search

IntegralEquations / HMatrices.jl

A Julia library for hierarchical matrices
MIT License
37 stars 3 forks source link

Use a shared buffer for the partial aca routine #44

Closed maltezfaria closed 8 months ago

codecov[bot] commented 8 months ago

Codecov Report

Merging #44 (c7f806d) into main (93d66d1) will increase coverage by 0.16%. The diff coverage is 98.37%.

@@            Coverage Diff             @@
##             main      #44      +/-   ##
==========================================
+ Coverage   71.75%   71.92%   +0.16%     
==========================================
  Files          14       14              
  Lines        1728     1774      +46     
==========================================
+ Hits         1240     1276      +36     
- Misses        488      498      +10
Files Coverage Δ
src/HMatrices.jl 100.00% <100.00%> (ø)
src/hmatrix.jl 64.75% <100.00%> (+0.53%) :arrow_up:
src/lu.jl 96.77% <100.00%> (+1.77%) :arrow_up:
src/rkmatrix.jl 65.45% <ø> (+0.58%) :arrow_up:
src/triangular.jl 93.33% <100.00%> (ø)
src/utils.jl 73.97% <100.00%> (+3.66%) :arrow_up:
src/compressor.jl 83.51% <97.14%> (+1.94%) :arrow_up:
src/multiplication.jl 72.91% <95.83%> (-3.29%) :arrow_down:
github-actions[bot] commented 8 months ago
Benchmark result # Judge result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmarks: - Target: 30 Oct 2023 - 15:18 - Baseline: 30 Oct 2023 - 15:21 * Package commits: - Target: 2a9645 - Baseline: 17e3c4 * Julia commits: - Target: bed2cd - Baseline: bed2cd * Julia command flags: - Target: `-O3` - Baseline: `-O3` * Environment variables: - Target: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` - Baseline: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results A ratio greater than `1.0` denotes a possible regression (marked with :x:), while a ratio less than `1.0` denotes a possible improvement (marked with :white_check_mark:). Only significant results - results that indicate possible regressions or improvements - are shown below (thus, an empty table means that all benchmark results remained invariant between builds). | ID | time ratio | memory ratio | |-------------------------------------------------------------------|------------------------------|------------------------------| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 0.68 (5%) :white_check_mark: | 1.08 (1%) :x: | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.39 (5%) :x: | 1.71 (1%) :x: | | `["Laplace", "LU threads=false"]` | 1.05 (5%) :x: | 1.09 (1%) :x: | | `["Laplace", "LU threads=true"]` | 1.15 (5%) :x: | 1.09 (1%) :x: | | `["Laplace", "assemble threads=false"]` | 1.04 (5%) | 1.23 (1%) :x: | | `["Laplace", "assemble threads=true"]` | 1.52 (5%) :x: | 1.45 (1%) :x: | | `["Laplace", "gemv threads=false"]` | 1.12 (5%) :x: | 1.00 (1%) | | `["Laplace", "gemv threads=true"]` | 0.18 (5%) :white_check_mark: | 0.32 (1%) :white_check_mark: | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ### Target ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1094498 s 1376 s 211068 s 489994578 s 0 s Memory: 31.013160705566406 GB (21468.765625 MB free) Uptime: 1.22852256e6 sec Load Avg: 1.2 1.11 0.82 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` ### Baseline ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1096510 s 1376 s 211184 s 490051237 s 0 s Memory: 31.013160705566406 GB (23491.62109375 MB free) Uptime: 1.2286696e6 sec Load Avg: 1.06 1.09 0.86 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Target result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 30 Oct 2023 - 15:18 * Package commit: 2a9645 * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 68.816 ms (5%) | | 99.55 MiB (1%) | 61 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.877 ms (5%) | | 717.02 KiB (1%) | 4935 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 646.970 ms (5%) | | 46.04 MiB (1%) | 16 | | `["Laplace", "LU threads=false"]` | 36.454 s (5%) | 611.351 ms | 13.45 GiB (1%) | 11099411 | | `["Laplace", "LU threads=true"]` | 31.682 s (5%) | 905.694 ms | 13.45 GiB (1%) | 11102712 | | `["Laplace", "assemble threads=false"]` | 7.326 s (5%) | 313.563 ms | 2.23 GiB (1%) | 4994929 | | `["Laplace", "assemble threads=true"]` | 1.436 s (5%) | | 2.63 GiB (1%) | 51945625 | | `["Laplace", "gemv threads=false"]` | 174.280 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace", "gemv threads=true"]` | 91.544 ms (5%) | | 15.04 MiB (1%) | 636449 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1094498 s 1376 s 211068 s 489994578 s 0 s Memory: 31.013160705566406 GB (21468.765625 MB free) Uptime: 1.22852256e6 sec Load Avg: 1.2 1.11 0.82 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Baseline result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 30 Oct 2023 - 15:21 * Package commit: 17e3c4 * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 100.692 ms (5%) | 1.550 ms | 91.89 MiB (1%) | 57 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.347 ms (5%) | | 419.34 KiB (1%) | 43 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 646.244 ms (5%) | 870.693 μs | 46.04 MiB (1%) | 16 | | `["Laplace", "LU threads=false"]` | 34.610 s (5%) | 151.814 ms | 12.33 GiB (1%) | 2253291 | | `["Laplace", "LU threads=true"]` | 27.440 s (5%) | 281.455 ms | 12.33 GiB (1%) | 2336692 | | `["Laplace", "assemble threads=false"]` | 7.036 s (5%) | 43.361 ms | 1.82 GiB (1%) | 133735 | | `["Laplace", "assemble threads=true"]` | 947.098 ms (5%) | | 1.82 GiB (1%) | 143978 | | `["Laplace", "gemv threads=false"]` | 155.740 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace", "gemv threads=true"]` | 520.836 ms (5%) | | 46.61 MiB (1%) | 1119125 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1096510 s 1376 s 211184 s 490051237 s 0 s Memory: 31.013160705566406 GB (23491.62109375 MB free) Uptime: 1.2286696e6 sec Load Avg: 1.06 1.09 0.86 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Runtime information | Runtime Info | | |:--|:--| | BLAS #threads | 20 | | `BLAS.vendor()` | `lbt` | | `Sys.CPU_THREADS` | 40 | `lscpu` output: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 46 bits physical, 48 bits virtual CPU(s): 40 On-line CPU(s) list: 0-39 Thread(s) per core: 2 Core(s) per socket: 10 Socket(s): 2 NUMA node(s): 2 Vendor ID: GenuineIntel CPU family: 6 Model: 85 Model name: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz Stepping: 4 CPU MHz: 2200.000 CPU max MHz: 3000,0000 CPU min MHz: 800,0000 BogoMIPS: 4400.00 Virtualization: VT-x L1d cache: 640 KiB L1i cache: 640 KiB L2 cache: 20 MiB L3 cache: 27,5 MiB NUMA node0 CPU(s): 0-9,20-29 NUMA node1 CPU(s): 10-19,30-39 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Meltdown: Mitigation; PTI Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Retbleed: Mitigation; IBRS Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; IBRS, IBPB conditional, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke md_clear flush_l1d arch_capabilities | Cpu Property | Value | |:------------------ |:---------------------------------------------------------- | | Brand | Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz | | Vendor | :Intel | | Architecture | :Skylake | | Model | Family: 0x06, Model: 0x55, Stepping: 0x04, Type: 0x00 | | Cores | 10 physical cores, 20 logical cores (on executing CPU) | | | Hyperthreading hardware capability detected | | Clock Frequencies | 2200 / 3000 MHz (base/max), 100 MHz bus | | Data Cache | Level 1:3 : (32, 1024, 14080) kbytes | | | 64 byte cache line size | | Address Size | 48 bits virtual, 46 bits physical | | SIMD | 512 bit = 64 byte max. SIMD vector size | | Time Stamp Counter | TSC is accessible via `rdtsc` | | | TSC runs at constant rate (invariant from clock frequency) | | Perf. Monitoring | Performance Monitoring Counters (PMC) revision 4 | | | Available hardware counters per logical core: | | | 3 fixed-function counters of 48 bit width | | | 4 general-purpose counters of 48 bit width | | Hypervisor | No |
github-actions[bot] commented 8 months ago
