RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-12-21 19:20:28 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add new numbers

Browse Source 
llvm-svn: 4702
This commit is contained in:
Chris Lattner 2002-11-12 16:06:51 +00:00
parent b257e87db5
commit 195d36a7cc
1 changed files with 69 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

76
docs/DSGraphStatus.html
View File

@ -9,16 +9,78 @@ particular pass. Runs that are all '*'d out were not completed because they
were taking too long (time listed show how long I waited).<p>
Fields that appear in bold have changes from the last entry on the page.
Floating point entries are only highlighted if they double or half their
previous value.<p>
Floating point entries are only highlighted if they change significantly from
their previous value.<p>
<hr>
<a name="20021112"><h2>Nov 12, 2002:</h2>
<a
href="http://mail.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20021111/001567.html">This
small change</a> is important to programs with large SCC's. It basically makes
sure to inline calls to non-scc functions before we inline <b>any</b> intra-scc
calls. The problem is that inlining an SCC call could add <b>more</b> call
sites that would slow things down.<p>
Note that the total time underestimates the improvement. Take a look at the
change on BU time/total time to get an accurate accessment. I had some of the
graph IO printing code commented out in the last run, which affected Analyze
time, but not total time.<p>
<pre>
Name: Anlyz: LocTime: BUTime: TDTime: TotTime: BCTime: LocSize: BUSize: TDSize: TotSize: BCSize: NumFold NumNodes main __main GlobGr
254.gap.lib 17.69 0.8298 4.1158 2.4087 8.9138 2.9912 | 2024984 <b>2840288</b> <b>2024560</b> <b>6889832</b> 16554904 | <b>5985</b> <b>24035+3950</b> 44+9 0+0 0+0
255.vortex.lib 14.99 0.5988 1.8871 3.6557 7.3284 2.4054 | 1381056 <b>1259144</b> <b>1997120</b> <b>4637320</b> 11689312 | <b>5853</b> <b>7328+2841</b> 166+11 0+0 0+0
300.twolf.lib 3.34 0.2774 0.2827 0.5115 1.5475 1.0153 | 466528 391512 396552 1254592 6936728 | 749 4128+784 90+53 0+0 0+0
197.parser.lib 1.85 0.1485 0.3190 0.2156 0.8689 0.6872 | 408392 <b>225184</b> <b>212552</b> <b>965384</b> 4447944 | <b>1343</b> 2257+707 14+6 0+0 0+0
burg.llvm.lib 1.22 0.1027 0.1926 0.1739 0.5598 0.4947 | 530600 <b>474592</b> 185792 <b>1190984</b> 3040208 | <b>758</b> 2273+576 45+7 0+0 0+0
164.gzip.llvm.lib 0.74 0.0398 0.0559 0.0350 0.1957 0.4561 | 145952 184776 70872 499912 1876248 | 24 971+87 8+2 0+0 0+0
optimizer-eval.llvm.lib 0.43 0.0183 0.0485 0.2054 0.3047 0.0839 | 101184 79456 61760 242400 624688 | * 309+41 72+27 0+0 0+0
256.bzip2.lib 0.34 0.0241 0.0404 0.0113 0.1250 0.1624 | 139504 83400 39712 335144 1373216 | * 563+37 8+2 0+0 0+0
181.mcf.lib 0.23 0.0216 0.0279 0.0301 0.1126 0.0795 | 115448 146520 43680 322864 589440 | 166 388+51 22+10 0+0 0+0
sim.llvm.lib 0.20 0.0137 0.0138 0.0131 0.0800 0.0876 | 81632 51496 21872 226584 734152 | * 260+35 39+22 0+0 0+0
voronoi.llvm.lib 0.17 0.0139 0.0246 0.0282 0.0811 0.0591 | 79824 84152 27112 204904 420568 | 18 299+77 15+8 0+0 0+0
sgefa.llvm.lib 0.16 0.0090 0.0195 0.0201 0.0848 0.0542 | 85688 100456 67024 277864 368680 | * 130+24 24+14 0+0 0+0
bh.llvm.lib 0.16 0.0121 0.0164 0.0115 0.0581 0.0682 | 75000 51080 27760 217632 470720 | 61 194+35 6+2 0+0 0+0
power.llvm.lib <b>0.13</b> 0.0044 <b>0.0122</b> 0.0037 0.0282 0.0484 | 27776 17688 18144 71424 213760 | * 81+18 11+2 0+0 0+0
em3d.llvm.lib 0.11 0.0060 0.0110 0.0059 0.0308 0.0561 | 33040 36256 13008 90632 227520 | 1 178+28 12+4 0+0 0+0
health.llvm.lib 0.10 0.0052 <b>0.0203</b> 0.0073 0.0406 0.0421 | 30632 31432 12704 89592 199888 | 18 97+31 12+4 0+0 0+0
tsp.llvm.lib 0.07 0.0051 0.0063 0.0027 0.0217 0.0332 | 18232 14336 4920 51888 180744 | 21 43+15 8+4 0+0 0+0
mst.llvm.lib 0.07 0.0040 0.0065 0.0037 0.0215 0.0296 | 18624 25576 7040 65808 178832 | 10 97+15 12+3 0+0 0+0
