René's URL Explorer Experiment

{"@context":"https://schema.org","@type":"DiscussionForumPosting","headline":"empirical Roofline result abnormal","articleBody":"In my laptop(4cores/8hyperthreads), the L1 speed is about 795GB/s. far slower than the speed of the book.\r\n\r\n![image](https://github.com/essentialsofparallelcomputing/Chapter3/assets/5372812/266251ef-e528-486c-bc26-d7d4f34e56ce)\r\n\r\n\r\nMy environment:\r\nUbuntu 20.04, gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0, openmpi 4.0.7(compiled from source and install to /home/lili/soft/localinstall with --prefix)\r\n\r\nmy configure:\r\n```\r\n# Linux workstation, MPI and OpenMP (8-core Intel Xeon CPU E5530, 2.40 GHz)\r\n\r\nERT_RESULTS Results.madonna.lbl.gov.01\r\n\r\nERT_DRIVER  driver1\r\nERT_KERNEL  kernel1\r\n\r\nERT_MPI         True\r\nERT_MPI_CFLAGS\r\nERT_MPI_LDFLAGS\r\n\r\nERT_OPENMP         True\r\nERT_OPENMP_CFLAGS  -fopenmp\r\nERT_OPENMP_LDFLAGS -fopenmp\r\n\r\nERT_FLOPS   1,2,4,8,16\r\nERT_ALIGN   32\r\n\r\nERT_CC      /home/lili/soft/localinstall/bin/mpic++\r\nERT_CFLAGS  -O3 -march=native -msse3 -mavx2 -fpermissive -fstrict-aliasing -ftree-vectorize\r\n\r\nERT_LD      /home/lili/soft/localinstall/bin/mpic++\r\nERT_LDFLAGS\r\nERT_LDLIBS\r\n\r\nERT_PRECISION FP64\r\n\r\nERT_RUN     export OMP_NUM_THREADS=ERT_OPENMP_THREADS; /home/lili/soft/localinstall/bin/mpirun -np ERT_MPI_PROCS ERT_CODE\r\n\r\nERT_PROCS_THREADS  1-8\r\nERT_MPI_PROCS      1,2,4\r\nERT_OPENMP_THREADS 1,2,4,8\r\n\r\nERT_NUM_EXPERIMENTS 3\r\n\r\nERT_MEMORY_MAX 1073741824\r\n\r\nERT_WORKING_SET_MIN 1\r\n\r\nERT_TRIALS_MIN 1\r\n\r\nERT_GNUPLOT gnuplot\r\n```\r\n\r\n\r\n```\r\n$ lscpu\r\nArchitecture:                       x86_64\r\nCPU op-mode(s):                     32-bit, 64-bit\r\nByte Order:                         Little Endian\r\nAddress sizes:                      39 bits physical, 48 bits virtual\r\nCPU(s):                             8\r\nOn-line CPU(s) list:                0-7\r\nThread(s) per core:                 2\r\nCore(s) per socket:                 4\r\nSocket(s):                          1\r\nNUMA node(s):                       1\r\nVendor ID:                          GenuineIntel\r\nCPU family:                         6\r\nModel:                              158\r\nModel name:                         Intel(R) Core(TM) i7-7820HQ CPU @ 2.90GHz\r\nStepping:                           9\r\nCPU MHz:                            1469.562\r\nCPU max MHz:                        3900.0000\r\nCPU min MHz:                        800.0000\r\nBogoMIPS:                           5799.77\r\nVirtualization:                     VT-x\r\nL1d cache:                          128 KiB\r\nL1i cache:                          128 KiB\r\nL2 cache:                           1 MiB\r\nL3 cache:                           8 MiB\r\nNUMA node0 CPU(s):                  0-7\r\nVulnerability Gather data sampling: Mitigation; Microcode\r\nVulnerability Itlb multihit:        KVM: Mitigation: Split huge pages\r\nVulnerability L1tf:                 Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable\r\nVulnerability Mds:                  Mitigation; Clear CPU buffers; SMT vulnerable\r\nVulnerability Meltdown:             Mitigation; PTI\r\nVulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable\r\nVulnerability Retbleed:             Mitigation; IBRS\r\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp\r\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\r\nVulnerability Spectre v2:           Mitigation; IBRS, IBPB conditional, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected\r\nVulnerability Srbds:                Mitigation; Microcode\r\nVulnerability Tsx async abort:      Mitigation; Clear CPU buffers; SMT vulnerable\r\nFlags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse\r\n                                    2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopolog\r\n                                    y nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xt\r\n                                    pr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3\r\n                                    dnowprefetch cpuid_fault epb invpcid_single pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpi\r\n                                    d ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx rdseed adx smap clflushopt inte\r\n                                    l_pt xsaveopt xsavec xgetbv1 xsaves dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp md_clea\r\n                                    r flush_l1d arch_capabilities\r\n```\r\n","author":{"url":"https://github.com/fancyerii","@type":"Person","name":"fancyerii"},"datePublished":"2024-05-22T12:06:33.000Z","interactionStatistic":{"@type":"InteractionCounter","interactionType":"https://schema.org/CommentAction","userInteractionCount":0},"url":"https://github.com/5/Chapter3/issues/5"}