OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

soft-fp64/fadd: Instead of tracking "b < a", track sign of the difference

Browse Source 
Results on the 308 shaders extracted from the fp64 portion of the OpenGL
CTS:

Tiger Lake and Ice Lake had similar results. (Tiger Lake shown)
total instructions in shared programs: 824403 -> 822766 (-0.20%)
instructions in affected programs: 756260 -> 754623 (-0.22%)
helped: 68
HURT: 1
helped stats (abs) min: 1 max: 118 x̄: 26.26 x̃: 18
helped stats (rel) min: 0.02% max: 0.97% x̄: 0.31% x̃: 0.23%
HURT stats (abs)   min: 149 max: 149 x̄: 149.00 x̃: 149
HURT stats (rel)   min: 0.17% max: 0.17% x̄: 0.17% x̃: 0.17%
95% mean confidence interval for instructions value: -31.94 -15.51
95% mean confidence interval for instructions %-change: -0.37% -0.23%
Instructions are helped.

total cycles in shared programs: 6828935 -> 6816791 (-0.18%)
cycles in affected programs: 6385191 -> 6373047 (-0.19%)
helped: 73
HURT: 0
helped stats (abs) min: 2 max: 852 x̄: 166.36 x̃: 120
helped stats (rel) min: <.01% max: 0.80% x̄: 0.22% x̃: 0.17%
95% mean confidence interval for cycles value: -210.80 -121.91
95% mean confidence interval for cycles %-change: -0.27% -0.17%
Cycles are helped.

total fills in shared programs: 1442 -> 1497 (3.81%)
fills in affected programs: 1442 -> 1497 (3.81%)
helped: 0
HURT: 1

Reviewed-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4142>
This commit is contained in:
Ian Romanick
2020-03-03 19:38:13 -08:00
committed by Marge Bot
parent 5b07f542e5
commit 73fa3a1ca4
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/compiler/glsl/float64.glsl
View File

@@ -771,14 +771,14 @@ __fadd64(uint64_t a, uint64_t b)
bExp = mix(bExp, 1, aExp == 0); bExp = mix(bExp, 1, aExp == 0);
aExp = mix(aExp, 1, aExp == 0); aExp = mix(aExp, 1, aExp == 0);
bool zexp_normal = false; bool zexp_normal = false;
bool blta = true; uint sign_of_difference = 0;
if (bFracHi < aFracHi) { if (bFracHi < aFracHi) {
__sub64(aFracHi, aFracLo, bFracHi, bFracLo, zFrac0, zFrac1); __sub64(aFracHi, aFracLo, bFracHi, bFracLo, zFrac0, zFrac1);
zexp_normal = true; zexp_normal = true;
} }
else if (aFracHi < bFracHi) { else if (aFracHi < bFracHi) {
__sub64(bFracHi, bFracLo, aFracHi, aFracLo, zFrac0, zFrac1); __sub64(bFracHi, bFracLo, aFracHi, aFracLo, zFrac0, zFrac1);
blta = false; sign_of_difference = 0x80000000;
zexp_normal = true; zexp_normal = true;
} }
else if (bFracLo < aFracLo) { else if (bFracLo < aFracLo) {
@@ -787,11 +787,11 @@ __fadd64(uint64_t a, uint64_t b)
} }
else if (aFracLo < bFracLo) { else if (aFracLo < bFracLo) {
__sub64(bFracHi, bFracLo, aFracHi, aFracLo, zFrac0, zFrac1); __sub64(bFracHi, bFracLo, aFracHi, aFracLo, zFrac0, zFrac1);
blta = false; sign_of_difference = 0x80000000;
zexp_normal = true; zexp_normal = true;
} }
zExp = mix(bExp, aExp, blta); zExp = mix(bExp, aExp, sign_of_difference == 0u);
aSign = mix(aSign ^ 0x80000000u, aSign, blta); aSign ^= sign_of_difference;
uint64_t retval_0 = __packFloat64(uint(FLOAT_ROUNDING_MODE == FLOAT_ROUND_DOWN) << 31, 0, 0u, 0u); uint64_t retval_0 = __packFloat64(uint(FLOAT_ROUNDING_MODE == FLOAT_ROUND_DOWN) << 31, 0, 0u, 0u);
uint64_t retval_1 = __normalizeRoundAndPackFloat64(aSign, zExp - 11, zFrac0, zFrac1); uint64_t retval_1 = __normalizeRoundAndPackFloat64(aSign, zExp - 11, zFrac0, zFrac1);
return mix(retval_0, retval_1, zexp_normal); return mix(retval_0, retval_1, zexp_normal);