[Mesa-dev] [PATCH] nir: Fix output swizzle in get_mul_for_src

[Iago Toral Quiroga]

When we compute the output swizzle we want to consider the writemask of the
add operation, not the one from the multiplication.
---
 src/glsl/nir/nir_opt_peephole_ffma.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/src/glsl/nir/nir_opt_peephole_ffma.c b/src/glsl/nir/nir_opt_peephole_ffma.c
index b430eac..c895c22 100644
--- a/src/glsl/nir/nir_opt_peephole_ffma.c
+++ b/src/glsl/nir/nir_opt_peephole_ffma.c
@@ -73,7 +73,8 @@ are_all_uses_fadd(nir_ssa_def *def)
 }
 
 static nir_alu_instr *
-get_mul_for_src(nir_alu_src *src, uint8_t swizzle[4], bool *negate, bool *abs)
+get_mul_for_src(nir_alu_src *src, int writemask,
+                uint8_t swizzle[4], bool *negate, bool *abs)
 {
    assert(src->src.is_ssa && !src->abs && !src->negate);
 
@@ -85,16 +86,16 @@ get_mul_for_src(nir_alu_src *src, uint8_t swizzle[4], bool *negate, bool *abs)
    switch (alu->op) {
    case nir_op_imov:
    case nir_op_fmov:
-      alu = get_mul_for_src(&alu->src[0], swizzle, negate, abs);
+      alu = get_mul_for_src(&alu->src[0], writemask, swizzle, negate, abs);
       break;
 
    case nir_op_fneg:
-      alu = get_mul_for_src(&alu->src[0], swizzle, negate, abs);
+      alu = get_mul_for_src(&alu->src[0], writemask, swizzle, negate, abs);
       *negate = !*negate;
       break;
 
    case nir_op_fabs:
-      alu = get_mul_for_src(&alu->src[0], swizzle, negate, abs);
+      alu = get_mul_for_src(&alu->src[0], writemask, swizzle, negate, abs);
       *negate = false;
       *abs = true;
       break;
@@ -116,7 +117,7 @@ get_mul_for_src(nir_alu_src *src, uint8_t swizzle[4], bool *negate, bool *abs)
       return NULL;
 
    for (unsigned i = 0; i < 4; i++) {
-      if (!(alu->dest.write_mask & (1 << i)))
+      if (!(writemask & (1 << i)))
          break;
 
       swizzle[i] = swizzle[src->swizzle[i]];
@@ -160,7 +161,8 @@ nir_opt_peephole_ffma_block(nir_block *block, void *void_state)
          negate = false;
          abs = false;
 
-         mul = get_mul_for_src(&add->src[add_mul_src], swizzle, &negate, &abs);
+         mul = get_mul_for_src(&add->src[add_mul_src], add->dest.write_mask,
+                               swizzle, &negate, &abs);
 
          if (mul != NULL)
             break;
-- 
1.9.1