[Python-Dev] Profile Guided Optimization active by-default
Hi All, This is Alecsandru from Server Scripting Languages Optimization team at Intel Corporation. I would like to submit a request to turn-on Profile Guided Optimization or PGO as the default build option for Python (both 2.7 and 3.6), given its performance benefits on a wide variety of workloads and hardware. For instance, as shown from attached sample performance results from the Grand Unified Python Benchmark, >20% speed up was observed. In addition, we are seeing 2-9% performance boost from OpenStack/Swift where more than 60% of the codes are in Python 2.7. Our analysis indicates the performance gain was mainly due to reduction of icache misses and CPU front-end stalls. Attached is the Makefile patches that modify the all build target and adds a new one called "disable-profile-opt". We built and tested this patch for Python 2.7 and 3.6 on our Linux machines (CentOS 7/Ubuntu Server 14.04, Intel Xeon Haswell/Broadwell with 18/8 cores). We use "regrtest" suite for training as it provides the best performance improvement. Some of the test programs in the suite may fail which leads to build fail. One solution is to disable the specific failed test using the "-x " flag (as shown in the patch) Steps to apply the patch: 1. hg clone https://hg.python.org/cpython cpython 2. cd cpython 3. hg update 2.7 (needed for 2.7 only) 4. Copy *.patch to the current directory 5. patch < python2.7-pgo.patch (or patch < python3.6-pgo.patch) 6. ./configure 7. make To disable PGO 7b. make disable-profile-opt In the following, please find our sample performance results from latest XEON machine, XEON Broadwell EP. Hardware (HW): Intel XEON (Broadwell) 8 Cores BIOS settings: Intel Turbo Boost Technology: false Hyper-Threading: false Operating System: Ubuntu 14.04.3 LTS trusty OS configuration: CPU freq set at fixed: 2.6GHz by echo 260 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_min_freq echo 260 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_max_freq Address Space Layout Randomization (ASLR) disabled (to reduce run to run variation) by echo 0 > /proc/sys/kernel/randomize_va_space GCC version:gcc version 4.8.4 (Ubuntu 4.8.4-2ubuntu1~14.04) Benchmark: Grand Unified Python Benchmark (GUPB) GUPB Source: https://hg.python.org/benchmarks/ Python2.7 results: Python source: hg clone https://hg.python.org/cpython cpython Python Source: hg update 2.7 hg id: 0511b1165bb6 (2.7) hg id -r 'ancestors(.) and tag()': 15c95b7d81dc (2.7) v2.7.10 hg --debug id -i: 0511b1165bb6cf40ada0768a7efc7ba89316f6a5 Benchmarks Speedup(%) simple_logging 20 raytrace20 silent_logging 19 richards19 chaos 16 formatted_logging 16 json_dump 15 hexiom2 13 pidigits12 slowunpickle12 django_v2 12 unpack_sequence 11 float 11 mako11 slowpickle 11 fastpickle 11 django 11 go 10 json_dump_v210 pathlib 10 regex_compile 10 pybench 9.9 etree_process 9 regex_v88 bzr_startup 8 2to38 slowspitfire8 telco 8 pickle_list 8 fannkuch8 etree_iterparse 8 nqueens 8 mako_v2 8 etree_generate 8 call_method_slots 7 html5lib_warmup 7 html5lib7 nbody 7 spectral_norm 7 spambayes 7 fastunpickle6 meteor_contest 6 chameleon 6 rietveld6 tornado_http5 unpickle_list 5 pickle_dict 4 regex_effbot3 normal_startup 3 startup_nosite 3 etree_parse 2 call_method_unknown 2 call_simple 1 json_load 1 call_method 1 Python3.6 results Python source: hg clone https://hg.python.org/cpython cpython hg id: 96d016f78726 tip hg id -r 'ancestors(.) and tag()': 1a58b1227501 (3.5) v3.5.0rc1 hg --debug id -i: 96d016f78726afbf66d396f084b291ea43792af1 Benchmark Speedup(%) fastunpickle22.94 fastpickle 21.67 json_load 17.64 simple_logging 17.49 meteor_cont
Re: [Python-Dev] Profile Guided Optimization active by-default
Hello and thank you for your feedback. We have measured PGO gain using other workloads also. Our initial choice for this optimization was pybench, but the speedup obtained was lower than using regrtest and it didn't cover a lot of Python scenarios. Instead, regrtest has an uniform distribution for the tests and the resulting binary is overall much faster than the default, or trained using other workloads, and thus covering a larger pool of Python loads. This optimization was also tested on a production environments running OpenStack Swift and got up to 9% improvements. The reason we proposed this target to be always on is that the obtained optimized binary is better out of the box for the general cases. Alecsandru From: gvanros...@gmail.com [mailto:gvanros...