diff options
author | Eric Anholt <[email protected]> | 2015-12-10 21:54:41 -0800 |
---|---|---|
committer | Eric Anholt <[email protected]> | 2015-12-11 12:36:16 -0800 |
commit | 076551116ed5fc1b0991cb84e1e5453f5a2e11db (patch) | |
tree | 481a7fc2fb45dfce5c74b3a81b2b28386ff7aad4 /src/gallium/drivers/vc4 | |
parent | e3efc4b02334897e0103f8cf926f376159ca1293 (diff) |
vc4: Add quick algebraic optimization for clamping of unpacked values.
GL likes to saturate your incoming color, but if that color's coming from
unpacking from unorms, there's no point. Ideally we'd have a range
propagation pass that cleans these up in NIR, but that doesn't seem to be
going to land soon. It seems like we could do a one-off optimization in
nir_opt_algebraic, except that doesn't want to operate on expressions
involving unpack_unorm_4x8, since it's sized.
total instructions in shared programs: 87879 -> 87761 (-0.13%)
instructions in affected programs: 6044 -> 5926 (-1.95%)
total estimated cycles in shared programs: 349457 -> 349252 (-0.06%)
estimated cycles in affected programs: 6172 -> 5967 (-3.32%)
No SSPD on openarena (which had the biggest gains, in its VS/CSes), n=15.
Diffstat (limited to 'src/gallium/drivers/vc4')
-rw-r--r-- | src/gallium/drivers/vc4/vc4_opt_algebraic.c | 18 |
1 files changed, 18 insertions, 0 deletions
diff --git a/src/gallium/drivers/vc4/vc4_opt_algebraic.c b/src/gallium/drivers/vc4/vc4_opt_algebraic.c index 207686b4af7..aea2b9dbe87 100644 --- a/src/gallium/drivers/vc4/vc4_opt_algebraic.c +++ b/src/gallium/drivers/vc4/vc4_opt_algebraic.c @@ -182,6 +182,24 @@ qir_opt_algebraic(struct vc4_compile *c) break; + case QOP_FMIN: + if (is_1f(c, inst->src[1]) && + inst->src[0].pack >= QPU_UNPACK_8D_REP && + inst->src[0].pack <= QPU_UNPACK_8D) { + replace_with_mov(c, inst, inst->src[0]); + progress = true; + } + break; + + case QOP_FMAX: + if (is_zero(c, inst->src[1]) && + inst->src[0].pack >= QPU_UNPACK_8D_REP && + inst->src[0].pack <= QPU_UNPACK_8D) { + replace_with_mov(c, inst, inst->src[0]); + progress = true; + } + break; + case QOP_FSUB: case QOP_SUB: if (is_zero(c, inst->src[1])) { |