diff options
author | Ian Romanick <[email protected]> | 2016-03-24 15:48:55 -0700 |
---|---|---|
committer | Ian Romanick <[email protected]> | 2016-03-31 14:59:36 -0700 |
commit | cdea12bf035117f7cae5db0d52f3050d81c50c37 (patch) | |
tree | 25322bc8909b7d140574e6f13528212f7afc5fc8 /src/mesa/program | |
parent | 8bb9c6ff7f2398e1a497a9b5413736f58205843c (diff) |
ptn: Fix all users of ptn_swizzle
None of the callers actually wanted what it did. In ptn_xpd, you only
ever want a vec3 swizzle. In ptn_tex, you want a swizzle that matches
the number of required texture coordinates.
shader-db results:
G45:
total instructions in shared programs: 4011240 -> 4010911 (-0.01%)
instructions in affected programs: 59232 -> 58903 (-0.56%)
helped: 114
HURT: 0
total cycles in shared programs: 84314194 -> 84313220 (-0.00%)
cycles in affected programs: 779150 -> 778176 (-0.13%)
helped: 110
HURT: 13
Ironlake:
total instructions in shared programs: 6397262 -> 6396605 (-0.01%)
instructions in affected programs: 117402 -> 116745 (-0.56%)
helped: 227
HURT: 0
total cycles in shared programs: 128889798 -> 128888524 (-0.00%)
cycles in affected programs: 1214644 -> 1213370 (-0.10%)
helped: 179
HURT: 44
Sandy Bridge:
total instructions in shared programs: 8467391 -> 8467384 (-0.00%)
instructions in affected programs: 3107 -> 3100 (-0.23%)
helped: 10
HURT: 6
total cycles in shared programs: 117580120 -> 117573448 (-0.01%)
cycles in affected programs: 103158 -> 96486 (-6.47%)
helped: 84
HURT: 11
Ivy Bridge:
total instructions in shared programs: 7774255 -> 7774258 (0.00%)
instructions in affected programs: 1677 -> 1680 (0.18%)
helped: 8
HURT: 6
total cycles in shared programs: 65743828 -> 65739190 (-0.01%)
cycles in affected programs: 89312 -> 84674 (-5.19%)
helped: 78
HURT: 23
Haswell:
total instructions in shared programs: 7107172 -> 7107150 (-0.00%)
instructions in affected programs: 2048 -> 2026 (-1.07%)
helped: 16
HURT: 0
total cycles in shared programs: 64653636 -> 64647486 (-0.01%)
cycles in affected programs: 86836 -> 80686 (-7.08%)
helped: 85
HURT: 17
Broadwell and Skylake:
total instructions in shared programs: 8447529 -> 8447507 (-0.00%)
instructions in affected programs: 2038 -> 2016 (-1.08%)
helped: 16
HURT: 0
total cycles in shared programs: 66418670 -> 66413416 (-0.01%)
cycles in affected programs: 90110 -> 84856 (-5.83%)
helped: 83
HURT: 20
Signed-off-by: Ian Romanick <[email protected]>
Reviewed-by: Iago Toral Quiroga <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
Diffstat (limited to 'src/mesa/program')
-rw-r--r-- | src/mesa/program/prog_to_nir.c | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/src/mesa/program/prog_to_nir.c b/src/mesa/program/prog_to_nir.c index ce25f6d14f6..a6119ae4e7c 100644 --- a/src/mesa/program/prog_to_nir.c +++ b/src/mesa/program/prog_to_nir.c @@ -59,7 +59,6 @@ struct ptn_compile { #define SWIZ(X, Y, Z, W) \ (unsigned[4]){ SWIZZLE_##X, SWIZZLE_##Y, SWIZZLE_##Z, SWIZZLE_##W } -#define ptn_swizzle(b, src, x, y, z, w) nir_swizzle(b, src, SWIZ(x, y, z, w), 4, true) #define ptn_channel(b, src, ch) nir_swizzle(b, src, SWIZ(ch, ch, ch, ch), 1, true) static nir_ssa_def * @@ -491,11 +490,11 @@ ptn_xpd(nir_builder *b, nir_alu_dest dest, nir_ssa_def **src) ptn_move_dest_masked(b, dest, nir_fsub(b, nir_fmul(b, - ptn_swizzle(b, src[0], Y, Z, X, X), - ptn_swizzle(b, src[1], Z, X, Y, X)), + nir_swizzle(b, src[0], SWIZ(Y, Z, X, W), 3, true), + nir_swizzle(b, src[1], SWIZ(Z, X, Y, W), 3, true)), nir_fmul(b, - ptn_swizzle(b, src[1], Y, Z, X, X), - ptn_swizzle(b, src[0], Z, X, Y, X))), + nir_swizzle(b, src[1], SWIZ(Y, Z, X, W), 3, true), + nir_swizzle(b, src[0], SWIZ(Z, X, Y, W), 3, true))), WRITEMASK_XYZ); ptn_move_dest_masked(b, dest, nir_imm_float(b, 1.0), WRITEMASK_W); } @@ -642,7 +641,8 @@ ptn_tex(nir_builder *b, nir_alu_dest dest, nir_ssa_def **src, unsigned src_number = 0; instr->src[src_number].src = - nir_src_for_ssa(ptn_swizzle(b, src[0], X, Y, Z, W)); + nir_src_for_ssa(nir_swizzle(b, src[0], SWIZ(X, Y, Z, W), + instr->coord_components, true)); instr->src[src_number].src_type = nir_tex_src_coord; src_number++; |