Skip to content

site_range keyword for truncate! #971

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 5 commits into from
Sep 8, 2022
Merged

site_range keyword for truncate! #971

merged 5 commits into from
Sep 8, 2022

Conversation

emstoudenmire
Copy link
Collaborator

Description

Adds a site_range keyword argument for truncate!. This is helpful for algorithms where it is known that only part of the MPS was changed, so as to avoid doing extra work. (Recent application of this is a specialized routine for applying MPOs which only act on part of an MPS.)

How Has This Been Tested?

Added a unit test to test/mps.jl

Checklist:

  • My code follows the style guidelines of this project. Please run using JuliaFormatter; format(".") in the base directory of the repository (~/.julia/dev/ITensors) to format your code according to our style guidelines.
  • I have performed a self-review of my own code.
  • I have commented my code, particularly in hard-to-understand areas.
  • I have added tests that verify the behavior of the changes I made.
  • I have made corresponding changes to the documentation.
  • My changes generate no new warnings.
  • Any dependent changes have been merged and published in downstream modules.

github-actions[bot]
github-actions bot reviewed Sep 7, 2022
View reviewed changes
mtfishman
mtfishman reviewed Sep 7, 2022
View reviewed changes
@mtfishman
Copy link
Member

mtfishman commented Sep 7, 2022 •
edited
Loading

Seems like a good idea. An alternative interface could be to allow passing a Vector of maxdim of the number of links, i.e.:

s = siteinds("S=1/2", 6)
psi = randomMPS(s; linkdims=4)
truncate!(psi; maxdim=[2, 3, 3, 3, 2])

Just bringing that up for debate but I think the site_range interface you propose is simpler.

For MPOs that only act on part of the MPS, I was picturing we could support something like this:

N = 10
site_range = 2:4
s = siteinds("S=1/2", N)
H = MPO(s[site_range])
psi = randomMPS(s)
Hpsi_sub = apply(H, psi[site_range])
Hpsi = copy(psi)
Hpsi[site_range] = Hpsi_sub

Not all of these operations are supported right now but it shouldn't be hard to support them. Note that the truncate! of a sub-MPS could be done in a similar way (i.e. slicing part of the MPS, truncating it, and then sticking it back into the original MPS). I'm curious how the slicing proposal I show above relates to what you had in mind for applying an MPO to a section of an MPS.

@emstoudenmire
Copy link
Collaborator Author

Interesting comments. I was thinking that we could eventually have an interface like how we have apply for gates, but for MPOs which are acting like "multi-site gates". These MPOs would just have a subset of the site indices, and would be assumed to act as the identity on all other sites. (At first we could require that the MPO have all of the sites in some contiguous range.)

Something like

G = make_gate_MPO(s[3:5])
psi = apply(G,psi; cutoff)

This is really helpful in particular for quantum computing simulations, which is the main use case for where I need it. It makes a big difference in the efficiency of the code.

@emstoudenmire
Copy link
Collaborator Author

The issue I'd have with the separate maxdims for the number of links is that to prevent any truncation, would one either have to put very large maxdims on the bonds you want the code to skip and or know the current linkdims in advance? (Not that they are hard to find out, but it just requires extra code.) Relatedly, even if the maxdim is high, the cutoff might still incur a truncation which one doesn't want, just because of some context where the truncation is known to be avoidable.

@github-actions
Copy link
Contributor

github-actions bot commented Sep 7, 2022

Benchmark result

Judge result

Benchmark Report for /home/runner/work/ITensors.jl/ITensors.jl

Job Properties

  • Time of benchmarks:
    • Target: 7 Sep 2022 - 20:38
    • Baseline: 7 Sep 2022 - 20:50
  • Package commits:
    • Target: 23b06d
    • Baseline: 8f538b
  • Julia commits:
    • Target: 5544a0
    • Baseline: 5544a0
  • Julia command flags:
    • Target: None
    • Baseline: None
  • Environment variables:
    • Target: None
    • Baseline: None