Benchmark result # Judge result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmarks: - Target: 30 Oct 2023 - 16:06 - Baseline: 30 Oct 2023 - 16:08 * Package commits: - Target: 72029d - Baseline: 17e3c4 * Julia commits: - Target: bed2cd - Baseline: bed2cd * Julia command flags: - Target: `-O3` - Baseline: `-O3` * Environment variables: - Target: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` - Baseline: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results A ratio greater than `1.0` denotes a possible regression (marked with :x:), while a ratio less than `1.0` denotes a possible improvement (marked with :white_check_mark:). Only significant results - results that indicate possible regressions or improvements - are shown below (thus, an empty table means that all benchmark results remained invariant between builds). | ID | time ratio | memory ratio | |-------------------------------------------------------------------|------------------------------|------------------------------| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 0.69 (5%) :white_check_mark: | 1.08 (1%) :x: | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.15 (5%) :x: | 1.41 (1%) :x: | | `["Laplace", "LU threads=false"]` | 1.09 (5%) :x: | 1.07 (1%) :x: | | `["Laplace", "LU threads=true"]` | 1.12 (5%) :x: | 1.07 (1%) :x: | | `["Laplace", "assemble threads=false"]` | 0.97 (5%) | 0.81 (1%) :white_check_mark: | | `["Laplace", "assemble threads=true"]` | 1.00 (5%) | 0.82 (1%) :white_check_mark: | | `["Laplace", "gemv threads=false"]` | 1.14 (5%) :x: | 1.00 (1%) | | `["Laplace", "gemv threads=true"]` | 0.15 (5%) :white_check_mark: | 0.32 (1%) :white_check_mark: | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ### Target ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1105216 s 1376 s 212366 s 491129438 s 0 s Memory: 31.013160705566406 GB (23224.19140625 MB free) Uptime: 1.23139043e6 sec Load Avg: 2.52 1.48 0.74 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` ### Baseline ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1107213 s 1376 s 212473 s 491185387 s 0 s Memory: 31.013160705566406 GB (23429.64453125 MB free) Uptime: 1.23153562e6 sec Load Avg: 2.44 1.67 0.91 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Target result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 30 Oct 2023 - 16:6 * Package commit: 72029d * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 71.296 ms (5%) | | 107.21 MiB (1%) | 65 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.569 ms (5%) | | 590.75 KiB (1%) | 25 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 640.493 ms (5%) | | 46.04 MiB (1%) | 16 | | `["Laplace", "LU threads=false"]` | 37.542 s (5%) | 416.767 ms | 13.25 GiB (1%) | 2219001 | | `["Laplace", "LU threads=true"]` | 29.816 s (5%) | 484.890 ms | 13.25 GiB (1%) | 2222266 | | `["Laplace", "assemble threads=false"]` | 6.803 s (5%) | 37.693 ms | 1.47 GiB (1%) | 60812 | | `["Laplace", "assemble threads=true"]` | 950.521 ms (5%) | | 1.50 GiB (1%) | 71158 | | `["Laplace", "gemv threads=false"]` | 166.469 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace", "gemv threads=true"]` | 79.412 ms (5%) | | 15.04 MiB (1%) | 636452 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1105216 s 1376 s 212366 s 491129438 s 0 s Memory: 31.013160705566406 GB (23224.19140625 MB free) Uptime: 1.23139043e6 sec Load Avg: 2.52 1.48 0.74 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Baseline result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 30 Oct 2023 - 16:8 * Package commit: 17e3c4 * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 103.156 ms (5%) | 1.556 ms | 99.55 MiB (1%) | 61 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.370 ms (5%) | | 419.34 KiB (1%) | 43 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 639.448 ms (5%) | 883.256 μs | 46.04 MiB (1%) | 16 | | `["Laplace", "LU threads=false"]` | 34.393 s (5%) | 149.849 ms | 12.33 GiB (1%) | 2253291 | | `["Laplace", "LU threads=true"]` | 26.643 s (5%) | 280.146 ms | 12.33 GiB (1%) | 2336667 | | `["Laplace", "assemble threads=false"]` | 7.043 s (5%) | 41.135 ms | 1.82 GiB (1%) | 133735 | | `["Laplace", "assemble threads=true"]` | 951.602 ms (5%) | | 1.82 GiB (1%) | 143978 | | `["Laplace", "gemv threads=false"]` | 145.901 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace", "gemv threads=true"]` | 521.644 ms (5%) | | 46.61 MiB (1%) | 1119127 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1107213 s 1376 s 212473 s 491185387 s 0 s Memory: 31.013160705566406 GB (23429.64453125 MB free) Uptime: 1.23153562e6 sec Load Avg: 2.44 1.67 0.91 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Runtime information | Runtime Info | | |:--|:--| | BLAS #threads | 20 | | `BLAS.vendor()` | `lbt` | | `Sys.CPU_THREADS` | 40 | `lscpu` output: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 46 bits physical, 48 bits virtual CPU(s): 40 On-line CPU(s) list: 0-39 Thread(s) per core: 2 Core(s) per socket: 10 Socket(s): 2 NUMA node(s): 2 Vendor ID: GenuineIntel CPU family: 6 Model: 85 Model name: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz Stepping: 4 CPU MHz: 800.034 CPU max MHz: 3000,0000 CPU min MHz: 800,0000 BogoMIPS: 4400.00 Virtualization: VT-x L1d cache: 640 KiB L1i cache: 640 KiB L2 cache: 20 MiB L3 cache: 27,5 MiB NUMA node0 CPU(s): 0-9,20-29 NUMA node1 CPU(s): 10-19,30-39 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Meltdown: Mitigation; PTI Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Retbleed: Mitigation; IBRS Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; IBRS, IBPB conditional, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke md_clear flush_l1d arch_capabilities | Cpu Property | Value | |:------------------ |:---------------------------------------------------------- | | Brand | Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz | | Vendor | :Intel | | Architecture | :Skylake | | Model | Family: 0x06, Model: 0x55, Stepping: 0x04, Type: 0x00 | | Cores | 10 physical cores, 20 logical cores (on executing CPU) | | | Hyperthreading hardware capability detected | | Clock Frequencies | 2200 / 3000 MHz (base/max), 100 MHz bus | | Data Cache | Level 1:3 : (32, 1024, 14080) kbytes | | | 64 byte cache line size | | Address Size | 48 bits virtual, 46 bits physical | | SIMD | 512 bit = 64 byte max. SIMD vector size | | Time Stamp Counter | TSC is accessible via `rdtsc` | | | TSC runs at constant rate (invariant from clock frequency) | | Perf. Monitoring | Performance Monitoring Counters (PMC) revision 4 | | | Available hardware counters per logical core: | | | 3 fixed-function counters of 48 bit width | | | 4 general-purpose counters of 48 bit width | | Hypervisor | No |
github-actions[bot] commented 8 months ago
Benchmark result # Judge result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmarks: - Target: 30 Oct 2023 - 16:31 - Baseline: 30 Oct 2023 - 16:33 * Package commits: - Target: e2639b - Baseline: 93d66d * Julia commits: - Target: bed2cd - Baseline: bed2cd * Julia command flags: - Target: `-O3` - Baseline: `-O3` * Environment variables: - Target: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` - Baseline: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results A ratio greater than `1.0` denotes a possible regression (marked with :x:), while a ratio less than `1.0` denotes a possible improvement (marked with :white_check_mark:). Only significant results - results that indicate possible regressions or improvements - are shown below (thus, an empty table means that all benchmark results remained invariant between builds). | ID | time ratio | memory ratio | |-------------------------------------------------------------------|------------------------------|------------------------------| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 0.61 (5%) :white_check_mark: | 0.87 (1%) :white_check_mark: | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.49 (5%) :x: | 1.64 (1%) :x: | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` ## Julia versioninfo ### Target ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1116432 s 1376 s 213961 s 491712656 s 0 s Memory: 31.013160705566406 GB (23449.1484375 MB free) Uptime: 1.23288101e6 sec Load Avg: 1.11 1.0 0.91 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` ### Baseline ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1118675 s 1376 s 214086 s 491773138 s 0 s Memory: 31.013160705566406 GB (23453.4375 MB free) Uptime: 1.23303819e6 sec Load Avg: 2.33 1.37 1.06 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Target result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 30 Oct 2023 - 16:31 * Package commit: e2639b * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 66.365 ms (5%) | | 99.55 MiB (1%) | 61 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.872 ms (5%) | | 637.62 KiB (1%) | 25 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 637.427 ms (5%) | | 46.04 MiB (1%) | 16 | | `["LaplaceVec", "LU threads=false"]` | 34.449 s (5%) | 336.894 ms | 13.25 GiB (1%) | 2219001 | | `["LaplaceVec", "LU threads=true"]` | 27.977 s (5%) | 460.699 ms | 13.25 GiB (1%) | 2222256 | | `["LaplaceVec", "assemble threads=false"]` | 1.290 s (5%) | 35.591 ms | 1.46 GiB (1%) | 52364 | | `["LaplaceVec", "assemble threads=true"]` | 189.593 ms (5%) | | 1.48 GiB (1%) | 62705 | | `["LaplaceVec", "gemv threads=false"]` | 152.972 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["LaplaceVec", "gemv threads=true"]` | 79.216 ms (5%) | | 15.04 MiB (1%) | 636451 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["LaplaceVec"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1116432 s 1376 s 213961 s 491712656 s 0 s Memory: 31.013160705566406 GB (23449.1484375 MB free) Uptime: 1.23288101e6 sec Load Avg: 1.11 1.0 0.91 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Baseline result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 30 Oct 2023 - 16:33 * Package commit: 93d66d * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 109.306 ms (5%) | 1.491 ms | 114.87 MiB (1%) | 69 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.257 ms (5%) | | 387.84 KiB (1%) | 41 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 641.757 ms (5%) | 871.007 μs | 46.04 MiB (1%) | 16 | | `["Laplace", "LU threads=false"]` | 34.726 s (5%) | 151.394 ms | 12.33 GiB (1%) | 2253291 | | `["Laplace", "LU threads=true"]` | 26.896 s (5%) | 278.916 ms | 12.33 GiB (1%) | 2336679 | | `["Laplace", "assemble threads=false"]` | 7.326 s (5%) | 40.982 ms | 1.82 GiB (1%) | 133735 | | `["Laplace", "assemble threads=true"]` | 952.288 ms (5%) | | 1.82 GiB (1%) | 143979 | | `["Laplace", "gemv threads=false"]` | 170.211 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace", "gemv threads=true"]` | 65.228 ms (5%) | | 5.33 MiB (1%) | 24652 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1118675 s 1376 s 214086 s 491773138 s 0 s Memory: 31.013160705566406 GB (23453.4375 MB free) Uptime: 1.23303819e6 sec Load Avg: 2.33 1.37 1.06 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Runtime information | Runtime Info | | |:--|:--| | BLAS #threads | 20 | | `BLAS.vendor()` | `lbt` | | `Sys.CPU_THREADS` | 40 | `lscpu` output: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 46 bits physical, 48 bits virtual CPU(s): 40 On-line CPU(s) list: 0-39 Thread(s) per core: 2 Core(s) per socket: 10 Socket(s): 2 NUMA node(s): 2 Vendor ID: GenuineIntel CPU family: 6 Model: 85 Model name: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz Stepping: 4 CPU MHz: 2200.000 CPU max MHz: 3000,0000 CPU min MHz: 800,0000 BogoMIPS: 4400.00 Virtualization: VT-x L1d cache: 640 KiB L1i cache: 640 KiB L2 cache: 20 MiB L3 cache: 27,5 MiB NUMA node0 CPU(s): 0-9,20-29 NUMA node1 CPU(s): 10-19,30-39 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Meltdown: Mitigation; PTI Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Retbleed: Mitigation; IBRS Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; IBRS, IBPB conditional, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke md_clear flush_l1d arch_capabilities | Cpu Property | Value | |:------------------ |:---------------------------------------------------------- | | Brand | Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz | | Vendor | :Intel | | Architecture | :Skylake | | Model | Family: 0x06, Model: 0x55, Stepping: 0x04, Type: 0x00 | | Cores | 10 physical cores, 20 logical cores (on executing CPU) | | | Hyperthreading hardware capability detected | | Clock Frequencies | 2200 / 3000 MHz (base/max), 100 MHz bus | | Data Cache | Level 1:3 : (32, 1024, 14080) kbytes | | | 64 byte cache line size | | Address Size | 48 bits virtual, 46 bits physical | | SIMD | 512 bit = 64 byte max. SIMD vector size | | Time Stamp Counter | TSC is accessible via `rdtsc` | | | TSC runs at constant rate (invariant from clock frequency) | | Perf. Monitoring | Performance Monitoring Counters (PMC) revision 4 | | | Available hardware counters per logical core: | | | 3 fixed-function counters of 48 bit width | | | 4 general-purpose counters of 48 bit width | | Hypervisor | No |
github-actions[bot] commented 8 months ago
Benchmark result # Judge result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmarks: - Target: 30 Oct 2023 - 17:12 - Baseline: 30 Oct 2023 - 17:15 * Package commits: - Target: bef6b1 - Baseline: 93d66d * Julia commits: - Target: bed2cd - Baseline: bed2cd * Julia command flags: - Target: `-O3` - Baseline: `-O3` * Environment variables: - Target: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` - Baseline: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results A ratio greater than `1.0` denotes a possible regression (marked with :x:), while a ratio less than `1.0` denotes a possible improvement (marked with :white_check_mark:). Only significant results - results that indicate possible regressions or improvements - are shown below (thus, an empty table means that all benchmark results remained invariant between builds). | ID | time ratio | memory ratio | |-------------------------------------------------------------------|------------------------------|---------------| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 0.67 (5%) :white_check_mark: | 1.00 (1%) | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.49 (5%) :x: | 1.64 (1%) :x: | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` ## Julia versioninfo ### Target ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1125579 s 1376 s 215049 s 492691789 s 0 s Memory: 31.013160705566406 GB (22722.18359375 MB free) Uptime: 1.23535506e6 sec Load Avg: 1.12 0.9 0.52 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` ### Baseline ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1127847 s 1376 s 215163 s 492751927 s 0 s Memory: 31.013160705566406 GB (23415.953125 MB free) Uptime: 1.23551142e6 sec Load Avg: 1.12 1.02 0.63 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Target result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 30 Oct 2023 - 17:12 * Package commit: bef6b1 * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 70.620 ms (5%) | | 107.21 MiB (1%) | 65 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.909 ms (5%) | | 637.62 KiB (1%) | 25 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 639.949 ms (5%) | | 46.04 MiB (1%) | 16 | | `["LaplaceVec", "LU threads=false"]` | 34.517 s (5%) | 354.479 ms | 13.25 GiB (1%) | 2219001 | | `["LaplaceVec", "LU threads=true"]` | 27.556 s (5%) | 331.752 ms | 13.25 GiB (1%) | 2222271 | | `["LaplaceVec", "assemble threads=false"]` | 1.919 s (5%) | 34.504 ms | 1.46 GiB (1%) | 52364 | | `["LaplaceVec", "assemble threads=true"]` | 190.638 ms (5%) | | 1.48 GiB (1%) | 62710 | | `["LaplaceVec", "gemv threads=false"]` | 155.689 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["LaplaceVec", "gemv threads=true"]` | 81.527 ms (5%) | | 15.04 MiB (1%) | 636451 