@gmail.com] On Behalf Of Guido van Rossum Sent: Saturday, August 22, 2015 7:15 PM To: Patrascu, Alecsandru Cc: python-dev@python.org Subject: Re: [Python-Dev] Profile Guided Optimization active by-default How about we first add a new Makefile target that enables PGO, without turning it on by default? Then later we can enable it by default. Also, I have my doubts about regrtest. How sure are we that it represents a typical Python load? Tests are often using a different mix of operations than production code. On Sat, Aug 22, 2015 at 7:46 AM, Patrascu, Alecsandru wrote: Hi All, This is Alecsandru from Server Scripting Languages Optimization team at Intel Corporation. I would like to submit a request to turn-on Profile Guided Optimization or PGO as the default build option for Python (both 2.7 and 3.6), given its performance benefits on a wide variety of workloads and hardware. For instance, as shown from attached sample performance results from the Grand Unified Python Benchmark, >20% speed up was observed. In addition, we are seeing 2-9% performance boost from OpenStack/Swift where more than 60% of the codes are in Python 2.7. Our analysis indicates the performance gain was mainly due to reduction of icache misses and CPU front-end stalls. Attached is the Makefile patches that modify the all build target and adds a new one called "disable-profile-opt". We built and tested this patch for Python 2.7 and 3.6 on our Linux machines (CentOS 7/Ubuntu Server 14.04, Intel Xeon Haswell/Broadwell with 18/8 cores). We use "regrtest" suite for training as it provides the best performance improvement. Some of the test programs in the suite may fail which leads to build fail. One solution is to disable the specific failed test using the "-x " flag (as shown in the patch) Steps to apply the patch: 1. hg clone https://hg.python.org/cpython cpython 2. cd cpython 3. hg update 2.7 (needed for 2.7 only) 4. Copy *.patch to the current directory 5. patch < python2.7-pgo.patch (or patch < python3.6-pgo.patch) 6. ./configure 7. make To disable PGO 7b. make disable-profile-opt In the following, please find our sample performance results from latest XEON machine, XEON Broadwell EP. Hardware (HW): Intel XEON (Broadwell) 8 Cores BIOS settings: Intel Turbo Boost Technology: false Hyper-Threading: false Operating System: Ubuntu 14.04.3 LTS trusty OS configuration: CPU freq set at fixed: 2.6GHz by echo 260 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_min_freq echo 260 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_max_freq Address Space Layout Randomization (ASLR) disabled (to reduce run to run variation) by echo 0 > /proc/sys/kernel/randomize_va_space GCC version: gcc version 4.8.4 (Ubuntu 4.8.4-2ubuntu1~14.04) Benchmark: Grand Unified Python Benchmark (GUPB) GUPB Source: https://hg.python.org/benchmarks/ Python2.7 results: Python source: hg clone https://hg.python.org/cpython cpython Python Source: hg update 2.7 hg id: 0511b1165bb6 (2.7) hg id -r 'ancestors(.) and tag()': 15c95b7d81dc (2.7) v2.7.10 hg --debug id -i: 0511b1165bb6cf40ada0768a7efc7ba89316f6a5 Benchmarks Speedup(%) simple_logging 20 raytrace 20 silent_logging 19 richards 19 chaos 16 formatted_logging 16 json_dump 15 hexiom2 13 pidigits 12 slowunpickle 12 django_v2 12 unpack_sequence 11 float 11 mako 11 slowpickle 11 fastpickle 11 django 11 go 10 json_dump_v2 10 pathlib 10 regex_compile 10 pybench 9.9 etree_process 9 regex_v8 8 bzr_startup 8 2t
Re: [Python-Dev] Profile Guided Optimization active by-default
This target replaces the existing one in the CPython Makefile, which now uses a quick run of pybench and the obtained binary does not perform well on general Python loads. I don't think is a good idea to add a by-default target that does PGO on dedicated workloads, like Django, because then it will perform better on that particular load and poorly on other. Of course, if any user has a dedicated workload for which he or she want to get the best benefit over PGO, it will have to run that training separately from the proposed one. Our proposal targets the broader audience that uses Python in various scenarios, and they will see an overall improvement after compiling Python from sources. Alecsandru From: Brett Cannon [mailto:br...@python.org] Sent: Saturday, August 22, 2015 7:25 PM To: gu...@python.org; Patrascu, Alecsandru Cc: python-dev@python.org Subject: Re: [Python-Dev] Profile Guided Optimization active by-default On Sat, Aug 22, 2015, 09:17 Guido van Rossum wrote: How about we first add a new Makefile target that enables PGO, without turning it on by default? Then later we can enable it by default. I agree. Updating the Makefile so it's easier to use PGO is great, but we should do a release with it as opt-in and go from there. Also, I have my doubts about regrtest. How sure are we that it represents a typical Python load? Tests are often using a different mix of operations than production code. That was also my question. You said that "it provides the best performance improvement", but compared to what; what else was tried? And what difference does it make to e.g. a Django app that is trained on their own simulated workload compared to using regrtest? IOW is regrtest displaying the