Results

A ratio greater than 1.0 denotes a possible regression (marked with ❌), while a ratio less
than 1.0 denotes a possible improvement (marked with ✅). 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
["getsetindex", "getindex indval end"] 0.90 (5%) ✅ 1.00 (1%)
["getsetindex", "getindex"] 0.92 (5%) ✅ 1.00 (1%)
["getsetindex", "setindex! end"] 1.07 (5%) ❌ 1.00 (1%)
["getsetindex", "setindex! indval end"] 0.94 (5%) ✅ 1.00 (1%)
["indexset", "constructor", "function"] 0.76 (5%) ✅ 1.00 (1%)
["indexset", "filter", "function"] 1.12 (5%) ❌ 1.00 (1%)
["indexset", "filter", "function, tuple"] 1.05 (5%) ❌ 1.00 (1%)
["indexset", "filter", "kwargs"] 1.28 (5%) ❌ 1.00 (1%)
["indexset", "set_functions", "noncommoninds, ITensor"] 0.95 (5%) ✅ 1.00 (1%)
["indexset", "set_functions", "unioninds, ITensor"] 0.90 (5%) ✅ 1.00 (1%)
["tagset", "tagset_unicode"] 1.06 (5%) ❌ 1.00 (1%)

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["autompo"]
  • ["contract"]
  • ["dmrg"]
  • ["getsetindex"]
  • ["indexset", "constructor"]
  • ["indexset", "filter"]
  • ["indexset", "set_functions"]
  • ["indexset", "set_functions", "uniqueinds"]
  • ["inplace"]
  • ["op"]
  • ["tagset"]

Julia versioninfo

Target

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8272CL CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2593 MHz        544 s          0 s        157 s      14848 s          0 s
       #2  2593 MHz      11755 s          0 s       1420 s       2428 s          0 s
  Memory: 6.781253814697266 GB (1276.5703125 MB free)
  Uptime: 1563.47 sec
  Load Avg:  1.0  1.0  0.84
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, skylake-avx512)
  Threads: 1 on 2 virtual cores

Baseline

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8272CL CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2593 MHz       7164 s          0 s       1035 s      14907 s          0 s
       #2  2593 MHz      11833 s          0 s       1448 s       9856 s          0 s
  Memory: 6.781253814697266 GB (1017.6328125 MB free)
  Uptime: 2319.54 sec
  Load Avg:  1.06  1.04  0.98
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, skylake-avx512)
  Threads: 1 on 2 virtual cores

Target result

Benchmark Report for /home/runner/work/ITensors.jl/ITensors.jl

Job Properties

  • Time of benchmark: 7 Sep 2022 - 20:38
  • Package commit: 23b06d
  • Julia commit: 5544a0
  • Julia command flags: None
  • Environment variables: None

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
["autompo", "Quartic Hamiltonian"] 52.926 s (5%) 6.554 s 12.43 GiB (1%) 170946222
["autompo", "Quartic QN Hamiltonian"] 73.350 s (5%) 9.731 s 21.63 GiB (1%) 227269091
["contract", "heff_2site"] 7.133 ms (5%) 19.41 MiB (1%) 196
["contract", "matmul_100"] 34.201 μs (5%) 80.47 KiB (1%) 15
["contract", "matmul_20"] 2.289 μs (5%) 5.55 KiB (1%) 14
["contract", "matmul_40"] 3.871 μs (5%) 14.92 KiB (1%) 14
["contract", "matmul_60"] 9.100 μs (5%) 30.47 KiB (1%) 15
["contract", "matmul_80"] 16.200 μs (5%) 52.34 KiB (1%) 15
["contract", "matmul_inplace_100"] 28.801 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_20"] 1.130 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_40"] 2.600 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_60"] 7.125 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_80"] 12.600 μs (5%) 1.25 KiB (1%) 10
["dmrg", "1d_S=1_heisenberg"] 23.135 s (5%) 937.829 ms 38.86 GiB (1%) 1944694
["dmrg", "1d_S=1_heisenberg_qn"] 10.519 s (5%) 1.201 s 9.80 GiB (1%) 55582438
["getsetindex", "getindex end"] 241.181 ns (5%) 800 bytes (1%) 5
["getsetindex", "getindex indval end"] 74.434 ns (5%) 384 bytes (1%) 3
["getsetindex", "getindex indval"] 82.849 ns (5%) 400 bytes (1%) 3
["getsetindex", "getindex"] 24.096 ns (5%) 16 bytes (1%) 1
["getsetindex", "setindex! end"] 336.568 ns (5%) 1.14 KiB (1%) 6
["getsetindex", "setindex! indval end"] 131.685 ns (5%) 736 bytes (1%) 3
["getsetindex", "setindex! indval"] 128.011 ns (5%) 752 bytes (1%) 3
["getsetindex", "setindex!"] 90.713 ns (5%) 368 bytes (1%) 1
["indexset", "constructor", "function"] 659.628 ns (5%) 2.20 KiB (1%) 11
["indexset", "constructor", "function, tuple"] 474.617 ns (5%) 2.09 KiB (1%) 7
["indexset", "filter", "function"] 227.928 ns (5%) 1.77 KiB (1%) 1
["indexset", "filter", "function, tuple"] 80.103 ns (5%) 368 bytes (1%) 1
["indexset", "filter", "kwargs"] 249.881 ns (5%) 1.77 KiB (1%) 1
["indexset", "set_functions", "commoninds, ITensor"] 514.068 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "noncommoninds, ITensor"] 605.331 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "prime, ITensor"] 193.242 ns (5%) 1.08 KiB (1%) 3
["indexset", "set_functions", "unioninds, ITensor"] 809.333 ns (5%) 4.23 KiB (1%) 6
["indexset", "set_functions", "uniqueinds", "3_inputs"] 623.815 ns (5%) 3.48 KiB (1%) 9
["indexset", "set_functions", "uniqueinds", "filter_not_tags"] 350.962 ns (5%) 1.23 KiB (1%) 4
["indexset", "set_functions", "uniqueinds", "filter_tags"] 242.465 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter0"] 152.127 ns (5%) 464 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter2"] 195.881 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds, ITensor"] 687.593 ns (5%) 2.92 KiB (1%) 7
["inplace", "axpy!"] 17.100 μs (5%) 79.42 KiB (1%) 16
["op", "op QN"] 8.434 μs (5%) 11.70 KiB (1%) 106
["op", "op"] 4.629 μs (5%) 5.20 KiB (1%) 44
["tagset", "tagset"] 288.493 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_long"] 368.604 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_unicode"] 431.668 ns (5%) 144 bytes (1%) 1