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["LaplaceVec"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1125579 s 1376 s 215049 s 492691789 s 0 s Memory: 31.013160705566406 GB (22722.18359375 MB free) Uptime: 1.23535506e6 sec Load Avg: 1.12 0.9 0.52 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Baseline result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 30 Oct 2023 - 17:15 * Package commit: 93d66d * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 106.001 ms (5%) | 1.542 ms | 107.21 MiB (1%) | 65 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.282 ms (5%) | | 387.84 KiB (1%) | 41 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 641.498 ms (5%) | 889.284 μs | 46.04 MiB (1%) | 16 | | `["Laplace", "LU threads=false"]` | 34.480 s (5%) | 220.347 ms | 12.33 GiB (1%) | 2253291 | | `["Laplace", "LU threads=true"]` | 27.440 s (5%) | 305.075 ms | 12.33 GiB (1%) | 2336716 | | `["Laplace", "assemble threads=false"]` | 7.321 s (5%) | 43.819 ms | 1.82 GiB (1%) | 133735 | | `["Laplace", "assemble threads=true"]` | 981.963 ms (5%) | | 1.82 GiB (1%) | 143979 | | `["Laplace", "gemv threads=false"]` | 148.060 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace", "gemv threads=true"]` | 58.965 ms (5%) | | 5.33 MiB (1%) | 24664 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1127847 s 1376 s 215163 s 492751927 s 0 s Memory: 31.013160705566406 GB (23415.953125 MB free) Uptime: 1.23551142e6 sec Load Avg: 1.12 1.02 0.63 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Runtime information | Runtime Info | | |:--|:--| | BLAS #threads | 20 | | `BLAS.vendor()` | `lbt` | | `Sys.CPU_THREADS` | 40 | `lscpu` output: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 46 bits physical, 48 bits virtual CPU(s): 40 On-line CPU(s) list: 0-39 Thread(s) per core: 2 Core(s) per socket: 10 Socket(s): 2 NUMA node(s): 2 Vendor ID: GenuineIntel CPU family: 6 Model: 85 Model name: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz Stepping: 4 CPU MHz: 2200.000 CPU max MHz: 3000,0000 CPU min MHz: 800,0000 BogoMIPS: 4400.00 Virtualization: VT-x L1d cache: 640 KiB L1i cache: 640 KiB L2 cache: 20 MiB L3 cache: 27,5 MiB NUMA node0 CPU(s): 0-9,20-29 NUMA node1 CPU(s): 10-19,30-39 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Meltdown: Mitigation; PTI Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Retbleed: Mitigation; IBRS Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; IBRS, IBPB conditional, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke md_clear flush_l1d arch_capabilities | Cpu Property | Value | |:------------------ |:---------------------------------------------------------- | | Brand | Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz | | Vendor | :Intel | | Architecture | :Skylake | | Model | Family: 0x06, Model: 0x55, Stepping: 0x04, Type: 0x00 | | Cores | 10 physical cores, 20 logical cores (on executing CPU) | | | Hyperthreading hardware capability detected | | Clock Frequencies | 2200 / 3000 MHz (base/max), 100 MHz bus | | Data Cache | Level 1:3 : (32, 1024, 14080) kbytes | | | 64 byte cache line size | | Address Size | 48 bits virtual, 46 bits physical | | SIMD | 512 bit = 64 byte max. SIMD vector size | | Time Stamp Counter | TSC is accessible via `rdtsc` | | | TSC runs at constant rate (invariant from clock frequency) | | Perf. Monitoring | Performance Monitoring Counters (PMC) revision 4 | | | Available hardware counters per logical core: | | | 3 fixed-function counters of 48 bit width | | | 4 general-purpose counters of 48 bit width | | Hypervisor | No |
github-actions[bot] commented 8 months ago
Benchmark result # Judge result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmarks: - Target: 30 Oct 2023 - 17:21 - Baseline: 30 Oct 2023 - 17:24 * Package commits: - Target: 834386 - Baseline: 93d66d * Julia commits: - Target: bed2cd - Baseline: bed2cd * Julia command flags: - Target: `-O3` - Baseline: `-O3` * Environment variables: - Target: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` - Baseline: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results A ratio greater than `1.0` denotes a possible regression (marked with :x:), while a ratio less than `1.0` denotes a possible improvement (marked with :white_check_mark:). Only significant results - results that indicate possible regressions or improvements - are shown below (thus, an empty table means that all benchmark results remained invariant between builds). | ID | time ratio | memory ratio | |-------------------------------------------------------------------|------------------------------|---------------| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 0.66 (5%) :white_check_mark: | 1.00 (1%) | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.10 (5%) :x: | 1.34 (1%) :x: | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` ## Julia versioninfo ### Target ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1132207 s 1376 s 215591 s 492895437 s 0 s Memory: 31.013160705566406 GB (23510.515625 MB free) Uptime: 1.23588234e6 sec Load Avg: 1.12 1.14 0.83 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` ### Baseline ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1134477 s 1376 s 215707 s 492956006 s 0 s Memory: 31.013160705566406 GB (23532.48828125 MB free) Uptime: 1.23603978e6 sec Load Avg: 2.28 1.44 0.99 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Target result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 30 Oct 2023 - 17:21 * Package commit: 834386 * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 71.264 ms (5%) | | 107.21 MiB (1%) | 65 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.652 ms (5%) | | 606.38 KiB (1%) | 25 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 637.196 ms (5%) | | 46.04 MiB (1%) | 16 | | `["LaplaceVec", "LU threads=false"]` | 36.160 s (5%) | 450.561 ms | 13.25 GiB (1%) | 2219001 | | `["LaplaceVec", "LU threads=true"]` | 27.595 s (5%) | 358.741 ms | 13.25 GiB (1%) | 2222254 | | `["LaplaceVec", "assemble threads=false"]` | 1.068 s (5%) | 35.428 ms | 1.46 GiB (1%) | 52364 | | `["LaplaceVec", "assemble threads=true"]` | 174.341 ms (5%) | | 1.48 GiB (1%) | 62714 | | `["LaplaceVec", "gemv threads=false"]` | 152.577 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["LaplaceVec", "gemv threads=true"]` | 80.186 ms (5%) | | 15.04 MiB (1%) | 636452 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["LaplaceVec"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1132207 s 1376 s 215591 s 492895437 s 0 s Memory: 31.013160705566406 GB (23510.515625 MB free) Uptime: 1.23588234e6 sec Load Avg: 1.12 1.14 0.83 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Baseline result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 30 Oct 2023 - 17:24 * Package commit: 93d66d * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 108.503 ms (5%) | 1.561 ms | 107.21 MiB (1%) | 65 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.504 ms (5%) | | 450.84 KiB (1%) | 45 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 644.317 ms (5%) | 898.229 μs | 46.04 MiB (1%) | 16 | | `["Laplace", "LU threads=false"]` | 34.959 s (5%) | 165.404 ms | 12.33 GiB (1%) | 2253291 | | `["Laplace", "LU threads=true"]` | 27.176 s (5%) | 279.390 ms | 12.33 GiB (1%) | 2336682 | | `["Laplace", "assemble threads=false"]` | 7.040 s (5%) | 42.941 ms | 1.82 GiB (1%) | 133735 | | `["Laplace", "assemble threads=true"]` | 945.519 ms (5%) | | 1.82 GiB (1%) | 143979 | | `["Laplace", "gemv threads=false"]` | 163.723 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace", "gemv threads=true"]` | 59.656 ms (5%) | | 5.33 MiB (1%) | 24663 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1134477 s 1376 s 215707 s 492956006 s 0 s Memory: 31.013160705566406 GB (23532.48828125 MB free) Uptime: 1.23603978e6 sec Load Avg: 2.28 1.44 0.99 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Runtime information | Runtime Info | | |:--|:--| | BLAS #threads | 20 | | `BLAS.vendor()` | `lbt` | | `Sys.CPU_THREADS` | 