search for: hexxagon

After going through 17000+ lines of output, I come up with the following... =========================================== In file included from /usr/home/llvm/obj/projects/llvm-test/../../../projects/llvm-test/MultiSource/Applications/hexxagon/hexxagonmove.cpp:26: /usr/include/sys/timeb.h:43: error: `time_t' does not name a type /usr/home/llvm/obj/projects/llvm-test/../../../projects/llvm-test/MultiSource/Applications/hexxagon/hexxagonmove.cpp: In function `int getTime()': /usr/home/llvm/obj/projects/llvm-test/../../../projects/l...

...il). Sparc testing results: make check: # of expected passes 1189 # of expected failures 34 Regressions Single Source: None New Failures Single Source (new tests): 2005-05-12-Int64ToFP: llc,jit Regressions MultiSource: Applications/d/make_dparser: llc, cbe, jit Applications/hexxagon/hexxagon: llc, cbe, jit Benchmarks/MallocBench/gs/gs: llc, cbe Benchmarks/Prolangs-C/cdecl/cdecl: llc, cbe, jit Benchmarks/Prolangs-C/football/football: cbe Benchmarks/Prolangs-C/gnugo/gnugo: llc, cbe, jit Benchmarks/Prolangs-C/agrep/agrep: llc Benchmarks/Prolangs-C/fixoutput/fixoutput: llc, cbe Be...

...elow, it would be nice to get them fixed before the > release, but I'm not sure if anybody has time to look into it. If nobody has > time, we'll probably ship it as is. Sorry, I don't have time to do this unless time == a month or more. > I've tried out a few programs: hexxagon is an XFAIL (Solaris doesn't have > stdint.h), and make_dparser is genuinely broken (even with Chris's llvm-gcc > fix). Some of the Prolangs-C tests are working now, probably due to Chris's > fix, so Sparc is probaby in better shape than it looks. I am pretty sure hexxagon...

..., I think we'll just file a bug report and fix it in 1.7. As for the regressions below, it would be nice to get them fixed before the release, but I'm not sure if anybody has time to look into it. If nobody has time, we'll probably ship it as is. I've tried out a few programs: hexxagon is an XFAIL (Solaris doesn't have stdint.h), and make_dparser is genuinely broken (even with Chris's llvm-gcc fix). Some of the Prolangs-C tests are working now, probably due to Chris's fix, so Sparc is probaby in better shape than it looks. If you want to try out the new CFE, just...

Tanya Lattner wrote: > >> 1. I'm still looking for volunteers to test MacOS X and Solaris. >> If you'd like to volunteer, please email the list to let us know. > > > I'll do minimal testing on Sparc. I'm not going to look into any > regressions though since no one has been really watching Sparc since I > graduated and I am sure there are

...<jeffc at jolt-lang.org> wrote: > After going through 17000+ lines of output, I come up with the following... > > =========================================== > > In file included from /usr/home/llvm/obj/projects/llvm-test/../../../projects/llvm-test/MultiSource/Applications/hexxagon/hexxagonmove.cpp:26: > /usr/include/sys/timeb.h:43: error: `time_t' does not name a type > /usr/home/llvm/obj/projects/llvm-test/../../../projects/llvm-test/MultiSource/Applications/hexxagon/hexxagonmove.cpp: In function `int getTime()': > /usr/home/llvm/obj/projects/llvm-test/../....

...; wrote: > > > After going through 17000+ lines of output, I come up with the following... > > > > =========================================== > > > > In file included from /usr/home/llvm/obj/projects/llvm-test/../../../projects/llvm-test/MultiSource/Applications/hexxagon/hexxagonmove.cpp:26: > > /usr/include/sys/timeb.h:43: error: `time_t' does not name a type > > /usr/home/llvm/obj/projects/llvm-test/../../../projects/llvm-test/MultiSource/Applications/hexxagon/hexxagonmove.cpp: In function `int getTime()': > > /usr/home/llvm/obj/projects...