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["autompo"]
  • ["contract"]
  • ["dmrg"]
  • ["getsetindex"]
  • ["indexset", "constructor"]
  • ["indexset", "filter"]
  • ["indexset", "set_functions"]
  • ["indexset", "set_functions", "uniqueinds"]
  • ["inplace"]
  • ["op"]
  • ["tagset"]

Julia versioninfo

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8272CL CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2593 MHz        544 s          0 s        157 s      14848 s          0 s
       #2  2593 MHz      11755 s          0 s       1420 s       2428 s          0 s
  Memory: 6.781253814697266 GB (1276.5703125 MB free)
  Uptime: 1563.47 sec
  Load Avg:  1.0  1.0  0.84
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, skylake-avx512)
  Threads: 1 on 2 virtual cores

Baseline result

Benchmark Report for /home/runner/work/ITensors.jl/ITensors.jl

Job Properties

  • Time of benchmark: 7 Sep 2022 - 20:50
  • Package commit: 8f538b
  • Julia commit: 5544a0
  • Julia command flags: None
  • Environment variables: None

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
["autompo", "Quartic Hamiltonian"] 54.048 s (5%) 6.920 s 12.43 GiB (1%) 170946268
["autompo", "Quartic QN Hamiltonian"] 74.404 s (5%) 10.027 s 21.63 GiB (1%) 227269115
["contract", "heff_2site"] 7.214 ms (5%) 19.41 MiB (1%) 196
["contract", "matmul_100"] 34.701 μs (5%) 80.47 KiB (1%) 15
["contract", "matmul_20"] 2.344 μs (5%) 5.55 KiB (1%) 14
["contract", "matmul_40"] 3.914 μs (5%) 14.92 KiB (1%) 14
["contract", "matmul_60"] 9.200 μs (5%) 30.47 KiB (1%) 15
["contract", "matmul_80"] 16.400 μs (5%) 52.34 KiB (1%) 15
["contract", "matmul_inplace_100"] 28.800 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_20"] 1.150 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_40"] 2.600 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_60"] 7.025 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_80"] 12.700 μs (5%) 1.25 KiB (1%) 10
["dmrg", "1d_S=1_heisenberg"] 23.733 s (5%) 1.096 s 38.86 GiB (1%) 1944795
["dmrg", "1d_S=1_heisenberg_qn"] 10.690 s (5%) 1.123 s 9.80 GiB (1%) 55583019
["getsetindex", "getindex end"] 235.070 ns (5%) 800 bytes (1%) 5
["getsetindex", "getindex indval end"] 82.681 ns (5%) 384 bytes (1%) 3
["getsetindex", "getindex indval"] 85.344 ns (5%) 400 bytes (1%) 3
["getsetindex", "getindex"] 26.205 ns (5%) 16 bytes (1%) 1
["getsetindex", "setindex! end"] 314.101 ns (5%) 1.14 KiB (1%) 6
["getsetindex", "setindex! indval end"] 140.156 ns (5%) 736 bytes (1%) 3
["getsetindex", "setindex! indval"] 133.590 ns (5%) 752 bytes (1%) 3
["getsetindex", "setindex!"] 92.261 ns (5%) 368 bytes (1%) 1
["indexset", "constructor", "function"] 867.962 ns (5%) 2.20 KiB (1%) 11
["indexset", "constructor", "function, tuple"] 468.917 ns (5%) 2.09 KiB (1%) 7
["indexset", "filter", "function"] 202.674 ns (5%) 1.77 KiB (1%) 1
["indexset", "filter", "function, tuple"] 76.226 ns (5%) 368 bytes (1%) 1
["indexset", "filter", "kwargs"] 195.560 ns (5%) 1.77 KiB (1%) 1
["indexset", "set_functions", "commoninds, ITensor"] 515.109 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "noncommoninds, ITensor"] 638.467 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "prime, ITensor"] 197.834 ns (5%) 1.08 KiB (1%) 3
["indexset", "set_functions", "unioninds, ITensor"] 900.013 ns (5%) 4.23 KiB (1%) 6
["indexset", "set_functions", "uniqueinds", "3_inputs"] 623.821 ns (5%) 3.48 KiB (1%) 9
["indexset", "set_functions", "uniqueinds", "filter_not_tags"] 356.671 ns (5%) 1.23 KiB (1%) 4
["indexset", "set_functions", "uniqueinds", "filter_tags"] 250.254 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter0"] 154.252 ns (5%) 464 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter2"] 195.566 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds, ITensor"] 714.490 ns (5%) 2.92 KiB (1%) 7
