
Results on Mali-G52:
total instructions in shared programs: 2439696 -> 2434339 (-0.22%)
instructions in affected programs: 418703 -> 413346 (-1.28%)
helped: 1630
HURT: 0
helped stats (abs) min: 1.0 max: 28.0 x̄: 3.29 x̃: 2
helped stats (rel) min: 0.11% max: 19.35% x̄: 1.64% x̃: 1.39%
95% mean confidence interval for instructions value: -3.44 -3.13
95% mean confidence interval for instructions %-change: -1.72% -1.56%
Instructions are helped.
total tuples in shared programs: 1946581 -> 1943005 (-0.18%)
tuples in affected programs: 251742 -> 248166 (-1.42%)
helped: 1113
HURT: 11
helped stats (abs) min: 1.0 max: 32.0 x̄: 3.23 x̃: 2
helped stats (rel) min: 0.17% max: 15.38% x̄: 1.80% x̃: 1.38%
HURT stats (abs) min: 1.0 max: 2.0 x̄: 1.45 x̃: 1
HURT stats (rel) min: 0.21% max: 3.12% x̄: 1.23% x̃: 0.89%
95% mean confidence interval for tuples value: -3.35 -3.01
95% mean confidence interval for tuples %-change: -1.88% -1.66%
Tuples are helped.
total clauses in shared programs: 357791 -> 357349 (-0.12%)
clauses in affected programs: 15879 -> 15437 (-2.78%)
helped: 371
HURT: 3
helped stats (abs) min: 1.0 max: 8.0 x̄: 1.20 x̃: 1
helped stats (rel) min: 0.80% max: 33.33% x̄: 3.85% x̃: 2.17%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 2.94% max: 5.26% x̄: 4.49% x̃: 5.26%
95% mean confidence interval for clauses value: -1.27 -1.09
95% mean confidence interval for clauses %-change: -4.21% -3.36%
Clauses are helped.
total cycles in shared programs: 167922.04 -> 167810.71 (-0.07%)
cycles in affected programs: 6772.08 -> 6660.75 (-1.64%)
helped: 655
HURT: 12
helped stats (abs) min: 0.041665999999999315 max: 1.3333319999999986 x̄: 0.17 x̃: 0
helped stats (rel) min: 0.18% max: 20.00% x̄: 2.02% x̃: 1.60%
HURT stats (abs) min: 0.041665999999999315 max: 0.125 x̄: 0.05 x̃: 0
HURT stats (rel) min: 0.21% max: 3.80% x̄: 1.23% x̃: 0.88%
95% mean confidence interval for cycles value: -0.18 -0.16
95% mean confidence interval for cycles %-change: -2.10% -1.81%
Cycles are helped.
total arith in shared programs: 74393.17 -> 74243.08 (-0.20%)
arith in affected programs: 10157.50 -> 10007.42 (-1.48%)
helped: 1129
HURT: 12
helped stats (abs) min: 0.041665999999999315 max: 1.3333319999999986 x̄: 0.13 x̃: 0
helped stats (rel) min: 0.18% max: 50.00% x̄: 1.94% x̃: 1.40%
HURT stats (abs) min: 0.041665999999999315 max: 0.125 x̄: 0.05 x̃: 0
HURT stats (rel) min: 0.21% max: 3.80% x̄: 1.23% x̃: 0.88%
95% mean confidence interval for arith value: -0.14 -0.12
95% mean confidence interval for arith %-change: -2.06% -1.76%
Arith are helped.
total quadwords in shared programs: 1692019 -> 1688164 (-0.23%)
quadwords in affected programs: 216669 -> 212814 (-1.78%)
helped: 1148
HURT: 11
helped stats (abs) min: 1.0 max: 41.0 x̄: 3.37 x̃: 2
helped stats (rel) min: 0.17% max: 17.24% x̄: 2.25% x̃: 1.73%
HURT stats (abs) min: 1.0 max: 2.0 x̄: 1.09 x̃: 1
HURT stats (rel) min: 0.60% max: 1.32% x̄: 0.85% x̃: 0.83%
95% mean confidence interval for quadwords value: -3.49 -3.16
95% mean confidence interval for quadwords %-change: -2.33% -2.10%
Quadwords are helped.