best across-the-board performance because it stresses the largest swath of Python and thus catches generic patterns in the code but individuals could get better performance with a simulated workload? -Brett On Sat, Aug 22, 2015 at 7:46 AM, Patrascu, Alecsandru wrote: Hi All, This is Alecsandru from Server Scripting Languages Optimization team at Intel Corporation. I would like to submit a request to turn-on Profile Guided Optimization or PGO as the default build option for Python (both 2.7 and 3.6), given its performance benefits on a wide variety of workloads and hardware. For instance, as shown from attached sample performance results from the Grand Unified Python Benchmark, >20% speed up was observed. In addition, we are seeing 2-9% performance boost from OpenStack/Swift where more than 60% of the codes are in Python 2.7. Our analysis indicates the performance gain was mainly due to reduction of icache misses and CPU front-end stalls. Attached is the Makefile patches that modify the all build target and adds a new one called "disable-profile-opt". We built and tested this patch for Python 2.7 and 3.6 on our Linux machines (CentOS 7/Ubuntu Server 14.04, Intel Xeon Haswell/Broadwell with 18/8 cores). We use "regrtest" suite for training as it provides the best performance improvement. Some of the test programs in the suite may fail which leads to build fail. One solution is to disable the specific failed test using the "-x " flag (as shown in the patch) Steps to apply the patch: 1. hg clone https://hg.python.org/cpython cpython 2. cd cpython 3. hg update 2.7 (needed for 2.7 only) 4. Copy *.patch to the current directory 5. patch < python2.7-pgo.patch (or patch < python3.6-pgo.patch) 6. ./configure 7. make To disable PGO 7b. make disable-profile-opt In the following, please find our sample performance results from latest XEON machine, XEON Broadwell EP. Hardware (HW): Intel XEON (Broadwell) 8 Cores BIOS settings: Intel Turbo Boost Technology: false Hyper-Threading: false Operating System: Ubuntu 14.04.3 LTS trusty OS configuration: CPU freq set at fixed: 2.6GHz by echo 260 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_min_freq echo 260 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_max_freq Address Space Layout Randomization (ASLR) disabled (to reduce run to run variation) by echo 0 > /proc/sys/kernel/randomize_va_space GCC version: gcc version 4.8.4 (Ubuntu 4.8.4-2ubuntu1~14.04) Benchmark: Grand Unified Python Benchmark (GUPB) GUPB Source: https://hg.python.org/benchmarks/ Python2.7 results: Python source: hg clone https://hg.python.org/cpython cpython Python Source: hg update 2.7 hg id: 0511b1165bb6 (2.7) hg id -r 'ancestors(.) and tag()': 15c95b7d81dc (2.7) v2.7.10 hg --debug id -i: 0511b1165bb6cf40ada0768a7efc7ba89316f6a5 Benchmarks Speedup(%) simple_logging 20 raytrace 20 silent_logging 19 richards 19 chaos
Re: [Python-Dev] Profile Guided Optimization active by-default
A trial period on numerous other Python loads in which the provided patches are tested is welcomed, to be sure that it works as presented. Yes, it is easy to change it to use a different training set, or subsets of the regrtest by adding additional parameters to the line inside the Makefile that runs it. Now, the attached patches run the full regrtest suite. Alecsandru From: gvanros...@gmail.com [mailto:gvanros...@gmail.com] On Behalf Of Guido van Rossum Sent: Saturday, August 22, 2015 7:56 PM To: Patrascu, Alecsandru Cc: python-dev@python.org Subject: Re: [Python-Dev] Profile Guided Optimization active by-default I'm sorry, but we're just not going to turn this on by default without doing a trial period ourselves. Your (and Intel's) contribution is very welcome, but in order to establish trust in a feature like this, an optional trial period is absolutely required. Regarding the training set, I agree that regrtest sounds to be better than pybench. If we make this an opt-in change, we can experiment with different training sets easily. (Also, I haven't seen the patch yet, but I presume it's easy to use a different training set? Experimentation should be encouraged.) On Sat, Aug 22, 2015 at 9:40 AM, Patrascu, Alecsandru wrote: Hello and thank you for your feedback. We have measured PGO gain using other workloads also. Our initial choice for this optimization was pybench, but the speedup obtained was lower than using regrtest and it didn't cover a lot of Python scenarios. Instead, regrtest has an uniform distribution for the tests and the resulting binary is overall much faster than the default, or trained using other workloads, and thus covering a larger pool of Python loads. This optimization was also tested on a production environments running OpenStack Swift and got up to 9% improvements. The reason we proposed this target to be always on is that the obtained optimized binary is better out of the box for the general cases. Alecsandru From: gvanros...