["inplace", "axpy!"] 17.400 μs (5%) 79.42 KiB (1%) 16
["op", "op QN"] 8.567 μs (5%) 11.70 KiB (1%) 106
["op", "op"] 4.871 μs (5%) 5.20 KiB (1%) 44
["tagset", "tagset"] 281.658 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_long"] 355.560 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_unicode"] 405.533 ns (5%) 144 bytes (1%) 1

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["autompo"]
  • ["contract"]
  • ["dmrg"]
  • ["getsetindex"]
  • ["indexset", "constructor"]
  • ["indexset", "filter"]
  • ["indexset", "set_functions"]
  • ["indexset", "set_functions", "uniqueinds"]
  • ["inplace"]
  • ["op"]
  • ["tagset"]

Julia versioninfo

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8272CL CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2593 MHz       7164 s          0 s       1035 s      14907 s          0 s
       #2  2593 MHz      11833 s          0 s       1448 s       9856 s          0 s
  Memory: 6.781253814697266 GB (1017.6328125 MB free)
  Uptime: 2319.54 sec
  Load Avg:  1.06  1.04  0.98
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, skylake-avx512)
  Threads: 1 on 2 virtual cores

Runtime information

Runtime Info
BLAS #threads 1
BLAS.vendor() openblas64
Sys.CPU_THREADS 2

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):                          2
On-line CPU(s) list:             0,1
Thread(s) per core:              1
Core(s) per socket:              2
Socket(s):                       1
NUMA node(s):                    1
Vendor ID:                       GenuineIntel
CPU family:                      6
Model:                           85
Model name:                      Intel(R) Xeon(R) Platinum 8272CL CPU @ 2.60GHz
Stepping:                        7
CPU MHz:                         2593.905
BogoMIPS:                        5187.81
Hypervisor vendor:               Microsoft
Virtualization type:             full
L1d cache:                       64 KiB
L1i cache:                       64 KiB
L2 cache:                        2 MiB
L3 cache:                        35.8 MiB
NUMA node0 CPU(s):               0,1
Vulnerability Itlb multihit:     KVM: Mitigation: VMX unsupported
Vulnerability L1tf:              Mitigation; PTE Inversion
Vulnerability Mds:               Mitigation; Clear CPU buffers; SMT Host state unknown
Vulnerability Meltdown:          Mitigation; PTI
Vulnerability Mmio stale data:   Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Retbleed:          Vulnerable
Vulnerability Spec store bypass: Vulnerable
Vulnerability Spectre v1:        Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:        Mitigation; Retpolines, STIBP disabled, RSB filling
Vulnerability Srbds:             Not affected
Vulnerability Tsx async abort:   Mitigation; Clear CPU buffers; SMT Host state unknown
Flags:                           fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology cpuid pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm avx512f avx512dq rdseed adx smap clflushopt avx512cd avx512bw avx512vl xsaveopt xsavec xsaves md_clear
Cpu Property Value
Brand Intel(R) Xeon(R) Platinum 8272CL CPU @ 2.60GHz
Vendor :Intel
Architecture :Skylake
Model Family: 0x06, Model: 0x55, Stepping: 0x07, Type: 0x00
Cores 2 physical cores, 2 logical cores (on executing CPU)
No Hyperthreading hardware capability detected
Clock Frequencies Not supported by CPU
Data Cache Level 1:3 : (32, 1024, 36608) 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 increased at every clock cycle (non-invariant TSC)
Perf. Monitoring Performance Monitoring Counters (PMC) are not supported
Hypervisor Yes, Microsoft

