[Mesa-dev] [PATCH 2/2] i965/nir/opt_peephole_ffma: Bypass fusion if any operand of fadd and fmul is a const

[Eduardo Lima Mitev]

When both fadd and fmul instructions have at least one operand that is a
constant and it is only used once, the total number of instructions can
be reduced from 3 (1 ffma + 2 load_const) to 2 (1 fmul + 1 fadd); because
the constants will be progagated as immediate operands of fmul and fadd.

This patch detects these situations and prevents fusing fmul+fadd into ffma.

Shader-db results on i965 Haswell:

total instructions in shared programs: 6240407 -> 6230467 (-0.16%)
instructions in affected programs:     1126478 -> 1116538 (-0.88%)
total loops in shared programs:        1979 -> 1979 (0.00%)
helped:                                7612
HURT:                                  843
GAINED:                                4
LOST:                                  0
---
 .../drivers/dri/i965/brw_nir_opt_peephole_ffma.c   | 31 ++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/src/mesa/drivers/dri/i965/brw_nir_opt_peephole_ffma.c b/src/mesa/drivers/dri/i965/brw_nir_opt_peephole_ffma.c
index a8448e7..0c60528 100644
--- a/src/mesa/drivers/dri/i965/brw_nir_opt_peephole_ffma.c
+++ b/src/mesa/drivers/dri/i965/brw_nir_opt_peephole_ffma.c
@@ -133,6 +133,28 @@ get_mul_for_src(nir_alu_src *src, int num_components,
    return alu;
 }
 
+/**
+ * Given a list of (at least two) nir_alu_src's, tells if any of them is a
+ * constant value and is used only once.
+ */
+static bool
+any_alu_src_is_a_constant(nir_alu_src srcs[])
+{
+   for (unsigned i = 0; i < 2; i++) {
+      if (srcs[i].src.ssa->parent_instr->type == nir_instr_type_load_const) {
+         nir_load_const_instr *load_const =
+            nir_instr_as_load_const (srcs[i].src.ssa->parent_instr);
+
+         if (list_length(&load_const->def.uses) == 1 &&
+             list_length(&load_const->def.if_uses) == 0) {
+            return true;
+         }
+      }
+   }
+
+   return false;
+}
+
 static bool
 brw_nir_opt_peephole_ffma_block(nir_block *block, void *void_state)
 {
@@ -183,6 +205,15 @@ brw_nir_opt_peephole_ffma_block(nir_block *block, void *void_state)
       mul_src[0] = mul->src[0].src.ssa;
       mul_src[1] = mul->src[1].src.ssa;
 
+      /* If any of the operands of the fmul and any of the fadd is a constant,
+       * we bypass because it will be more efficient as the constants will be
+       * propagated as operands, potentially saving two load_const instructions.
+       */
+      if (any_alu_src_is_a_constant(mul->src) &&
+          any_alu_src_is_a_constant(add->src)) {
+         continue;
+      }
+
       if (abs) {
          for (unsigned i = 0; i < 2; i++) {
             nir_alu_instr *abs = nir_alu_instr_create(state->mem_ctx,
-- 
2.5.3