40 | `lscpu` output: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 46 bits physical, 48 bits virtual CPU(s): 40 On-line CPU(s) list: 0-39 Thread(s) per core: 2 Core(s) per socket: 10 Socket(s): 2 NUMA node(s): 2 Vendor ID: GenuineIntel CPU family: 6 Model: 85 Model name: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz Stepping: 4 CPU MHz: 800.119 CPU max MHz: 3000,0000 CPU min MHz: 800,0000 BogoMIPS: 4400.00 Virtualization: VT-x L1d cache: 640 KiB L1i cache: 640 KiB L2 cache: 20 MiB L3 cache: 27,5 MiB NUMA node0 CPU(s): 0-9,20-29 NUMA node1 CPU(s): 10-19,30-39 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Meltdown: Mitigation; PTI Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Retbleed: Mitigation; IBRS Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; IBRS, IBPB conditional, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke md_clear flush_l1d arch_capabilities | Cpu Property | Value | |:------------------ |:---------------------------------------------------------- | | Brand | Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz | | Vendor | :Intel | | Architecture | :Skylake | | Model | Family: 0x06, Model: 0x55, Stepping: 0x04, Type: 0x00 | | Cores | 10 physical cores, 20 logical cores (on executing CPU) | | | Hyperthreading hardware capability detected | | Clock Frequencies | 2200 / 3000 MHz (base/max), 100 MHz bus | | Data Cache | Level 1:3 : (32, 1024, 14080) kbytes | | | 64 byte cache line size | | Address Size | 48 bits virtual, 46 bits physical | | SIMD | 512 bit = 64 byte max. SIMD vector size | | Time Stamp Counter | TSC is accessible via `rdtsc` | | | TSC runs at constant rate (invariant from clock frequency) | | Perf. Monitoring | Performance Monitoring Counters (PMC) revision 4 | | | Available hardware counters per logical core: | | | 3 fixed-function counters of 48 bit width | | | 4 general-purpose counters of 48 bit width | | Hypervisor | No |
github-actions[bot] commented 8 months ago
Benchmark result # Judge result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmarks: - Target: 30 Oct 2023 - 17:47 - Baseline: 30 Oct 2023 - 17:50 * Package commits: - Target: 2affc6 - Baseline: 93d66d * Julia commits: - Target: bed2cd - Baseline: bed2cd * Julia command flags: - Target: `-O3` - Baseline: `-O3` * Environment variables: - Target: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` - Baseline: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results A ratio greater than `1.0` denotes a possible regression (marked with :x:), while a ratio less than `1.0` denotes a possible improvement (marked with :white_check_mark:). Only significant results - results that indicate possible regressions or improvements - are shown below (thus, an empty table means that all benchmark results remained invariant between builds). | ID | time ratio | memory ratio | |-------------------------------------------------------------------|------------------------------|------------------------------| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 0.68 (5%) :white_check_mark: | 1.00 (1%) | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 0.90 (5%) :white_check_mark: | 1.11 (1%) :x: | | `["Laplace", "LU threads=false"]` | 1.07 (5%) :x: | 1.07 (1%) :x: | | `["Laplace", "LU threads=true"]` | 1.09 (5%) :x: | 1.07 (1%) :x: | | `["Laplace", "assemble threads=false"]` | 0.92 (5%) :white_check_mark: | 0.80 (1%) :white_check_mark: | | `["Laplace", "assemble threads=true"]` | 1.06 (5%) :x: | 0.82 (1%) :white_check_mark: | | `["Laplace", "gemv threads=true"]` | 0.14 (5%) :white_check_mark: | 0.32 (1%) :white_check_mark: | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ### Target ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1145998 s 1376 s 216954 s 493516398 s 0 s Memory: 31.013160705566406 GB (22174.53515625 MB free) Uptime: 1.23747314e6 sec Load Avg: 1.25 1.23 1.02 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` ### Baseline ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1147994 s 1376 s 217077 s 493573194 s 0 s Memory: 31.013160705566406 GB (23502.796875 MB free) Uptime: 1.23762048e6 sec Load Avg: 1.65 1.28 1.05 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Target result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 30 Oct 2023 - 17:47 * Package commit: 2affc6 * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 71.770 ms (5%) | | 107.21 MiB (1%) | 65 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.634 ms (5%) | | 606.38 KiB (1%) | 25 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 641.340 ms (5%) | | 46.04 MiB (1%) | 16 | | `["Laplace", "LU threads=false"]` | 37.582 s (5%) | 451.200 ms | 13.25 GiB (1%) | 2219001 | | `["Laplace", "LU threads=true"]` | 30.090 s (5%) | 597.488 ms | 13.25 GiB (1%) | 2222254 | | `["Laplace", "assemble threads=false"]` | 6.783 s (5%) | 40.060 ms | 1.46 GiB (1%) | 52364 | | `["Laplace", "assemble threads=true"]` | 990.635 ms (5%) | | 1.48 GiB (1%) | 62711 | | `["Laplace", "gemv threads=false"]` | 160.964 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace", "gemv threads=true"]` | 77.477 ms (5%) | | 15.04 MiB (1%) | 636449 | | `["LaplaceVec", "LU threads=false"]` | 42.209 s (5%) | 832.444 ms | 13.25 GiB (1%) | 2219001 | | `["LaplaceVec", "LU threads=true"]` | 27.458 s (5%) | 355.821 ms | 13.25 GiB (1%) | 2222241 | | `["LaplaceVec", "assemble threads=false"]` | 1.785 s (5%) | 36.948 ms | 1.46 GiB (1%) | 52364 | | `["LaplaceVec", "assemble threads=true"]` | 169.682 ms (5%) | | 1.48 GiB (1%) | 62712 | | `["LaplaceVec", "gemv threads=false"]` | 160.336 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["LaplaceVec", "gemv threads=true"]` | 79.585 ms (5%) | | 15.04 MiB (1%) | 636451 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` - `["LaplaceVec"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1145998 s 1376 s 216954 s 493516398 s 0 s Memory: 31.013160705566406 GB (22174.53515625 MB free) Uptime: 1.23747314e6 sec Load Avg: 1.25 1.23 1.02 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Baseline result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 30 Oct 2023 - 17:50 * Package commit: 93d66d * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 105.670 ms (5%) | 1.471 ms | 107.21 MiB (1%) | 65 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.810 ms (5%) | | 545.34 KiB (1%) | 51 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 643.010 ms (5%) | 839.872 μs | 46.04 MiB (1%) | 16 | | `["Laplace", "LU threads=false"]` | 35.240 s (5%) | 186.459 ms | 12.33 GiB (1%) | 2253291 | | `["Laplace", "LU threads=true"]` | 27.544 s (5%) | 353.849 ms | 12.33 GiB (1%) | 2336688 | | `["Laplace", "assemble threads=false"]` | 7.370 s (5%) | 44.495 ms | 1.82 GiB (1%) | 133735 | | `["Laplace", "assemble threads=true"]` | 933.698 ms (5%) | | 1.82 GiB (1%) | 143979 | | `["Laplace", "gemv threads=false"]` | 157.559 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace", "gemv threads=true"]` | 572.433 ms (5%) | | 46.63 MiB (1%) | 1119122 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1147994 s 1376 s 217077 s 493573194 s 0 s Memory: 31.013160705566406 GB (23502.796875 MB free) Uptime: 1.23762048e6 sec Load Avg: 1.65 1.28 1.05 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Runtime information | Runtime Info | | |:--|:--| | BLAS #threads | 20 | | `BLAS.vendor()` | `lbt` | | `Sys.CPU_THREADS` | 40 | `lscpu` output: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 46 bits physical, 48 bits virtual CPU(s): 40 On-line CPU(s) list: 0-39 Thread(s) per core: 2 Core(s) per socket: 10 Socket(s): 2 NUMA node(s): 2 Vendor ID: GenuineIntel CPU family: 6 Model: 85 Model name: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz Stepping: 4 CPU MHz: 2200.000 CPU max MHz: 3000,0000 CPU min MHz: 800,0000 BogoMIPS: 4400.00 Virtualization: VT-x L1d cache: 640 KiB L1i cache: 640 KiB L2 cache: 20 MiB L3 cache: 27,5 MiB NUMA node0 CPU(s): 0-9,20-29 NUMA node1 CPU(s): 10-19,30-39 