@github-actions
Copy link
Contributor

github-actions bot commented Sep 7, 2022

Benchmark result

Judge result

Benchmark Report for /home/runner/work/ITensors.jl/ITensors.jl

Job Properties

  • Time of benchmarks:
    • Target: 7 Sep 2022 - 20:47
    • Baseline: 7 Sep 2022 - 21:01
  • Package commits:
    • Target: 72ed4c
    • Baseline: 8f538b
  • Julia commits:
    • Target: 5544a0
    • Baseline: 5544a0
  • Julia command flags:
    • Target: None
    • Baseline: None
  • Environment variables:
    • Target: None
    • Baseline: None

Results

A ratio greater than 1.0 denotes a possible regression (marked with ❌), while a ratio less
than 1.0 denotes a possible improvement (marked with ✅). 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
["contract", "matmul_100"] 0.90 (5%) ✅ 1.00 (1%)
["contract", "matmul_60"] 0.83 (5%) ✅ 1.00 (1%)
["contract", "matmul_inplace_20"] 0.90 (5%) ✅ 1.00 (1%)
["contract", "matmul_inplace_40"] 0.81 (5%) ✅ 1.00 (1%)
["contract", "matmul_inplace_60"] 1.16 (5%) ❌ 1.00 (1%)
["contract", "matmul_inplace_80"] 0.87 (5%) ✅ 1.00 (1%)
["getsetindex", "getindex indval end"] 0.95 (5%) ✅ 1.00 (1%)
["getsetindex", "getindex indval"] 1.07 (5%) ❌ 1.00 (1%)
["getsetindex", "setindex! end"] 1.11 (5%) ❌ 1.00 (1%)
["indexset", "constructor", "function, tuple"] 1.06 (5%) ❌ 1.00 (1%)
["indexset", "filter", "function"] 1.09 (5%) ❌ 1.00 (1%)
["indexset", "set_functions", "commoninds, ITensor"] 0.94 (5%) ✅ 1.00 (1%)
["indexset", "set_functions", "unioninds, ITensor"] 0.92 (5%) ✅ 1.00 (1%)
["indexset", "set_functions", "uniqueinds", "3_inputs"] 1.13 (5%) ❌ 1.00 (1%)
["indexset", "set_functions", "uniqueinds", "filter_tags"] 0.89 (5%) ✅ 1.00 (1%)
["indexset", "set_functions", "uniqueinds, ITensor"] 0.85 (5%) ✅ 1.00 (1%)
["op", "op QN"] 1.07 (5%) ❌ 1.00 (1%)
["tagset", "tagset_long"] 0.90 (5%) ✅ 1.00 (1%)
["tagset", "tagset_unicode"] 1.22 (5%) ❌ 1.00 (1%)

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["autompo"]
  • ["contract"]
  • ["dmrg"]
  • ["getsetindex"]
  • ["indexset", "constructor"]
  • ["indexset", "filter"]
  • ["indexset", "set_functions"]
  • ["indexset", "set_functions", "uniqueinds"]
  • ["inplace"]
  • ["op"]
  • ["tagset"]

Julia versioninfo

Target

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz      10757 s          0 s       1043 s       3793 s          0 s
       #2  2095 MHz       3036 s          0 s        693 s      11855 s          0 s
  Memory: 6.78125 GB (1501.1171875 MB free)
  Uptime: 1566.4 sec
  Load Avg:  1.05  1.04  0.89
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, skylake-avx512)
  Threads: 1 on 2 virtual cores

Baseline

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz      18236 s          0 s       1955 s       3815 s          0 s
       #2  2095 MHz       3099 s          0 s        730 s      20140 s          0 s
  Memory: 6.78125 GB (968.9453125 MB free)
  Uptime: 2408.02 sec
  Load Avg:  1.02  1.02  1.0
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, skylake-avx512)
  Threads: 1 on 2 virtual cores