lists.llvm.lib 0.07 0.0043 0.0131 0.0071 0.0299 0.0269 | 24552 16920 14440 68024 141480 | 30 67+26 3+1 0+0 0+0
fib2.llvm.lib <b>0.07</b> <b>0.0053</b> <b>0.0217</b> 0.0008 <b>0.0313</b> <b>0.0076</b> | 7960 6288 1640 28408 42256 | * 21+5 8+3 0+0 0+0
perimeter.llvm.lib 0.06 0.0031 0.0064 0.0021 0.0190 0.0275 | 15016 14192 3936 45912 156352 | * 35+15 7+4 0+0 0+0
hash.llvm.lib 0.06 0.0031 0.0050 0.0052 0.0200 0.0211 | 25728 16608 8208 63576 151680 | * 117+17 14+6 0+0 0+0
bisort.llvm.lib 0.06 0.0030 0.0055 0.0019 0.0318 <b>0.0126</b> | 13288 11408 3712 39448 127360 | * 35+13 7+4 0+0 0+0
sumarraymalloc.llvm.lib 0.04 0.0009 0.0014 0.0009 0.0075 <b>0.0240</b> | 7040 2672 2048 25872 54352 | * 23+5 7+4 0+0 0+0
objinst.llvm.lib 0.04 0.0019 0.0050 0.0032 0.0154 <b>0.0100</b> | 11280 15784 4112 45296 89856 | 34 45+14 16+10 0+0 0+0
methcall.llvm.lib 0.04 0.0018 0.0047 0.0031 0.0145 <b>0.0122</b> | 11008 9880 3928 38624 87976 | 30 43+12 14+8 0+0 0+0
matrix.llvm.lib 0.04 0.0013 0.0021 0.0014 0.0106 <b>0.0198</b> | 8808 8872 3072 33144 69112 | * 38+9 12+8 0+0 0+0
llubenchmark.llvm.lib 0.04 0.0024 0.0026 0.0015 0.0142 0.0118 | 11072 11760 2624 36480 124344 | * 31+7 15+5 0+0 0+0
heapsort.llvm.lib 0.04 0.0009 0.0019 0.0007 0.0073 <b>0.0137</b> | 2856 6968 2008 26976 63160 | * 26+3 7+2 0+0 0+0
ary3.llvm.lib 0.04 0.0013 0.0020 0.0011 0.0090 <b>0.0134</b> | 10240 13104 10888 45832 73064 | 6 44+5 12+3 0+0 0+0
ackermann.llvm.lib 0.04 0.0007 0.0015 0.0004 0.0066 0.0262 | 1744 5728 1200 22056 46448 | * 13+2 3+1 0+0 0+0
treeadd.llvm.lib 0.03 0.0015 0.0028 0.0010 0.0090 0.0084 | 3856 7384 2200 29784 72064 | * 25+7 6+3 0+0 0+0
sieve.llvm.lib 0.03 0.0008 0.0012 0.0006 0.0061 0.0162 | 2176 6176 1632 23432 216840 | * 22+2 12+1 0+0 0+0
random.llvm.lib <b>0.03</b> 0.0008 0.0017 0.0004 0.0059 <b>0.0133</b> | 2056 5720 1320 22080 45264 | * 15+2 3+1 0+0 0+0
matrixTranspose.llvm.lib 0.03 0.0005 0.0010 0.0003 0.0032 0.0129 | 4272 1144 736 8560 68448 | * 8+1 5+1 0+0 0+0
hello.llvm.lib 0.03 0.0004 0.0015 0.0001 0.0066 0.0107 | 752 2952 472 6512 14160 | * 2+0 0+0 0+0 0+0
sumarray2d.llvm.lib <b>0.02</b> 0.0005 0.0009 0.0002 0.0034 <b>0.0055</b> | 1568 3584 848 8264 23288 | * 10+1 7+1 0+0 0+0
printargs.llvm.lib <b>0.02</b> 0.0004 0.0013 0.0002 0.0032 0.0058 | 1240 1048 696 5128 19160 | * 6+1 4+1 0+0 0+0
pi.llvm.lib 0.02 0.0008 0.0021 0.0005 0.0052 0.0036 | 5392 1560 1392 8344 36032 | * 17+2 13+2 0+0 0+0
indvars.llvm.lib 0.02 0.0006 0.0010 0.0003 0.0037 0.0036 | 4744 1072 4208 12544 31336 | * 13+1 8+1 0+0 0+0
sumarray.llvm.lib <b>0.01</b> 0.0004 0.0008 0.0002 0.0026 <b>0.0029</b> | 904 3192 624 4720 15152 | * 6+1 4+1 0+0 0+0
</pre><p>
<hr>
<a name="20021111-2"><h2>Nov 11, 2002 #2:</h2>
This is the result after fixing some major bugs. The globals list was supposed
to be kept sorted, but there was one minor, tiny, little, bug that caused it to
get screwed up sometimes. This caused vortex to explode, fixing it gets things
back in control where you'd expect. Viola.<p>
This is the result after <a
href="http://mail.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20021111/001565.html">fixing
some major bugs</a>. The globals list was supposed to be kept sorted, but there
was one minor, tiny, little, bug that caused it to get screwed up sometimes.
This caused vortex to explode, fixing it gets things back in control where you'd
expect. Viola.<p>
This also includes a merging bug that caused some things to be merged and some
other things to happen when they shouldn't, which accounts for folding
@ -646,7 +708,7 @@ burg.llvm.lib analyze: ../../../include/llvm/Analysis/DSNode.h:7
<address><a href="mailto:sabre@nondot.org">Chris Lattner</a></address>
<!-- Created: Wed Nov 6 19:57:57 CST 2002 -->
<!-- hhmts start -->
Last modified: Tue Nov 12 00:49:40 CST 2002
Last modified: Tue Nov 12 10:06:27 CST 2002
<!-- hhmts end -->
</body>
</html>