nir: Fix load_const comparisons for CSE.

We want the size of a float per component, not the size of a whole vec4.

NIR instructions on i965:
total instructions in shared programs: 1261937 -> 1261929 (-0.00%)
instructions in affected programs:     114 -> 106 (-7.02%)

Looking at one of these examples (tesseract), it's from vec4 load_consts
for a MRT solid fill, which do get CSEed now that we don't memcmp off the
end of the const value and into the SSA def.  For the 1-component loads
that are common in i965, we were only memcmping off into the rest of the
usually zero-filled const_value.

Reviewed-by: Connor Abbott <cwabbott0@gmail.com>

diff --git a/src/glsl/nir/nir_opt_cse.c b/src/glsl/nir/nir_opt_cse.c
index b3e9c0d..9b38320 100644 (file)
--- a/src/glsl/nir/nir_opt_cse.c
+++ b/src/glsl/nir/nir_opt_cse.c
@@ -90,7 +90,7 @@ nir_instrs_equal(nir_instr *instr1, nir_instr *instr2)
          return false;
 
       return memcmp(load1->value.f, load2->value.f,
-                    load1->def.num_components * sizeof load2->value.f) == 0;
+                    load1->def.num_components * sizeof(*load2->value.f)) == 0;
    }
    case nir_instr_type_phi: {
       nir_phi_instr *phi1 = nir_instr_as_phi(instr1);