@gmail.com [mailto:gvanros...@gmail.com] On Behalf Of Guido van Rossum Sent: Saturday, August 22, 2015 7:15 PM To: Patrascu, Alecsandru Cc: python-dev@python.org Subject: Re: [Python-Dev] Profile Guided Optimization active by-default How about we first add a new Makefile target that enables PGO, without turning it on by default? Then later we can enable it by default. Also, I have my doubts about regrtest. How sure are we that it represents a typical Python load? Tests are often using a different mix of operations than production code. On Sat, Aug 22, 2015 at 7:46 AM, Patrascu, Alecsandru wrote: Hi All, This is Alecsandru from Server Scripting Languages Optimization team at Intel Corporation. I would like to submit a request to turn-on Profile Guided Optimization or PGO as the default build option for Python (both 2.7 and 3.6), given its performance benefits on a wide variety of workloads and hardware. For instance, as shown from attached sample performance results from the Grand Unified Python Benchmark, >20% speed up was observed. In addition, we are seeing 2-9% performance boost from OpenStack/Swift where more than 60% of the codes are in Python 2.7. Our analysis indicates the performance gain was mainly due to reduction of icache misses and CPU front-end stalls. Attached is the Makefile patches that modify the all build target and adds a new one called "disable-profile-opt". We built and tested this patch for Python 2.7 and 3.6 on our Linux machines (CentOS 7/Ubuntu Server 14.04, Intel Xeon Haswell/Broadwell with 18/8 cores). We use "regrtest" suite for training as it provides the best performance improvement. Some of the test programs in the suite may fail which leads to build fail. One solution is to disable the specific failed test using the "-x " flag (as shown in the patch) Steps to apply the patch: 1. hg clone https://hg.python.org/cpython cpython 2. cd cpython 3. hg update 2.7 (needed for 2.7 only) 4. Copy *.patch to the current directory 5. patch < python2.7-pgo.patch (or patch < python3.6-pgo.patch) 6. ./configure 7. make To disable PGO 7b. make disable-profile-opt In the following, please find our sample performance results from latest XEON machine, XEON Broadwell EP. Hardware (HW): Intel XEON (Broadwell) 8 Cores BIOS settings: Intel Turbo Boost Technology: false Hyper-Threading: false Operating System: Ubuntu 14.04.3 LTS trusty OS configuration: CPU freq set at fixed: 2.6GHz by echo 260 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_min_freq echo 260 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_max_freq Address Space Layout Randomization (ASLR) disabled (to reduce run to run variation) by echo 0 > /proc/sys/kernel/randomize_va_space GCC version: gcc
Re: [Python-Dev] Profile Guided Optimization active by-default
Yes, the results are measured from running the benchmarks from the repo [1]. Furthermore, this optimization is generic and can handle any kind of changes in hardware or the CPython 2/3 source code. We are not adding to or modifying regrtest and our rule will be applied on the latest tests existing in the CPython repo. Since they are up to date and being easy to be executed, this proposal makes sure that users will always take benefit from them. [1] https://hg.python.org/benchmarks/ Alecsandru From: Eric Snow [mailto:ericsnowcurren...@gmail.com] Sent: Saturday, August 22, 2015 8:26 PM To: Patrascu, Alecsandru Cc: Python-Dev Subject: Re: [Python-Dev] Profile Guided Optimization active by-default On Aug 22, 2015 9:02 AM, "Patrascu, Alecsandru" wrote: [snip] > For instance, as shown from attached sample performance results from the > Grand Unified Python Benchmark, >20% speed up was observed. Are you referring to the tests in the benchmarks repo? [1] How does the real-world performance improvement compare with other languages you are targeting for optimization? And thanks for working on this! I have several more questions: What sorts of future changes in CPython's code might interfere with your optimizations? What future additions might stand to benefit? What changes in existing code might improve optimization opportunities? What is the added maintenance burden of the optimizations on CPython, if any? What is the performance impact on non-Intel architectures? What about older Intel architectures? ...and future ones? What is Intel's commitment to supporting these (or other) optimizations in the future? How is the practical EOL of the optimizations managed? Finally, +1 on adding an opt-in Makefile target rather than enabling the optimizations by default. Thanks again! -eric [1] https://hg.python.org/benchmarks/ ___ Python-Dev mailing list Python-Dev@python.org https://mail.python.org/mailman/listinfo/python-dev Unsubscribe: https://mail.python.org/mailman/options/python-dev/archive%40mail-archive.com
