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

soft-fp64: Don't open-code umulExtended

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: 928859 -> 859509 (-7.47%)
instructions in affected programs: 866293 -> 796943 (-8.01%)
helped: 76
HURT: 0
helped stats (abs) min: 75 max: 8042 x̄: 912.50 x̃: 688
helped stats (rel) min: 5.35% max: 21.02% x̄: 10.35% x̃: 7.58%
95% mean confidence interval for instructions value: -1138.37 -686.63
95% mean confidence interval for instructions %-change: -11.69% -9.00%
Instructions are helped.

total cycles in shared programs: 7272912 -> 7072275 (-2.76%)
cycles in affected programs: 6763486 -> 6562849 (-2.97%)
helped: 76
HURT: 0
helped stats (abs) min: 214 max: 30136 x̄: 2639.96 x̃: 1923
helped stats (rel) min: 1.75% max: 9.20% x̄: 4.04% x̃: 2.41%
95% mean confidence interval for cycles value: -3455.29 -1824.63
95% mean confidence interval for cycles %-change: -4.69% -3.39%
Cycles are helped.

total spills in shared programs: 817 -> 814 (-0.37%)
spills in affected programs: 791 -> 788 (-0.38%)
helped: 2
HURT: 0

total fills in shared programs: 2438 -> 2488 (2.05%)
fills in affected programs: 2392 -> 2442 (2.09%)
helped: 0
HURT: 2

Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
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 12:26:37 -08:00
committed by Marge Bot
parent d1e0227ef1
commit 812230fd94
1 changed files with 8 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
src/compiler/glsl/float64.glsl
View File

@@ -730,30 +730,6 @@ __fadd64(uint64_t a, uint64_t b)
}
}
/* Multiplies `a' by `b' to obtain a 64-bit product. The product is broken
* into two 32-bit pieces which are stored at the locations pointed to by
* `z0Ptr' and `z1Ptr'.
*/
void
__mul32To64(uint a, uint b, out uint z0Ptr, out uint z1Ptr)
{
uint aLow = a & 0x0000FFFFu;
uint aHigh = a>>16;
uint bLow = b & 0x0000FFFFu;
uint bHigh = b>>16;
uint z1 = aLow * bLow;
uint zMiddleA = aLow * bHigh;
uint zMiddleB = aHigh * bLow;
uint z0 = aHigh * bHigh;
zMiddleA += zMiddleB;
z0 += ((uint(zMiddleA < zMiddleB)) << 16) + (zMiddleA >> 16);
zMiddleA <<= 16;
z1 += zMiddleA;
z0 += uint(z1 < zMiddleA);
z1Ptr = z1;
z0Ptr = z0;
}
/* Multiplies the 64-bit value formed by concatenating `a0' and `a1' to the
* 64-bit value formed by concatenating `b0' and `b1' to obtain a 128-bit
* product. The product is broken into four 32-bit pieces which are stored at
@@ -773,12 +749,12 @@ __mul64To128(uint a0, uint a1, uint b0, uint b1,
uint more1 = 0u;
uint more2 = 0u;
__mul32To64(a1, b1, z2, z3);
__mul32To64(a1, b0, z1, more2);
umulExtended(a1, b1, z2, z3);
umulExtended(a1, b0, z1, more2);
__add64(z1, more2, 0u, z2, z1, z2);
__mul32To64(a0, b0, z0, more1);
umulExtended(a0, b0, z0, more1);
__add64(z0, more1, 0u, z1, z0, z1);
__mul32To64(a0, b1, more1, more2);
umulExtended(a0, b1, more1, more2);
__add64(more1, more2, 0u, z2, more1, z2);
__add64(z0, z1, 0u, more1, z0, z1);
z3Ptr = z3;
@@ -1442,7 +1418,7 @@ __estimateDiv64To32(uint a0, uint a1, uint b)
return 0xFFFFFFFFu;
b0 = b>>16;
z = (b0<<16 <= a0) ? 0xFFFF0000u : (a0 / b0)<<16;
__mul32To64(b, z, term0, term1);
umulExtended(b, z, term0, term1);
__sub64(a0, a1, term0, term1, rem0, rem1);
while (int(rem0) < 0) {
z -= 0x10000u;
@@ -1612,7 +1588,7 @@ __fsqrt64(uint64_t a)
zFrac0 = 0x7FFFFFFFu;
doubleZFrac0 = zFrac0 + zFrac0;
__shortShift64Left(aFracHi, aFracLo, 9 - (aExp & 1), aFracHi, aFracLo);
__mul32To64(zFrac0, zFrac0, term0, term1);
umulExtended(zFrac0, zFrac0, term0, term1);
__sub64(aFracHi, aFracLo, term0, term1, rem0, rem1);
while (int(rem0) < 0) {
--zFrac0;
@@ -1623,9 +1599,9 @@ __fsqrt64(uint64_t a)
if ((zFrac1 & 0x1FFu) <= 5u) {
if (zFrac1 == 0u)
zFrac1 = 1u;
__mul32To64(doubleZFrac0, zFrac1, term1, term2);
umulExtended(doubleZFrac0, zFrac1, term1, term2);
__sub64(rem1, 0u, term1, term2, rem1, rem2);
__mul32To64(zFrac1, zFrac1, term2, term3);
umulExtended(zFrac1, zFrac1, term2, term3);
__sub96(rem1, rem2, 0u, 0u, term2, term3, rem1, rem2, rem3);
while (int(rem1) < 0) {
--zFrac1;