diff options
| author | Jason Ekstrand <[email protected]> | 2016-05-05 17:14:39 -0700 |
|---|---|---|
| committer | Jason Ekstrand <[email protected]> | 2016-05-11 11:44:35 -0700 |
| commit | 47f01e538ad575d3f2b02e747905e7ab9dd3a9bb (patch) | |
| tree | f5015584655d42317bcca2fce6b7c6078f5ccec1 /src | |
| parent | 1b72c31e1f1947123d8c236b56e230f030f60cf9 (diff) | |
ptn: Emit mul+add for MAD
Unlike fma() in GLSL, MAD in ARB programs is 100% splittable. Just emit
the split version and let the optimizer fuse them later.
Shader-db results on Haswell:
total instructions in shared programs: 7560379 -> 7560300 (-0.00%)
instructions in affected programs: 143928 -> 143849 (-0.05%)
helped: 443
HURT: 250
Reviewed-by: Kenneth Graunke <[email protected]>
Diffstat (limited to 'src')
| -rw-r--r-- | src/mesa/program/prog_to_nir.c | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/src/mesa/program/prog_to_nir.c b/src/mesa/program/prog_to_nir.c index b93355342af..9e01151a1c4 100644 --- a/src/mesa/program/prog_to_nir.c +++ b/src/mesa/program/prog_to_nir.c @@ -666,7 +666,7 @@ static const nir_op op_trans[MAX_OPCODE] = { [OPCODE_LIT] = 0, [OPCODE_LOG] = 0, [OPCODE_LRP] = 0, - [OPCODE_MAD] = nir_op_ffma, + [OPCODE_MAD] = 0, [OPCODE_MAX] = nir_op_fmax, [OPCODE_MIN] = nir_op_fmin, [OPCODE_MOV] = nir_op_fmov, @@ -757,6 +757,10 @@ ptn_emit_instruction(struct ptn_compile *c, struct prog_instruction *prog_inst) ptn_lrp(b, dest, src); break; + case OPCODE_MAD: + ptn_move_dest(b, dest, nir_fadd(b, nir_fmul(b, src[0], src[1]), src[2])); + break; + case OPCODE_DST: ptn_dst(b, dest, src); break; |