Re: [Python-Dev] Profile Guided Optimization active by-default
Thank you Stefan for also pointing out the importance of regrtest as a good training set for building Python. Indeed, Ubuntu delivers in their repos the Python2/3 binaries already optimized using PGO based on regrtest. Alecsandru -Original Message- From: Python-Dev [mailto:python-dev-bounces+alecsandru.patrascu=intel@python.org] On Behalf Of Stefan Behnel Sent: Saturday, August 22, 2015 8:25 PM To: python-dev@python.org Subject: Re: [Python-Dev] Profile Guided Optimization active by-default Guido van Rossum schrieb am 22.08.2015 um 18:55: > Regarding the training set, I agree that regrtest sounds to be better > than pybench. If we make this an opt-in change, we can experiment with > different training sets easily. (Also, I haven't seen the patch yet, > but I presume it's easy to use a different training set? It's just one command in one line, yes. > Experimentation should be encouraged.) A well chosen training set can have a notable impact on PGO compiled code in general, and switching from pybench to regrtests should make such a difference. However, since CPython's overall performance is mostly determined by the interpreter loop, general object operations (getattr!) and the basic builtin types, of which the regression test suite makes plenty of use, it is rather unlikely that other training sets would provide substantially better performance for Python code execution. Note also that Ubuntu has shipped PGO builds based on the regrtests for years, and they seemed to be quite happy with it. Stefan ___ Python-Dev mailing list Python-Dev@python.org https://mail.python.org/mailman/listinfo/python-dev Unsubscribe: https://mail.python.org/mailman/options/python-dev/alecsandru.patrascu%40intel.com ___ Python-Dev mailing list Python-Dev@python.org https://mail.python.org/mailman/listinfo/python-dev Unsubscribe: https://mail.python.org/mailman/options/python-dev/archive%40mail-archive.com
Re: [Python-Dev] Profile Guided Optimization active by-default
I'm sorry, I forgot to mention this, I already opened an issue and the patches are uploaded [1]. [1] http://bugs.python.org/issue24915 From: Brett Cannon [mailto:br...@python.org] Sent: Saturday, August 22, 2015 9:00 PM To: Patrascu, Alecsandru; python-dev@python.org Subject: Re: [Python-Dev] Profile Guided Optimization active by-default I just realized I didn't see anyone say it, but please upload the patches to bugs.Python.org for easier tracking and reviewing. On Sat, Aug 22, 2015, 08:01 Patrascu, Alecsandru wrote: Hi All, This is Alecsandru from Server Scripting Languages Optimization team at Intel Corporation. I would like to submit a request to turn-on Profile Guided Optimization or PGO as the default build option for Python (both 2.7 and 3.6), given its performance benefits on a wide variety of workloads and hardware. For instance, as shown from attached sample performance results from the Grand Unified Python Benchmark, >20% speed up was observed. In addition, we are seeing 2-9% performance boost from OpenStack/Swift where more than 60% of the codes are in Python 2.7. Our analysis indicates the performance gain was mainly due to reduction of icache misses and CPU front-end stalls. Attached is the Makefile patches that modify the all build target and adds a new one called "disable-profile-opt". We built and tested this patch for Python 2.7 and 3.6 on our Linux machines (CentOS 7/Ubuntu Server 14.04, Intel Xeon Haswell/Broadwell with 18/8 cores). We use "regrtest" suite for training as it provides the best performance improvement. Some of the test programs in the suite may fail which leads to build fail. One solution is to disable the specific failed test using the "-x " flag (as shown in the patch) Steps to apply the patch: 1. hg clone https://hg.python.org/cpython cpython 2. cd cpython 3. hg update 2.7 (needed for 2.7 only) 4. Copy *.patch to the current directory 5. patch < python2.7-pgo.patch (or patch < python3.6-pgo.patch) 6. ./configure 7. make To disable PGO 7b. make disable-profile-opt In the following, please find our sample performance results from latest XEON machine, XEON Broadwell EP. Hardware (HW): Intel XEON (Broadwell) 8 Cores BIOS settings: Intel Turbo Boost Technology: false Hyper-Threading: false Operating System: Ubuntu 14.04.3 LTS trusty OS configuration: CPU freq set at fixed: 2.6GHz by echo 260 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_min_freq echo 260 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_max_freq Address Space Layout Randomization (ASLR) disabled (to reduce run to run variation) by echo 0 > /proc/sys/kernel/randomize_va_space GCC version: gcc version 4.8.4 (Ubuntu 4.8.4-2ubuntu1~14.04) Benchmark: Grand Unified Python Benchmark (GUPB) GUPB Source: https://hg.python.org/benchmarks/ Python2.7 results: Python source: hg clone https://hg.python.org/cpython cpython Python Source: hg update 2.7 hg id: 0511b1165bb6 (2.7) hg id -r 'ancestors(.) and tag()': 15c95b7d81dc (2.7) v2.7.10 hg --debug id -i: 0511b1165bb6cf40ada0768a7efc7ba89316f6a5 Benchmarks Speedup(%) simple_logging 20 raytrace 20 silent_logging 19 richards 19 chaos 16 formatted_logging 16 json_dump 15 hexiom2 13 pidigits 12 slowunpickle 12 django_v2 12 unpack_sequence 11 float 11 mako 11 slowpickle 11 fastpickle 11 django 11 go 10 json_dump_v2 10 pathlib 10 regex_compile 10 pybench 9.9 etree_process 9 regex_v8 8 bzr_startup 8 2to3 8 slowspitfire 8 telco 8 pickle_list 8 fannkuch 8 etree_iterparse 8 nqueens 8 mako_v2 8 etree_generate 8 call_method_slots 7 html5lib_warmup 7 html5lib 7 nbody 7 spectral_norm 7 spambayes 7 fastunpickle 6 meteor_contest 6 chameleon 6 rietveld 6 tornado_http 5 unpickle_list 5 pickle_dict 4 regex_effbot 3 normal_startup 3 startup_nosite 3 etree_parse 2 call_method_unknown 2 call_simple 1
Re: [Python-Dev] Profile Guided Optimization active by-default
I removed the zip file and uploaded the patches individually. Alecsandru From: Brett Cannon [mailto:br...@python.org] Sent: Sunday, August 23, 2015 4:47 AM To: Patrascu, Alecsandru; python-dev@python.org Subject: Re: [Python-Dev] Profile Guided Optimization active by-default On Sat, 22 Aug 2015 at 11:10 Patrascu, Alecsandru wrote: I'm sorry, I forgot to mention this, I already opened an issue and the patches are uploaded [1]. [1] http://bugs.python.org/issue24915 Great, thanks Alecandru. Do please follow Stefan's comment, though, and upload the patch files directly and not as a zip file. That way we can use our code review tool to do a proper review of the patches. -Brett From: Brett Cannon [mailto:br...@python.org] Sent: Saturday, August 22, 2015 9:00 PM To: Patrascu, Alecsandru; python-dev@python.org Subject: Re: [Python-Dev] Profile Guided Optimization active by-default I just realized I didn't see anyone say it, but please upload the patches to bugs.Python.org for easier tracking and reviewing. On Sat, Aug 22, 2015, 08:01 Patrascu, Alecsandru wrote: Hi All, This is Alecsandru from Server Scripting Languages Optimization team at Intel Corporation. I would like to submit a request to turn-on Profile Guided Optimization or PGO as the default build option for Python (both 2.7 and 3.6), given its performance benefits on a wide variety of workloads and hardware. For instance, as shown from attached sample performance results from the Grand Unified Python Benchmark, >20% speed up was observed. In addition, we are seeing 2-9% performance boost from OpenStack/Swift where more than 60% of the codes are in Python 2.7. Our analysis indicates the performance gain was mainly due to reduction of icache misses and CPU front-end stalls. Attached is the Makefile patches that modify the all build target and adds a new one called "disable-profile-opt". We built and tested this patch for Python 2.7 and 3.6 on our Linux machines (CentOS 7/Ubuntu Server 14.04, Intel Xeon Haswell/Broadwell with 18/8 cores). We use "regrtest" suite for training as it provides the best performance improvement. Some of the test programs in the suite may fail which leads to build fail. One solution is to disable the specific failed test using the "-x " flag (as shown in the patch) Steps to apply the patch: 1. hg clone https://hg.python.org/cpython cpython 2. cd cpython 3. hg update 2.7 (needed for 2.7 only) 4. Copy *.patch to the current directory 5. patch < python2.7-pgo.patch (or patch < python3.6-pgo.patch) 6. ./configure 7. make To disable PGO 7b. make disable-profile-opt In the following, please find our sample performance results from latest XEON machine, XEON Broadwell EP. Hardware (HW): Intel XEON (Broadwell) 8 Cores BIOS settings: Intel Turbo Boost Technology: false Hyper-Threading: false Operating System: Ubuntu 14.04.3 LTS trusty OS configuration: CPU freq set at fixed: 2.6GHz by echo 260 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_min_freq echo 260 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_max_freq Address Space Layout Randomization (ASLR) disabled (to reduce run to run variation) by echo 0 > /proc/sys/kernel/randomize_va_space GCC version: gcc version 4.8.4 (Ubuntu 4.8.4-2ubuntu1~14.04) Benchmark: Grand Unified Python Benchmark (GUPB) GUPB Source: https://hg.python.org/benchmarks/ Python2.7 results: Python source: hg clone https://hg.python.org/cpython cpython Python Source: hg update 2.7 hg id: 0511b1165bb6 (2.7) hg id -r 'ancestors(.) and tag()': 15c95b7d81dc (2.7) v2.7.10 hg --debug id -i: 0511b1165bb6cf40ada0768a7efc7ba89316f6a5 Benchmarks Speedup(%) simple_logging 20 raytrace 20 silent_logging 19 richards 19 chaos 16 formatted_logging 16 json_dump 15 hexiom2 13 pidigits 12 slowunpickle 12 django_v2 12 unpack_sequence 11 float 11 mako 11 slowpickle 11 fastpickle 11 django 11 go 10 json_dump_v2 10 pathlib 10 regex_compile 10 pybench 9.9 etree_process 9 regex_v8 8 bzr_startup 8 2to3 8 slowspitfire 8 telco 8 pickle_list 8 fannkuch 8 etree_iterparse 8 nqueens 8 mako_v2 8 etree_generate 8