...; > After going through 17000+ lines of output, I come up with the following... > > > > > > =========================================== > > > > > > In file included from /usr/home/llvm/obj/projects/llvm-test/../../../projects/llvm-test/MultiSource/Applications/hexxagon/hexxagonmove.cpp:26: > > > /usr/include/sys/timeb.h:43: error: `time_t' does not name a type > > > /usr/home/llvm/obj/projects/llvm-test/../../../projects/llvm-test/MultiSource/Applications/hexxagon/hexxagonmove.cpp: In function `int getTime()': > > > /usr/home/ll...

...se.stepfft JIT failures in clang, pass in llvm-gcc: MultiSource/Applications/sqlite3/sqlite3 SingleSource/Regression/C++/ofstream_ctor 3. Some performance regressions GCC/LLC (2.6 -> 2.7), but keep in mind that I wasn't using GCC 4.4.3 as comparison for llvm 2.6! MultiSource/Applications/hexxagon/hexxagon 1.22 -> 1.14 MultiSource/Applications/lua/lua 0.91 -> 0.84 MultiSource/Applications/obsequi/Obsequi 0.93 -> 0.86 MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk 1.01 -> 0.91 MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow 0.94 -> 0.75 MultiSource/Benchm...

...he float-variants. > > +1 > > The second chart shows relative code size increase (vertical axis) vs relative performance improvement (horizontal axis): > I manually checked the cause of the 3 biggest performance regressions (proprietary benchmark1: -13.70%; MultiSource/Applications/hexxagon/hexxagon: -10.10%; MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow > -5.23%). > For the proprietary benchmark and hexxagon, the code generation didn't change for the hottest parts, so probably is caused by micro-architectural effects of code layout changes. > > This is alway...

...and a code size difference larger than 1%. Negative numbers means smaller code, positive larger. Targeting i386 PIC -O2: -7.3% MultiSource/Benchmarks/MiBench/security-rijndael/Output/security-rijndael -7.2% MultiSource/Benchmarks/Prolangs-C/simulator/Output/simulator -5.3% MultiSource/Applications/hexxagon/Output/hexxagon -5.2% MultiSource/Applications/SIBsim4/Output/SIBsim4 -4.8% MultiSource/Benchmarks/MallocBench/cfrac/Output/cfrac -4.1% MultiSource/Applications/d/Output/make_dparser -4.0% MultiSource/Applications/JM/ldecod/Output/ldecod -3.9% External/Nurbs/Output/nurbs -3.7% MultiSource/Benchmark...

...ut-C++/wc > TEST-FAIL: cbe /SingleSource/Benchmarks/Shootout-C++/wc > TEST-FAIL: llc /SingleSource/Benchmarks/Misc-C++/bigfib > TEST-FAIL: jit /SingleSource/Benchmarks/Misc-C++/bigfib > TEST-FAIL: cbe /SingleSource/Benchmarks/Misc-C++/bigfib > TEST-FAIL: llc /MultiSource/Applications/hexxagon/hexxagon > TEST-FAIL: jit /MultiSource/Applications/hexxagon/hexxagon > TEST-FAIL: cbe /MultiSource/Applications/hexxagon/hexxagon > TEST-FAIL: llc /MultiSource/Applications/oggenc/oggenc > TEST-FAIL: jit /MultiSource/Applications/oggenc/oggenc > TEST-FAIL: cbe /MultiSource/Applicati...

...t; float-variants. > +1 The second chart shows relative code size increase (vertical axis) vs > relative performance improvement (horizontal axis): > I manually checked the cause of the 3 biggest performance regressions > (proprietary benchmark1: -13.70%; > MultiSource/Applications/hexxagon/hexxagon: -10.10%; > MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow -5.23%). > For the proprietary benchmark and hexxagon, the code generation didn't > change for the hottest parts, so probably is caused by micro-architectural > effects of code layout changes. > This is...

