agx: Fuse conditions into if's

Simple greedy thing that has the potential to inflate register pressure but
reduces instructions. Thanks to the recent loop work that turns if { break }
into while_icmp, this also implicitly handles fusing conditions into loops,
which is what actually prompted this.

Surprisingly, this helps register pressure on my shader-db (no change to thread
count), I guess by eliminating the boolean temps in case where the sources are
used multiple times.

   total instructions in shared programs: 1786561 -> 1784943 (-0.09%)
   instructions in affected programs: 128557 -> 126939 (-1.26%)
   helped: 474
   HURT: 13
   Instructions are helped.

   total bytes in shared programs: 11733236 -> 11720734 (-0.11%)
   bytes in affected programs: 976034 -> 963532 (-1.28%)
   helped: 521
   HURT: 13
   Bytes are helped.

   total halfregs in shared programs: 474245 -> 474094 (-0.03%)
   halfregs in affected programs: 1869 -> 1718 (-8.08%)
   helped: 28
   HURT: 7
   Halfregs are helped.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>

diff --git a/src/asahi/compiler/agx_optimizer.c b/src/asahi/compiler/agx_optimizer.c
index bd74af7..88149ef 100644 (file)
--- a/src/asahi/compiler/agx_optimizer.c
+++ b/src/asahi/compiler/agx_optimizer.c
@@ -243,6 +243,38 @@ agx_optimizer_copyprop(agx_instr **defs, agx_instr *I)
    }
 }
 
+/*
+ * Fuse conditions into if. Specifically, acts on if_icmp and fuses:
+ *
+ *    if_icmp(cmp(x, y, *), 0, ne) -> if_cmp(x, y, *)
+ */
+static void
+agx_optimizer_if_cmp(agx_instr **defs, agx_instr *I)
+{
+   /* Check for unfused if */
+   if (!agx_is_equiv(I->src[1], agx_zero()) || I->icond != AGX_ICOND_UEQ ||
+       !I->invert_cond || I->src[0].type != AGX_INDEX_NORMAL)
+      return;
+
+   /* Check for condition */
+   agx_instr *def = defs[I->src[0].value];
+   if (def->op != AGX_OPCODE_ICMP && def->op != AGX_OPCODE_FCMP)
+      return;
+
+   /* Fuse */
+   I->src[0] = def->src[0];
+   I->src[1] = def->src[1];
+   I->invert_cond = def->invert_cond;
+
+   if (def->op == AGX_OPCODE_ICMP) {
+      I->op = AGX_OPCODE_IF_ICMP;
+      I->icond = def->icond;
+   } else {
+      I->op = AGX_OPCODE_IF_FCMP;
+      I->fcond = def->fcond;
+   }
+}
+
 static void
 agx_optimizer_forward(agx_context *ctx)
 {
@@ -269,6 +301,9 @@ agx_optimizer_forward(agx_context *ctx)
           I->op != AGX_OPCODE_UNIFORM_STORE &&
           I->op != AGX_OPCODE_BLOCK_IMAGE_STORE)
          agx_optimizer_inline_imm(defs, I, info.nr_srcs, info.is_float);
+
+      if (I->op == AGX_OPCODE_IF_ICMP)
+         agx_optimizer_if_cmp(defs, I);
    }
 
    free(defs);