Signed-off-by: Alyssa Rosenzweig <alyssa at collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16725>
---
src/panfrost/bifrost/bi_opt_mod_props.c | 80 ++++++++++++++++++++++++++++++++-
1 file changed, 79 insertions(+), 1 deletion(-)
diff --git a/src/panfrost/bifrost/bi_opt_mod_props.c b/src/panfrost/bifrost/bi_opt_mod_props.c
index b0458b362e1..5e9b76df3ae 100644
--- a/src/panfrost/bifrost/bi_opt_mod_props.c
+++ b/src/panfrost/bifrost/bi_opt_mod_props.c
@@ -228,6 +228,83 @@ bi_optimizer_clamp(bi_instr *I, bi_instr *use)
return true;
}
+static enum bi_opcode
+bi_sized_mux_op(unsigned size)
+{
+ switch (size) {
+ case 8: return BI_OPCODE_MUX_V4I8;
+ case 16: return BI_OPCODE_MUX_V2I16;
+ case 32: return BI_OPCODE_MUX_I32;
+ default: unreachable("invalid size");
+ }
+}
+
+static bool
+bi_is_fixed_mux(bi_instr *I, unsigned size, bi_index v1)
+{
+ return I->op == bi_sized_mux_op(size) &&
+ bi_is_value_equiv(I->src[0], bi_zero()) &&
+ bi_is_value_equiv(I->src[1], v1);
+}
+
+static bool
+bi_takes_int_result_type(enum bi_opcode op)
+{
+ switch (op) {
+ case BI_OPCODE_ICMP_I32:
+ case BI_OPCODE_ICMP_S32:
+ case BI_OPCODE_ICMP_U32:
+ case BI_OPCODE_ICMP_V2I16:
+ case BI_OPCODE_ICMP_V2S16:
+ case BI_OPCODE_ICMP_V2U16:
+ case BI_OPCODE_ICMP_V4I8:
+ case BI_OPCODE_ICMP_V4S8:
+ case BI_OPCODE_ICMP_V4U8:
+ case BI_OPCODE_FCMP_F32:
+ case BI_OPCODE_FCMP_V2F16:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static bool
+bi_takes_float_result_type(enum bi_opcode op)
+{
+ return (op == BI_OPCODE_FCMP_F32) ||
+ (op == BI_OPCODE_FCMP_V2F16);
+}
+
+/* CMP+MUX -> CMP with result type */
+static bool
+bi_optimizer_result_type(bi_instr *I, bi_instr *mux)
+{
+ if (bi_opcode_props[I->op].size != bi_opcode_props[mux->op].size)
+ return false;
+
+ if (bi_is_fixed_mux(mux, 32, bi_imm_f32(1.0)) ||
+ bi_is_fixed_mux(mux, 16, bi_imm_f16(1.0))) {
+
+ if (!bi_takes_float_result_type(I->op))
+ return false;
+
+ I->result_type = BI_RESULT_TYPE_F1;
+ } else if (bi_is_fixed_mux(mux, 32, bi_imm_u32(1)) ||
+ bi_is_fixed_mux(mux, 16, bi_imm_u16(1)) ||
+ bi_is_fixed_mux(mux, 8, bi_imm_u8(1))) {
+
+ if (!bi_takes_int_result_type(I->op))
+ return false;
+
+ I->result_type = BI_RESULT_TYPE_I1;
+ } else {
+ return false;
+ }
+
+ I->dest[0] = mux->dest[0];
+ return true;
+}
+
static bool
bi_is_var_tex(bi_instr *var, bi_instr *tex)
{
@@ -289,7 +366,8 @@ bi_opt_mod_prop_backward(bi_context *ctx)
/* Destination has a single use, try to propagate */
bool propagated =
- bi_optimizer_clamp(I, use);
+ bi_optimizer_clamp(I, use) ||
+ bi_optimizer_result_type(I, use);
if (!propagated && I->op == BI_OPCODE_LD_VAR_IMM && use->op == BI_OPCODE_SPLIT_I32) {
/* Need to see through the split in a
More information about the mesa-commit
mailing list