Target result

Benchmark Report for /home/runner/work/ITensors.jl/ITensors.jl

Job Properties

  • Time of benchmark: 7 Sep 2022 - 20:47
  • Package commit: 72ed4c
  • Julia commit: 5544a0
  • Julia command flags: None
  • Environment variables: None

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
["autompo", "Quartic Hamiltonian"] 59.123 s (5%) 7.525 s 12.43 GiB (1%) 170946222
["autompo", "Quartic QN Hamiltonian"] 82.323 s (5%) 10.880 s 21.63 GiB (1%) 227269091
["contract", "heff_2site"] 7.800 ms (5%) 19.41 MiB (1%) 196
["contract", "matmul_100"] 34.100 μs (5%) 80.47 KiB (1%) 15
["contract", "matmul_20"] 2.511 μs (5%) 5.55 KiB (1%) 14
["contract", "matmul_40"] 3.929 μs (5%) 14.92 KiB (1%) 14
["contract", "matmul_60"] 8.700 μs (5%) 30.47 KiB (1%) 15
["contract", "matmul_80"] 16.000 μs (5%) 52.34 KiB (1%) 15
["contract", "matmul_inplace_100"] 27.700 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_20"] 1.200 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_40"] 2.478 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_60"] 7.800 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_80"] 12.200 μs (5%) 1.25 KiB (1%) 10
["dmrg", "1d_S=1_heisenberg"] 25.752 s (5%) 1.046 s 38.86 GiB (1%) 1944769
["dmrg", "1d_S=1_heisenberg_qn"] 11.260 s (5%) 1.078 s 9.80 GiB (1%) 55582864
["getsetindex", "getindex end"] 254.955 ns (5%) 800 bytes (1%) 5
["getsetindex", "getindex indval end"] 85.392 ns (5%) 384 bytes (1%) 3
["getsetindex", "getindex indval"] 87.984 ns (5%) 400 bytes (1%) 3
["getsetindex", "getindex"] 26.031 ns (5%) 16 bytes (1%) 1
["getsetindex", "setindex! end"] 340.005 ns (5%) 1.14 KiB (1%) 6
["getsetindex", "setindex! indval end"] 141.223 ns (5%) 736 bytes (1%) 3
["getsetindex", "setindex! indval"] 135.104 ns (5%) 752 bytes (1%) 3
["getsetindex", "setindex!"] 92.422 ns (5%) 368 bytes (1%) 1
["indexset", "constructor", "function"] 688.652 ns (5%) 2.20 KiB (1%) 11
["indexset", "constructor", "function, tuple"] 533.166 ns (5%) 2.09 KiB (1%) 7
["indexset", "filter", "function"] 238.607 ns (5%) 1.77 KiB (1%) 1
["indexset", "filter", "function, tuple"] 84.766 ns (5%) 368 bytes (1%) 1
["indexset", "filter", "kwargs"] 214.749 ns (5%) 1.77 KiB (1%) 1
["indexset", "set_functions", "commoninds, ITensor"] 518.038 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "noncommoninds, ITensor"] 617.513 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "prime, ITensor"] 196.380 ns (5%) 1.08 KiB (1%) 3
["indexset", "set_functions", "unioninds, ITensor"] 816.692 ns (5%) 4.23 KiB (1%) 6
["indexset", "set_functions", "uniqueinds", "3_inputs"] 695.371 ns (5%) 3.48 KiB (1%) 9
["indexset", "set_functions", "uniqueinds", "filter_not_tags"] 344.559 ns (5%) 1.23 KiB (1%) 4
["indexset", "set_functions", "uniqueinds", "filter_tags"] 239.933 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter0"] 151.574 ns (5%) 464 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter2"] 209.822 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds, ITensor"] 657.828 ns (5%) 2.92 KiB (1%) 7
["inplace", "axpy!"] 20.900 μs (5%) 79.42 KiB (1%) 16
["op", "op QN"] 9.667 μs (5%) 11.70 KiB (1%) 106
["op", "op"] 5.017 μs (5%) 5.20 KiB (1%) 44
["tagset", "tagset"] 320.286 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_long"] 356.576 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_unicode"] 480.219 ns (5%) 144 bytes (1%) 1

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["autompo"]
  • ["contract"]
  • ["dmrg"]
  • ["getsetindex"]
  • ["indexset", "constructor"]
  • ["indexset", "filter"]
  • ["indexset", "set_functions"]
  • ["indexset", "set_functions", "uniqueinds"]
  • ["inplace"]
  • ["op"]
  • ["tagset"]

