pan/midgard: Use more aggressive writeout criteria

We loosen the requirement of "no dependencies" to simply be "no
non-pipelined dependencies", so we check for what could be pipelined.

total bundles in shared programs: 2176 -> 2156 (-0.92%)
bundles in affected programs: 779 -> 759 (-2.57%)
helped: 20
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 0.33% max: 20.00% x̄: 6.47% x̃: 2.78%
95% mean confidence interval for bundles value: -1.00 -1.00
95% mean confidence interval for bundles %-change: -9.44% -3.50%
Bundles are helped.

total quadwords in shared programs: 3605 -> 3585 (-0.55%)
quadwords in affected programs: 1391 -> 1371 (-1.44%)
helped: 20
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 0.19% max: 14.29% x̄: 3.84% x̃: 1.64%
95% mean confidence interval for quadwords value: -1.00 -1.00
95% mean confidence interval for quadwords %-change: -5.73% -1.94%
Quadwords are helped.

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>

diff --git a/src/panfrost/midgard/midgard_schedule.c b/src/panfrost/midgard/midgard_schedule.c
index 4672f144d9c28cba6574612b3e771d3b5e5db803..3bf656d49d2adba03f5aa0c5f3102ea796df0efd 100644 (file)
--- a/src/panfrost/midgard/midgard_schedule.c
+++ b/src/panfrost/midgard/midgard_schedule.c
@@ -122,14 +122,14 @@ midgard_has_hazard(
  *
  *  - All components of r0 are written in the bundle
  *  - No components of r0 are written in VLUT
- *  - Dependencies of r0 are not written in the bundle
+ *  - Non-pipelined dependencies of r0 are not written in the bundle
  *
  * This function checks if these requirements are satisfied given the content
  * of a scheduled bundle.
  */
 
 static bool
-can_writeout_fragment(midgard_instruction **bundle, unsigned count, unsigned node_count)
+can_writeout_fragment(compiler_context *ctx, midgard_instruction **bundle, unsigned count, unsigned node_count)
 {
         /* First scan for which components of r0 are written out. Initially
          * none are written */
@@ -148,10 +148,20 @@ can_writeout_fragment(midgard_instruction **bundle, unsigned count, unsigned nod
                 /* Record written out mask */
                 r0_written_mask |= ins->mask;
 
-                /* Record dependencies */
+                /* Record dependencies, but only if they won't become pipeline
+                 * registers. We know we can't be live after this, because
+                 * we're writeout at the very end of the shader. So check if
+                 * they were written before us. */
+
                 unsigned src0 = ins->ssa_args.src0;
                 unsigned src1 = ins->ssa_args.src1;
 
+                if (!mir_is_written_before(ctx, bundle[0], src0))
+                        src0 = -1;
+
+                if (!mir_is_written_before(ctx, bundle[0], src1))
+                        src1 = -1;
+
                 if ((src0 > 0) && (src0 < node_count))
                         BITSET_SET(dependencies, src0);
 
@@ -452,7 +462,7 @@ schedule_bundle(compiler_context *ctx, midgard_block *block, midgard_instruction
 
                                 unsigned node_count = ctx->func->impl->ssa_alloc + ctx->func->impl->reg_alloc;
 
-                                if (ains->writeout && !can_writeout_fragment(scheduled, index, node_count)) {
+                                if (ains->writeout && !can_writeout_fragment(ctx, scheduled, index, node_count)) {
                                         /* We only work on full moves
                                          * at the beginning. We could
                                          * probably do better */