Re: [Python-Dev] Profile Guided Optimization active by-default
Indeed, as Gregory well mentioned, PGO is unrelated to a particular CPU on which we do profiling. From: Python-Dev [mailto:python-dev-bounces+alecsandru.patrascu=intel@python.org] On Behalf Of Gregory P. Smith Sent: Tuesday, August 25, 2015 7:44 PM To: Xavier Combelle; python-dev@python.org Subject: Re: [Python-Dev] Profile Guided Optimization active by-default PGO is unrelated to the particular CPU the profiling is done on. (It is conceivable that it'd make a small difference but I've never observed that in practice) On Tue, Aug 25, 2015, 9:28 AM Xavier Combelle wrote: Pardon me if I'm not in the right place to ask the following naive question. (say me if it's the case) Does Profile Guided Optimization performance improvements are specific to the chip where the built is done or the performance is better on a larger set of chips? ___ Python-Dev mailing list Python-Dev@python.org https://mail.python.org/mailman/listinfo/python-dev Unsubscribe: https://mail.python.org/mailman/options/python-dev/archive%40mail-archive.com
[Python-Dev] Hash computation enhancement for {buffer, string, unicode}object
Hi All, This is Alecsandru from Server Scripting Languages Optimization team at Intel Corporation. I would like to submit a patch that improves the performance of the hash computation code on stringobject, bufferobject and unicodeobject. As can be seen from the attached sample performance results from the Grand Unified Python Benchmark, speedups up to 40% were observed. Furthermore, we see a 5-7% performance on OpenStack/Swift, where most of the code is in Python 2.7. Attached is the patch that modifies Object/stringobject.c, Object/bufferobject.c and Object/unicodeobject.c files. We built and tested this patch for Python 2.7 on our Linux machines (CentOS 7/Ubuntu Server 14.04, Intel Xeon Haswell/Broadwell with 18/8 cores). I've also opened an issue on the bug tracker: http://bugs.python.org/issue25106 Steps to apply the patch: 1. hg clone https://hg.python.org/cpython cpython 2. cd cpython 3. hg update 2.7 4. Copy hash8.patch to the current directory 5. hg import --no-commit hash8.patch 6. ./configure 7. make In the following, please find our sample performance results measured on a XEON Haswell machine. Hardware (HW): Intel XEON (Haswell) 18 Cores BIOS settings: Intel Turbo Boost Technology: false Hyper-Threading: false Operating System: Ubuntu 14.04.3 LTS trusty OS configuration: CPU freq set at fixed: 2.0GHz by echo 200 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_min_freq echo 200 > /sys/devices/system/cpu/cpu*/cpufreq/scaling_max_freq Address Space Layout Randomization (ASLR) disabled (to reduce run to run variation) by echo 0 > /proc/sys/kernel/randomize_va_space GCC version:gcc version 4.8.4 (Ubuntu 4.8.4-2ubuntu1~14.04) Benchmark: Grand Unified Python Benchmark (GUPB) GUPB Source: https://hg.python.org/benchmarks/ Python2.7 results: Python source: hg clone https://hg.python.org/cpython cpython Python Source: hg update 2.7 Benchmarks Speedup(%) unpack_sequence 40.32733766 chaos 24.84002537 chameleon 23.01392651 silent_logging 22.27202911 django 20.83842317 etree_process 20.46968294 nqueens 20.34234985 pathlib 19.63445919 pidigits19.34722148 etree_generate 19.25836634 pybench 19.06895825 django_v2 18.06073108 etree_iterparse 17.3797149 fannkuch17.08120879 pickle_list 16.60363602 raytrace16.0316265 slowpickle 15.86611184 pickle_dict 15.30447114 call_simple 14.42909032 richards14.2949594 simple_logging 13.6522626 etree_parse 13.38113097 json_dump_v212.2655 float 11.88164311 mako11.20606516 spectral_norm 11.04356684 hg_startup 10.57686164 mako_v2 10.37912648 slowunpickle10.24030714 go 10.03567319 meteor_contest 9.956231435 normal_startup 9.607401586 formatted_logging 9.601244811 html5lib9.082603748 2to38.741557816 html5lib_warmup 8.268150981 nbody 7.507012306 regex_compile 7.153922724 bzr_startup 7.140244739 telco 6.869411927 slowspitfire5.746323922 tornado_http5.24360121 rietveld3.865704876 regex_v83.777622219 hexiom2 3.586305282 json_dump 3.477551682 spambayes 3.183991854 fastunpickle2.971645347 fastpickle 0.673086656 regex_effbot0.127946837 json_load 0.023727176 Thank you, Alecsandru hash8-v01.patch Description: hash8-v01.patch ___ Python-Dev mailing list Python-Dev@python.org https://mail.python.org/mailman/listinfo/python-dev Unsubscribe: https://mail.python.org/mailman/options/python-dev/archive%40mail-archive.com
[Python-Dev] CPython build options for out-of-the box performance