Julia versioninfo

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz      10757 s          0 s       1043 s       3793 s          0 s
       #2  2095 MHz       3036 s          0 s        693 s      11855 s          0 s
  Memory: 6.78125 GB (1501.1171875 MB free)
  Uptime: 1566.4 sec
  Load Avg:  1.05  1.04  0.89
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, skylake-avx512)
  Threads: 1 on 2 virtual cores

Baseline result

Benchmark Report for /home/runner/work/ITensors.jl/ITensors.jl

Job Properties

  • Time of benchmark: 7 Sep 2022 - 21:1
  • Package commit: 8f538b
  • Julia commit: 5544a0
  • Julia command flags: None
  • Environment variables: None

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
["autompo", "Quartic Hamiltonian"] 59.821 s (5%) 7.399 s 12.43 GiB (1%) 170946268
["autompo", "Quartic QN Hamiltonian"] 84.141 s (5%) 11.134 s 21.63 GiB (1%) 227269095
["contract", "heff_2site"] 8.073 ms (5%) 19.41 MiB (1%) 196
["contract", "matmul_100"] 37.901 μs (5%) 80.47 KiB (1%) 15
["contract", "matmul_20"] 2.489 μs (5%) 5.55 KiB (1%) 14
["contract", "matmul_40"] 3.886 μs (5%) 14.92 KiB (1%) 14
["contract", "matmul_60"] 10.500 μs (5%) 30.47 KiB (1%) 15
["contract", "matmul_80"] 16.400 μs (5%) 52.34 KiB (1%) 15
["contract", "matmul_inplace_100"] 27.800 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_20"] 1.340 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_40"] 3.067 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_60"] 6.725 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_80"] 14.000 μs (5%) 1.25 KiB (1%) 10
["dmrg", "1d_S=1_heisenberg"] 26.759 s (5%) 1.193 s 38.86 GiB (1%) 1944673
["dmrg", "1d_S=1_heisenberg_qn"] 11.640 s (5%) 1.187 s 9.80 GiB (1%) 55581902
["getsetindex", "getindex end"] 258.789 ns (5%) 800 bytes (1%) 5
["getsetindex", "getindex indval end"] 90.023 ns (5%) 384 bytes (1%) 3
["getsetindex", "getindex indval"] 82.237 ns (5%) 400 bytes (1%) 3
["getsetindex", "getindex"] 26.834 ns (5%) 16 bytes (1%) 1
["getsetindex", "setindex! end"] 307.624 ns (5%) 1.14 KiB (1%) 6
["getsetindex", "setindex! indval end"] 141.113 ns (5%) 736 bytes (1%) 3
["getsetindex", "setindex! indval"] 133.298 ns (5%) 752 bytes (1%) 3
["getsetindex", "setindex!"] 93.581 ns (5%) 368 bytes (1%) 1
["indexset", "constructor", "function"] 678.795 ns (5%) 2.20 KiB (1%) 11
["indexset", "constructor", "function, tuple"] 501.565 ns (5%) 2.09 KiB (1%) 7
["indexset", "filter", "function"] 217.924 ns (5%) 1.77 KiB (1%) 1
["indexset", "filter", "function, tuple"] 83.948 ns (5%) 368 bytes (1%) 1
["indexset", "filter", "kwargs"] 210.853 ns (5%) 1.77 KiB (1%) 1
["indexset", "set_functions", "commoninds, ITensor"] 553.022 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "noncommoninds, ITensor"] 633.138 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "prime, ITensor"] 202.613 ns (5%) 1.08 KiB (1%) 3
["indexset", "set_functions", "unioninds, ITensor"] 884.641 ns (5%) 4.23 KiB (1%) 6
["indexset", "set_functions", "uniqueinds", "3_inputs"] 613.258 ns (5%) 3.48 KiB (1%) 9
["indexset", "set_functions", "uniqueinds", "filter_not_tags"] 351.490 ns (5%) 1.23 KiB (1%) 4
["indexset", "set_functions", "uniqueinds", "filter_tags"] 269.615 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter0"] 150.289 ns (5%) 464 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter2"] 217.276 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds, ITensor"] 769.586 ns (5%) 2.92 KiB (1%) 7
["inplace", "axpy!"] 20.600 μs (5%) 79.42 KiB (1%) 16
["op", "op QN"] 9.033 μs (5%) 11.70 KiB (1%) 106
["op", "op"] 5.100 μs (5%) 5.20 KiB (1%) 44
["tagset", "tagset"] 312.903 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_long"] 395.455 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_unicode"] 393.234 ns (5%) 144 bytes (1%) 1