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Meltdown: Mitigation; PTI Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Retbleed: Mitigation; IBRS Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; IBRS, IBPB conditional, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke md_clear flush_l1d arch_capabilities | Cpu Property | Value | |:------------------ |:---------------------------------------------------------- | | Brand | Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz | | Vendor | :Intel | | Architecture | :Skylake | | Model | Family: 0x06, Model: 0x55, Stepping: 0x04, Type: 0x00 | | Cores | 10 physical cores, 20 logical cores (on executing CPU) | | | Hyperthreading hardware capability detected | | Clock Frequencies | 2200 / 3000 MHz (base/max), 100 MHz bus | | Data Cache | Level 1:3 : (32, 1024, 14080) kbytes | | | 64 byte cache line size | | Address Size | 48 bits virtual, 46 bits physical | | SIMD | 512 bit = 64 byte max. SIMD vector size | | Time Stamp Counter | TSC is accessible via `rdtsc` | | | TSC runs at constant rate (invariant from clock frequency) | | Perf. Monitoring | Performance Monitoring Counters (PMC) revision 4 | | | Available hardware counters per logical core: | | | 3 fixed-function counters of 48 bit width | | | 4 general-purpose counters of 48 bit width | | Hypervisor | No |
github-actions[bot] commented 8 months ago
Benchmark result # Judge result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmarks: - Target: 4 Nov 2023 - 09:26 - Baseline: 4 Nov 2023 - 09:29 * Package commits: - Target: a0017a - Baseline: 93d66d * Julia commits: - Target: bed2cd - Baseline: bed2cd * Julia command flags: - Target: `-O3` - Baseline: `-O3` * Environment variables: - Target: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` - Baseline: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results A ratio greater than `1.0` denotes a possible regression (marked with :x:), while a ratio less than `1.0` denotes a possible improvement (marked with :white_check_mark:). Only significant results - results that indicate possible regressions or improvements - are shown below (thus, an empty table means that all benchmark results remained invariant between builds). | ID | time ratio | memory ratio | |-------------------------------------------------------------------|------------------------------|------------------------------| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 0.64 (5%) :white_check_mark: | 0.93 (1%) :white_check_mark: | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.09 (5%) :x: | 1.31 (1%) :x: | | `["Laplace", "assemble threads=false"]` | 0.95 (5%) :white_check_mark: | 0.80 (1%) :white_check_mark: | | `["Laplace", "assemble threads=true"]` | 1.02 (5%) | 0.82 (1%) :white_check_mark: | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ### Target ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 818 MHz 1341245 s 2460 s 250934 s 654025428 s 0 s Memory: 31.013160705566406 GB (22965.87890625 MB free) Uptime: 1.6393997e6 sec Load Avg: 1.02 0.9 0.5 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` ### Baseline ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1343493 s 2460 s 251060 s 654085838 s 0 s Memory: 31.013160705566406 GB (23425.8828125 MB free) Uptime: 1.63955671e6 sec Load Avg: 2.03 1.2 0.67 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Target result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 4 Nov 2023 - 9:26 * Package commit: a0017a * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 67.753 ms (5%) | | 99.55 MiB (1%) | 61 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.607 ms (5%) | | 590.75 KiB (1%) | 25 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 642.787 ms (5%) | | 46.04 MiB (1%) | 16 | | `["Laplace permuted", "assemble threads=false"]` | 6.544 s (5%) | 104.113 ms | 1.46 GiB (1%) | 52364 | | `["Laplace permuted", "assemble threads=true"]` | 932.197 ms (5%) | | 1.48 GiB (1%) | 62712 | | `["Laplace vectorized", "LU threads=false"]` | 35.625 s (5%) | 334.154 ms | 11.85 GiB (1%) | 2142967 | | `["Laplace vectorized", "LU threads=true"]` | 37.117 s (5%) | 425.602 ms | 11.85 GiB (1%) | 2142967 | | `["Laplace vectorized", "assemble threads=false"]` | 1.098 s (5%) | 36.430 ms | 1.46 GiB (1%) | 52364 | | `["Laplace vectorized", "assemble threads=true"]` | 168.291 ms (5%) | | 1.48 GiB (1%) | 62717 | | `["Laplace vectorized", "gemv threads=false"]` | 156.976 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace vectorized", "gemv threads=true"]` | 80.115 ms (5%) | | 15.04 MiB (1%) | 636450 | | `["Laplace", "assemble threads=false"]` | 6.980 s (5%) | 38.849 ms | 1.46 GiB (1%) | 52364 | | `["Laplace", "assemble threads=true"]` | 951.198 ms (5%) | | 1.49 GiB (1%) | 62709 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace permuted"]` - `["Laplace vectorized"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 818 MHz 1341245 s 2460 s 250934 s 654025428 s 0 s Memory: 31.013160705566406 GB (22965.87890625 MB free) Uptime: 1.6393997e6 sec Load Avg: 1.02 0.9 0.5 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Baseline result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 4 Nov 2023 - 9:29 * Package commit: 93d66d * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 106.340 ms (5%) | 1.474 ms | 107.21 MiB (1%) | 65 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.480 ms (5%) | | 450.84 KiB (1%) | 45 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 640.741 ms (5%) | 842.588 μs | 46.04 MiB (1%) | 16 | | `["Laplace", "LU threads=false"]` | 34.704 s (5%) | 153.074 ms | 12.33 GiB (1%) | 2253291 | | `["Laplace", "LU threads=true"]` | 26.972 s (5%) | 295.860 ms | 12.33 GiB (1%) | 2336684 | | `["Laplace", "assemble threads=false"]` | 7.361 s (5%) | 42.194 ms | 1.82 GiB (1%) | 133736 | | `["Laplace", "assemble threads=true"]` | 929.066 ms (5%) | | 1.82 GiB (1%) | 143979 | | `["Laplace", "gemv threads=false"]` | 161.913 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace", "gemv threads=true"]` | 62.932 ms (5%) | | 5.33 MiB (1%) | 24652 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1343493 s 2460 s 251060 s 654085838 s 0 s Memory: 31.013160705566406 GB (23425.8828125 MB free) Uptime: 1.63955671e6 sec Load Avg: 2.03 1.2 0.67 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Runtime information | Runtime Info | | |:--|:--| | BLAS #threads | 20 | | `BLAS.vendor()` | `lbt` | | `Sys.CPU_THREADS` | 40 | `lscpu` output: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 46 bits physical, 48 bits virtual CPU(s): 40 On-line CPU(s) list: 0-39 Thread(s) per core: 2 Core(s) per socket: 10 Socket(s): 2 NUMA node(s): 2 Vendor ID: GenuineIntel CPU family: 6 Model: 85 Model name: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz Stepping: 4 CPU MHz: 800.116 CPU max MHz: 3000,0000 CPU min MHz: 800,0000 BogoMIPS: 4400.00 Virtualization: VT-x L1d cache: 640 KiB L1i cache: 640 KiB L2 cache: 20 MiB L3 cache: 27,5 MiB NUMA node0 CPU(s): 0-9,20-29 NUMA node1 CPU(s): 10-19,30-39 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Meltdown: Mitigation; PTI Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Retbleed: Mitigation; IBRS Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; IBRS, IBPB conditional, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke md_clear flush_l1d arch_capabilities | Cpu Property | Value | |:------------------ |:---------------------------------------------------------- | | Brand | Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz | | Vendor | :Intel | | Architecture | :Skylake | | Model | Family: 0x06, Model: 0x55, Stepping: 0x04, Type: 0x00 | | Cores | 10 physical cores, 20 logical cores (on executing CPU) | | | Hyperthreading hardware capability detected | | Clock Frequencies | 2200 / 3000 MHz (base/max), 100 MHz bus | | Data Cache | Level 1:3 : (32, 1024, 14080) kbytes | | | 64 byte cache line size | | Address Size | 48 bits virtual, 46 bits physical | | SIMD | 512 bit = 64 byte max. SIMD vector size | | Time Stamp Counter | TSC is accessible via `rdtsc` | | | TSC runs at constant rate (invariant from clock frequency) | | Perf. Monitoring | Performance Monitoring Counters (PMC) revision 4 | | | Available hardware counters per logical core: | | | 3 fixed-function counters of 48 bit width | | | 4 general-purpose counters of 48 bit width | | Hypervisor | No |