Hi all, This is Alecsandru from the Dynamic Scripting Languages Optimization Team at Intel Corporation. I want to open a discussion regarding the way CPython is built, mainly the options that are available to the programmers. Analyzing the CPython ecosystem we can see that there are a lot of users that just download the sources and hit the commands "./configure", "make" and "make install" once and then continue using it with their Python scripts. One of the problems with this workflow it that the users do not benefit from the entire optimization features that are existing in the build system, such as PGO and LTO. Therefore, I propose a workflow, like the following. Assume some work has to be done into the CPython interpreter, a developer can do the following steps: A. Implementation and debugging phase. 1. The command "./configure PYDIST=debug" is ran once. It will enable the Py_DEBUG, -O0 and -g flags 2. The command "make" is ran once or multiple times B. Testing the implementation from step A, in a pre-release environment 1. The command "./configure PYDIST=devel" is ran once. It will disable the Py_DEBUG flags and will enable the -O3 and -g flags, and it is just like the current implementation in CPython 2. The command "make" is ran once or multiple times C. For any other CPython usage, for example distributing the interpreter, installing it inside an operating system, or just the majority of users who are not CPython developers and only want to compile it once and use it as-is: 1. The command "./configure" is ran once. Alternatively, the command "./configure PYDIST=release" can be used. It will disable all debugging functionality, enable the -O3 flag and will enable PGO and LTO. 2. The command "make" is ran once If you think this benefits CPython, I can create an issue and post the patches that enable all of the above. Thank you, Alecsandru ___ Python-Dev mailing list Python-Dev@python.org https://mail.python.org/mailman/listinfo/python-dev Unsubscribe: https://mail.python.org/mailman/options/python-dev/archive%40mail-archive.com
Re: [Python-Dev] CPython build options for out-of-the box performance
I've added the patches here[1], to be more clear about the workflow and the small modifications in the CPython build system. [1] http://bugs.python.org/issue26359 Thank you, Alecsandru > -Original Message- > From: Python-Dev [mailto:python-dev- > bounces+alecsandru.patrascu=intel@python.org] On Behalf Of Patrascu, > Alecsandru > Sent: Tuesday, February 9, 2016 1:45 PM > To: python-dev@python.org > Subject: [Python-Dev] CPython build options for out-of-the box performance > > Hi all, > > This is Alecsandru from the Dynamic Scripting Languages Optimization Team > at Intel Corporation. I want to open a discussion regarding the way > CPython is built, mainly the options that are available to the > programmers. Analyzing the CPython ecosystem we can see that there are a > lot of users that just download the sources and hit the commands > "./configure", "make" and "make install" once and then continue using it > with their Python scripts. One of the problems with this workflow it that > the users do not benefit from the entire optimization features that are > existing in the build system, such as PGO and LTO. > > Therefore, I propose a workflow, like the following. Assume some work has > to be done into the CPython interpreter, a developer can do the following > steps: > A. Implementation and debugging phase. > 1. The command "./configure PYDIST=debug" is ran once. It will enable > the Py_DEBUG, -O0 and -g flags > 2. The command "make" is ran once or multiple times > > B. Testing the implementation from step A, in a pre-release environment > 1. The command "./configure PYDIST=devel" is ran once. It will disable > the Py_DEBUG flags and will enable the -O3 and -g flags, and it is just > like the current implementation in CPython > 2. The command "make" is ran once or multiple times > > C. For any other CPython usage, for example distributing the interpreter, > installing it inside an operating system, or just the majority of users > who are not CPython developers and only want to compile it once and use it > as-is: > 1. The command "./configure" is ran once. Alternatively, the command > "./configure PYDIST=release" can be used. It will disable all debugging > functionality, enable the -O3 flag and will enable PGO and LTO. > 2. The command "make" is ran once > > If you think this benefits CPython, I can create an issue and post the > patches that enable all of the above. > > Thank you, > Alecsandru > > ___ > Python-Dev mailing list > Python-Dev@python.org > https://mail.python.org/mailman/listinfo/python-dev > Unsubscribe: https://mail.python.org/mailman/options/python- > dev/alecsandru.patrascu%40intel.com ___ Python-Dev mailing list Python-Dev@python.org https://mail.python.org/mailman/listinfo/python-dev Unsubscribe: https://mail.python.org/mailman/options/python-dev/archive%40mail-archive.com