...egression/C++/ofstream_ctor > This isn't part of our release criteria. So, these are not release blockers. > 3. Some performance regressions GCC/LLC (2.6 -> 2.7), but keep in mind > that I wasn't using GCC 4.4.3 as comparison for llvm 2.6! > > MultiSource/Applications/hexxagon/hexxagon 1.22 -> 1.14 > MultiSource/Applications/lua/lua 0.91 -> 0.84 > MultiSource/Applications/obsequi/Obsequi 0.93 -> 0.86 > MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk 1.01 -> 0.91 > MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow 0.94 -> 0.7...

...eSource/Benchmarks/Shootout-C++/wc TEST-FAIL: cbe /SingleSource/Benchmarks/Shootout-C++/wc TEST-FAIL: llc /SingleSource/Benchmarks/Misc-C++/bigfib TEST-FAIL: jit /SingleSource/Benchmarks/Misc-C++/bigfib TEST-FAIL: cbe /SingleSource/Benchmarks/Misc-C++/bigfib TEST-FAIL: llc /MultiSource/Applications/hexxagon/hexxagon TEST-FAIL: jit /MultiSource/Applications/hexxagon/hexxagon TEST-FAIL: cbe /MultiSource/Applications/hexxagon/hexxagon TEST-FAIL: llc /MultiSource/Applications/oggenc/oggenc TEST-FAIL: jit /MultiSource/Applications/oggenc/oggenc TEST-FAIL: cbe /MultiSource/Applications/oggenc/oggenc TEST-FA...

LLVMers, The LLVM 1.9 Prerelease is available for testing: http://llvm.org/prereleases/1.9/ If anyone can spare some time, please download the appropriate tarballs for your platform and test the release (at least with make check). I'd also appreciate any documentation reviews. Please note that llvm-gcc3 on x86 may not have a clean dejagnu run. You should see one XPASS for

.../perf/db_default/v4/nts/1283/graph?test.162=3> 2.35% 0.4337 > 0.4439 0.0002 1.79% 0.0002 > MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000 > <http://llvm.org/perf/db_default/v4/nts/1283/graph?test.310=3> 2.32% 2.7068 > 2.7695 0.0071 1.48% 0.0071 > MultiSource/Applications/hexxagon/hexxagon > <http://llvm.org/perf/db_default/v4/nts/1283/graph?test.243=3> 2.28% 0.9968 > 1.0195 0.0005 2.89% 0.0005 > MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset > <http://llvm.org/perf/db_default/v4/nts/1283/graph?test.392=3> 2.22% 4.3907 > 4.4882 0....

Thanks for running these Kristof! I'd still like to hear from Apple, and if we can get a few more x86 micro-architectures covered that'd be great, but it looks like -O3 is uncontroversial, and the question is whether this makes sense at O2... To me, it would help a lot to know the actual breakdown of benchmarks such as yours Kristof (as they seem to have more codesize impact than others

...nts/1283/graph?test.162=3> 2.35% 0.4337 >> 0.4439 0.0002 1.79% 0.0002 >> MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000 >> <http://llvm.org/perf/db_default/v4/nts/1283/graph?test.310=3> 2.32% 2.7068 >> 2.7695 0.0071 1.48% 0.0071 >> MultiSource/Applications/hexxagon/hexxagon >> <http://llvm.org/perf/db_default/v4/nts/1283/graph?test.243=3> 2.28% 0.9968 >> 1.0195 0.0005 2.89% 0.0005 >> MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset >> <http://llvm.org/perf/db_default/v4/nts/1283/graph?test.392=3> 2.22% 4.390...

...162=3> 2.35% 0.4337 >>> 0.4439 0.0002 1.79% 0.0002 >>> MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000 >>> <http://llvm.org/perf/db_default/v4/nts/1283/graph?test.310=3> 2.32% 2.7068 >>> 2.7695 0.0071 1.48% 0.0071 >>> MultiSource/Applications/hexxagon/hexxagon >>> <http://llvm.org/perf/db_default/v4/nts/1283/graph?test.243=3> 2.28% 0.9968 >>> 1.0195 0.0005 2.89% 0.0005 >>> MultiSource/Benchmarks/MiBench/consumer-typeset/consumer-typeset >>> <http://llvm.org/perf/db_default/v4/nts/1283/graph?test.392=3...