github-actions[bot] commented 8 months ago
Benchmark result # Judge result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmarks: - Target: 4 Nov 2023 - 10:15 - Baseline: 4 Nov 2023 - 10:17 * Package commits: - Target: 3ad924 - Baseline: 93d66d * Julia commits: - Target: bed2cd - Baseline: bed2cd * Julia command flags: - Target: `-O3` - Baseline: `-O3` * Environment variables: - Target: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` - Baseline: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results A ratio greater than `1.0` denotes a possible regression (marked with :x:), while a ratio less than `1.0` denotes a possible improvement (marked with :white_check_mark:). Only significant results - results that indicate possible regressions or improvements - are shown below (thus, an empty table means that all benchmark results remained invariant between builds). | ID | time ratio | memory ratio | |-------------------------------------------------------------------|------------------------------|------------------------------| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 0.67 (5%) :white_check_mark: | 0.87 (1%) :white_check_mark: | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.25 (5%) :x: | 1.41 (1%) :x: | | `["Laplace", "assemble threads=false"]` | 0.85 (5%) :white_check_mark: | 0.80 (1%) :white_check_mark: | | `["Laplace", "assemble threads=true"]` | 0.90 (5%) :white_check_mark: | 0.82 (1%) :white_check_mark: | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ### Target ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1352417 s 2460 s 252123 s 655176954 s 0 s Memory: 31.013160705566406 GB (22647.39453125 MB free) Uptime: 1.64231012e6 sec Load Avg: 1.49 1.23 0.65 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` ### Baseline ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1354695 s 2460 s 252263 s 655237857 s 0 s Memory: 31.013160705566406 GB (23426.55078125 MB free) Uptime: 1.64246848e6 sec Load Avg: 1.73 1.38 0.8 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Target result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 4 Nov 2023 - 10:15 * Package commit: 3ad924 * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 68.076 ms (5%) | | 99.55 MiB (1%) | 61 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.877 ms (5%) | | 637.62 KiB (1%) | 25 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 638.349 ms (5%) | | 46.04 MiB (1%) | 16 | | `["Laplace permuted", "assemble threads=false"]` | 6.823 s (5%) | 35.559 ms | 1.46 GiB (1%) | 52364 | | `["Laplace permuted", "assemble threads=true"]` | 924.995 ms (5%) | | 1.48 GiB (1%) | 62709 | | `["Laplace vectorized", "LU threads=false"]` | 34.681 s (5%) | 358.582 ms | 11.85 GiB (1%) | 2142967 | | `["Laplace vectorized", "LU threads=true"]` | 36.276 s (5%) | 455.101 ms | 11.85 GiB (1%) | 2142967 | | `["Laplace vectorized", "assemble threads=false"]` | 1.080 s (5%) | 39.336 ms | 1.46 GiB (1%) | 52364 | | `["Laplace vectorized", "assemble threads=true"]` | 158.334 ms (5%) | | 1.48 GiB (1%) | 62717 | | `["Laplace vectorized", "gemv threads=false"]` | 155.354 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace vectorized", "gemv threads=true"]` | 78.845 ms (5%) | | 15.04 MiB (1%) | 636455 | | `["Laplace", "assemble threads=false"]` | 6.564 s (5%) | 35.382 ms | 1.46 GiB (1%) | 52364 | | `["Laplace", "assemble threads=true"]` | 963.967 ms (5%) | | 1.48 GiB (1%) | 62712 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace permuted"]` - `["Laplace vectorized"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1352417 s 2460 s 252123 s 655176954 s 0 s Memory: 31.013160705566406 GB (22647.39453125 MB free) Uptime: 1.64231012e6 sec Load Avg: 1.49 1.23 0.65 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Baseline result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 4 Nov 2023 - 10:17 * Package commit: 93d66d * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 101.882 ms (5%) | 1.437 ms | 114.87 MiB (1%) | 69 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.507 ms (5%) | | 450.84 KiB (1%) | 45 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 642.018 ms (5%) | 853.089 μs | 46.04 MiB (1%) | 16 | | `["Laplace", "LU threads=false"]` | 34.625 s (5%) | 152.754 ms | 12.33 GiB (1%) | 2253291 | | `["Laplace", "LU threads=true"]` | 26.942 s (5%) | 299.648 ms | 12.33 GiB (1%) | 2336679 | | `["Laplace", "assemble threads=false"]` | 7.679 s (5%) | 221.457 ms | 1.82 GiB (1%) | 133735 | | `["Laplace", "assemble threads=true"]` | 1.073 s (5%) | | 1.82 GiB (1%) | 143979 | | `["Laplace", "gemv threads=false"]` | 158.473 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace", "gemv threads=true"]` | 69.120 ms (5%) | | 5.33 MiB (1%) | 24650 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1354695 s 2460 s 252263 s 655237857 s 0 s Memory: 31.013160705566406 GB (23426.55078125 MB free) Uptime: 1.64246848e6 sec Load Avg: 1.73 1.38 0.8 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Runtime information | Runtime Info | | |:--|:--| | BLAS #threads | 20 | | `BLAS.vendor()` | `lbt` | | `Sys.CPU_THREADS` | 40 | `lscpu` output: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 46 bits physical, 48 bits virtual CPU(s): 40 On-line CPU(s) list: 0-39 Thread(s) per core: 2 Core(s) per socket: 10 Socket(s): 2 NUMA node(s): 2 Vendor ID: GenuineIntel CPU family: 6 Model: 85 Model name: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz Stepping: 4 CPU MHz: 2200.000 CPU max MHz: 3000,0000 CPU min MHz: 800,0000 BogoMIPS: 4400.00 Virtualization: VT-x L1d cache: 640 KiB L1i cache: 640 KiB L2 cache: 20 MiB L3 cache: 27,5 MiB NUMA node0 CPU(s): 0-9,20-29 NUMA node1 CPU(s): 10-19,30-39 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Meltdown: Mitigation; PTI Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Retbleed: Mitigation; IBRS Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; IBRS, IBPB conditional, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke md_clear flush_l1d arch_capabilities | Cpu Property | Value | |:------------------ |:---------------------------------------------------------- | | Brand | Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz | | Vendor | :Intel | | Architecture | :Skylake | | Model | Family: 0x06, Model: 0x55, Stepping: 0x04, Type: 0x00 | | Cores | 10 physical cores, 20 logical cores (on executing CPU) | | | Hyperthreading hardware capability detected | | Clock Frequencies | 2200 / 3000 MHz (base/max), 100 MHz bus | | Data Cache | Level 1:3 : (32, 1024, 14080) kbytes | | | 64 byte cache line size | | Address Size | 48 bits virtual, 46 bits physical | | SIMD | 512 bit = 64 byte max. SIMD vector size | | Time Stamp Counter | TSC is accessible via `rdtsc` | | | TSC runs at constant rate (invariant from clock frequency) | | Perf. Monitoring | Performance Monitoring Counters (PMC) revision 4 | | | Available hardware counters per logical core: | | | 3 fixed-function counters of 48 bit width | | | 4 general-purpose counters of 48 bit width | | Hypervisor | No |
github-actions[bot] commented 8 months ago
