\n<\/code><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\nDefault Optimization Behavior<\/h2>\n
Most open source programs that compile from source code use the -O2 or -O3 flags. This will result in fast code that can run on any compute node on the SCC. The -march=native, which is sometimes used by default in open source programs, can be problematic when run on the login nodes as they are Broadwell architecture CPUs which support AVX2 instructions. Codes compiled with -march=native on a login node will only be able to execute on Broadwell architecture compute nodes on the SCC.<\/p>\n
Recommendations<\/h2>\n
Most codes will be well-optimized with the -O2 or -O3 flags plus the -msse4.2 flag. Programs that involve intensive floating-point calculations inside of loops can additionally be compiled with the -xarch<\/em> flag.\u00a0 For maximum cross-compatibility across the SCC compute nodes and probable highest performance a combination of flags should be used:<\/p>\ngcc -O3 -march=sandybridge -mtune=intel -c mycode.cpp<\/code><\/pre>\nNote that selecting specific SIMD instructions with the -mavx* flag or -march=arch<\/em> flag will restrict compatibility with compute nodes unless the job is submitted with this qsub flag: -l cpu_arch=compatible_arch<\/em>. The compatible_arch<\/em> value is an architecture name that matches the SIMD instructions.\u00a0 Alternatively, the qsub flag -l cpu_arch=\\!compatible_arch<\/em> can be used to exclude an incompatible architecture:<\/p>\ngcc -O3 -ffastmath -march=broadwell mycode.cpp -o mycode\r\nqsub -l cpu_arch=broadwell -b y mycode\r\n# OR...as the -march=broadwell has produced AVX2 instructions\r\n# select nodes that support AVX2.\r\nqsub -l avx2 -b y mycode<\/code><\/pre>\nAnother option is to compile the code as part of a batch job which completely avoids any architectural issues and allows for the maximum amount of optimizations. For example, a job that is submitted to run on a Buy-in node equipped with an Ivybridge architecture CPU could be compiled with tunings for that node. As a precaution the source is copied into $TMPDIR:<\/p>\n
Example Batch Script to Recompile on a Compute Node<\/strong><\/h4><\/p>\n
#!\/bin\/bash -l\r\n#$ -l cpu_arch=ivybridge\r\nmodule load gcc\/9.3.0<\/code><\/pre>\n# Copy the source to $TMPDIR to avoid interaction\r\n# with other jobs running\r\ncp -R \/projectnb\/myproject\/mysource $TMPDIR\r\ncd $TMPDIR\/mysource\r\n<\/code><\/pre>\ngcc -O3 -march=native -ffastmath -c file1.c \r\ngcc -O3 -march=native -ffastmath -c file2.c \r\ngcc -o myexe file1.o file2.o -lm \r\nmyexe arg1 arg2 ....<\/code><\/pre>\n<\/div>\n<\/div>\n\n","protected":false},"excerpt":{"rendered":"
The GNU family of compilers produce highly optimized code for Intel and AMD CPUs.\u00a0 As the LLVM C and C++ compilers deliberately share the majority of their optimization flags with their GNU equivalents the information here applies to both sets of compilers.\u00a0 As with all compilers, programs compiled with optimization should have their output double-checked…<\/p>\n","protected":false},"author":1692,"featured_media":0,"parent":78157,"menu_order":5,"comment_status":"closed","ping_status":"closed","template":"","meta":[],"_links":{"self":[{"href":"https:\/\/www.bu.edu\/tech\/wp-json\/wp\/v2\/pages\/107605"}],"collection":[{"href":"https:\/\/www.bu.edu\/tech\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.bu.edu\/tech\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/tech\/wp-json\/wp\/v2\/users\/1692"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/tech\/wp-json\/wp\/v2\/comments?post=107605"}],"version-history":[{"count":10,"href":"https:\/\/www.bu.edu\/tech\/wp-json\/wp\/v2\/pages\/107605\/revisions"}],"predecessor-version":[{"id":161263,"href":"https:\/\/www.bu.edu\/tech\/wp-json\/wp\/v2\/pages\/107605\/revisions\/161263"}],"up":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/tech\/wp-json\/wp\/v2\/pages\/78157"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/tech\/wp-json\/wp\/v2\/media?parent=107605"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}