Benchmark result # Judge result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmarks: - Target: 4 Nov 2023 - 10:33 - Baseline: 4 Nov 2023 - 10:35 * Package commits: - Target: 846fb0 - Baseline: 93d66d * Julia commits: - Target: bed2cd - Baseline: bed2cd * Julia command flags: - Target: `-O3` - Baseline: `-O3` * Environment variables: - Target: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` - Baseline: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results A ratio greater than `1.0` denotes a possible regression (marked with :x:), while a ratio less than `1.0` denotes a possible improvement (marked with :white_check_mark:). Only significant results - results that indicate possible regressions or improvements - are shown below (thus, an empty table means that all benchmark results remained invariant between builds). | ID | time ratio | memory ratio | |-------------------------------------------------------------------|------------------------------|------------------------------| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 0.71 (5%) :white_check_mark: | 1.08 (1%) :x: | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.29 (5%) :x: | 1.41 (1%) :x: | | `["Laplace", "assemble threads=false"]` | 0.93 (5%) :white_check_mark: | 0.80 (1%) :white_check_mark: | | `["Laplace", "assemble threads=true"]` | 1.01 (5%) | 0.82 (1%) :white_check_mark: | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ### Target ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1363467 s 2460 s 253232 s 655596249 s 0 s Memory: 31.013160705566406 GB (23200.43359375 MB free) Uptime: 1.64338914e6 sec Load Avg: 1.2 1.27 1.0 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` ### Baseline ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1365744 s 2460 s 253346 s 655656192 s 0 s Memory: 31.013160705566406 GB (23444.08984375 MB free) Uptime: 1.64354503e6 sec Load Avg: 2.38 1.54 1.13 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Target result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 4 Nov 2023 - 10:33 * Package commit: 846fb0 * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 73.955 ms (5%) | | 107.21 MiB (1%) | 65 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.892 ms (5%) | | 637.62 KiB (1%) | 25 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 639.591 ms (5%) | | 46.04 MiB (1%) | 16 | | `["Laplace permuted", "assemble threads=false"]` | 6.397 s (5%) | 36.639 ms | 1.46 GiB (1%) | 52364 | | `["Laplace permuted", "assemble threads=true"]` | 938.101 ms (5%) | | 1.48 GiB (1%) | 62707 | | `["Laplace vectorized", "LU threads=false"]` | 35.823 s (5%) | 418.114 ms | 11.85 GiB (1%) | 2142967 | | `["Laplace vectorized", "LU threads=true"]` | 36.065 s (5%) | 341.265 ms | 11.85 GiB (1%) | 2142967 | | `["Laplace vectorized", "assemble threads=false"]` | 1.408 s (5%) | 35.582 ms | 1.46 GiB (1%) | 52364 | | `["Laplace vectorized", "assemble threads=true"]` | 166.435 ms (5%) | | 1.48 GiB (1%) | 62713 | | `["Laplace vectorized", "gemv threads=false"]` | 158.776 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace vectorized", "gemv threads=true"]` | 79.799 ms (5%) | | 15.04 MiB (1%) | 636451 | | `["Laplace", "assemble threads=false"]` | 6.564 s (5%) | 39.406 ms | 1.46 GiB (1%) | 52364 | | `["Laplace", "assemble threads=true"]` | 956.386 ms (5%) | | 1.48 GiB (1%) | 62708 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace permuted"]` - `["Laplace vectorized"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1363467 s 2460 s 253232 s 655596249 s 0 s Memory: 31.013160705566406 GB (23200.43359375 MB free) Uptime: 1.64338914e6 sec Load Avg: 1.2 1.27 1.0 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Baseline result # Benchmark Report for */home/lfaria/runner-hmatrices/_work/HMatrices.jl/HMatrices.jl* ## Job Properties * Time of benchmark: 4 Nov 2023 - 10:35 * Package commit: 93d66d * Julia commit: bed2cd * Julia command flags: `-O3` * Environment variables: `OPENBLAS_NUM_THREADS => 1` `JULIA_NUM_THREADS => 8` ## Results Below is a table of this job's results, obtained by running the benchmarks. The values listed in the `ID` column have the structure `[parent_group, child_group, ..., key]`, and can be used to index into the BaseBenchmarks suite to retrieve the corresponding benchmarks. The percentages accompanying time and memory values in the below table are noise tolerances. The "true" time/memory value for a given benchmark is expected to fall within this percentage of the reported value. An empty cell means that the value was zero. | ID | time | GC time | memory | allocations | |-------------------------------------------------------------------|----------------:|-----------:|----------------:|------------:| | `["Compressors", "ACA(0.0, 9223372036854775807, 1.0e-6)"]` | 103.522 ms (5%) | 1.560 ms | 99.55 MiB (1%) | 61 | | `["Compressors", "PartialACA(0.0, 9223372036854775807, 1.0e-6)"]` | 1.465 ms (5%) | | 450.84 KiB (1%) | 45 | | `["Compressors", "TSVD(0.0, 9223372036854775807, 1.0e-6)"]` | 643.711 ms (5%) | 883.177 μs | 46.04 MiB (1%) | 16 | | `["Laplace", "LU threads=false"]` | 34.598 s (5%) | 150.343 ms | 12.33 GiB (1%) | 2253291 | | `["Laplace", "LU threads=true"]` | 26.844 s (5%) | 275.810 ms | 12.33 GiB (1%) | 2336680 | | `["Laplace", "assemble threads=false"]` | 7.080 s (5%) | 42.065 ms | 1.82 GiB (1%) | 133735 | | `["Laplace", "assemble threads=true"]` | 945.328 ms (5%) | | 1.82 GiB (1%) | 143978 | | `["Laplace", "gemv threads=false"]` | 148.801 ms (5%) | | 1.43 MiB (1%) | 2236 | | `["Laplace", "gemv threads=true"]` | 63.929 ms (5%) | | 5.33 MiB (1%) | 24656 | ## Benchmark Group List Here's a list of all the benchmark groups executed by this job: - `["Compressors"]` - `["Laplace"]` ## Julia versioninfo ``` Julia Version 1.9.3 Commit bed2cd540a1 (2023-08-24 14:43 UTC) Build Info: Official https://julialang.org/ release Platform Info: OS: Linux (x86_64-linux-gnu) Ubuntu 20.04.6 LTS uname: Linux 5.15.0-86-generic #96~20.04.1-Ubuntu SMP Thu Sep 21 13:23:37 UTC 2023 x86_64 x86_64 CPU: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz: speed user nice sys idle irq #1-40 2200 MHz 1365744 s 2460 s 253346 s 655656192 s 0 s Memory: 31.013160705566406 GB (23444.08984375 MB free) Uptime: 1.64354503e6 sec Load Avg: 2.38 1.54 1.13 WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-14.0.6 (ORCJIT, skylake-avx512) Threads: 8 on 40 virtual cores ``` --- # Runtime information | Runtime Info | | |:--|:--| | BLAS #threads | 20 | | `BLAS.vendor()` | `lbt` | | `Sys.CPU_THREADS` | 40 | `lscpu` output: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 46 bits physical, 48 bits virtual CPU(s): 40 On-line CPU(s) list: 0-39 Thread(s) per core: 2 Core(s) per socket: 10 Socket(s): 2 NUMA node(s): 2 Vendor ID: GenuineIntel CPU family: 6 Model: 85 Model name: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz Stepping: 4 CPU MHz: 2200.000 CPU max MHz: 3000,0000 CPU min MHz: 800,0000 BogoMIPS: 4400.00 Virtualization: VT-x L1d cache: 640 KiB L1i cache: 640 KiB L2 cache: 20 MiB L3 cache: 27,5 MiB NUMA node0 CPU(s): 0-9,20-29 NUMA node1 CPU(s): 10-19,30-39 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Meltdown: Mitigation; PTI Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable Vulnerability Retbleed: Mitigation; IBRS Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; IBRS, IBPB conditional, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke md_clear flush_l1d arch_capabilities | Cpu Property | Value | |:------------------ |:---------------------------------------------------------- | | Brand | Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz | | Vendor | :Intel | | Architecture | :Skylake | | Model | Family: 0x06, Model: 0x55, Stepping: 0x04, Type: 0x00 | | Cores | 10 physical cores, 20 logical cores (on executing CPU) | | | Hyperthreading hardware capability detected | | Clock Frequencies | 2200 / 3000 MHz (base/max), 100 MHz bus | | Data Cache | Level 1:3 : (32, 1024, 14080) kbytes | | | 64 byte cache line size | | Address Size | 48 bits virtual, 46 bits physical | | SIMD | 512 bit = 64 byte max. SIMD vector size | | Time Stamp Counter | TSC is accessible via `rdtsc` | | | TSC runs at constant rate (invariant from clock frequency) | | Perf. Monitoring | Performance Monitoring Counters (PMC) revision 4 | | | Available hardware counters per logical core: | | | 3 fixed-function counters of 48 bit width | | | 4 general-purpose counters of 48 bit width | | Hypervisor | No |