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["autompo"]
  • ["contract"]
  • ["dmrg"]
  • ["getsetindex"]
  • ["indexset", "constructor"]
  • ["indexset", "filter"]
  • ["indexset", "set_functions"]
  • ["indexset", "set_functions", "uniqueinds"]
  • ["inplace"]
  • ["op"]
  • ["tagset"]

Julia versioninfo

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz      18236 s          0 s       1955 s       3815 s          0 s
       #2  2095 MHz       3099 s          0 s        730 s      20140 s          0 s
  Memory: 6.78125 GB (968.9453125 MB free)
  Uptime: 2408.02 sec
  Load Avg:  1.02  1.02  1.0
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, skylake-avx512)
  Threads: 1 on 2 virtual cores

Runtime information

Runtime Info
BLAS #threads 1
BLAS.vendor() openblas64
Sys.CPU_THREADS 2

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):                          2
On-line CPU(s) list:             0,1
Thread(s) per core:              1
Core(s) per socket:              2
Socket(s):                       1
NUMA node(s):                    1
Vendor ID:                       GenuineIntel
CPU family:                      6
Model:                           85
Model name:                      Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz
Stepping:                        4
CPU MHz:                         2095.078
BogoMIPS:                        4190.15
Hypervisor vendor:               Microsoft
Virtualization type:             full
L1d cache:                       64 KiB
L1i cache:                       64 KiB
L2 cache:                        2 MiB
L3 cache:                        35.8 MiB
NUMA node0 CPU(s):               0,1
Vulnerability Itlb multihit:     KVM: Mitigation: VMX unsupported
Vulnerability L1tf:              Mitigation; PTE Inversion
Vulnerability Mds:               Mitigation; Clear CPU buffers; SMT Host state unknown
Vulnerability Meltdown:          Mitigation; PTI
Vulnerability Mmio stale data:   Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Retbleed:          Vulnerable
Vulnerability Spec store bypass: Vulnerable
Vulnerability Spectre v1:        Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:        Mitigation; Retpolines, STIBP disabled, RSB filling
Vulnerability Srbds:             Not affected
Vulnerability Tsx async abort:   Mitigation; Clear CPU buffers; SMT Host state unknown
Flags:                           fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology cpuid pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm avx512f avx512dq rdseed adx smap clflushopt avx512cd avx512bw avx512vl xsaveopt xsavec xsaves md_clear
Cpu Property Value
Brand Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz
Vendor :Intel
Architecture :Skylake
Model Family: 0x06, Model: 0x55, Stepping: 0x04, Type: 0x00
Cores 2 physical cores, 2 logical cores (on executing CPU)
No Hyperthreading hardware capability detected
Clock Frequencies Not supported by CPU
Data Cache Level 1:3 : (32, 1024, 36608) 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 increased at every clock cycle (non-invariant TSC)
Perf. Monitoring Performance Monitoring Counters (PMC) are not supported
Hypervisor Yes, Microsoft

@mtfishman
Copy link
Member

Yeah that's a clear disadvantage of specifying a vector of maxdim, so let's scratch that idea.

Agreed it would be good to support that kind of interface for apply, the slicing interface I show above could be an internal implementation detail for that.

@github-actions
Copy link
Contributor

github-actions bot commented Sep 7, 2022

Benchmark result

Judge result

Benchmark Report for /home/runner/work/ITensors.jl/ITensors.jl

Job Properties

  • Time of benchmarks:
    • Target: 7 Sep 2022 - 21:09
    • Baseline: 7 Sep 2022 - 21:21
  • Package commits:
    • Target: e5ab91
    • Baseline: 8f538b
  • Julia commits:
    • Target: 5544a0
    • Baseline: 5544a0
  • Julia command flags:
    • Target: None
    • Baseline: None
  • Environment variables:
    • Target: None
    • Baseline: None

Results

A ratio greater than 1.0 denotes a possible regression (marked with ❌), while a ratio less
than 1.0 denotes a possible improvement (marked with ✅). 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
["indexset", "constructor", "function"] 1.10 (5%) ❌ 1.00 (1%)
["indexset", "filter", "function, tuple"] 1.14 (5%) ❌ 1.00 (1%)
["indexset", "set_functions", "uniqueinds", "3_inputs"] 0.93 (5%) ✅ 1.00 (1%)

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["autompo"]
  • ["contract"]
  • ["dmrg"]
  • ["getsetindex"]
  • ["indexset", "constructor"]
  • ["indexset", "filter"]
  • ["indexset", "set_functions"]
  • ["indexset", "set_functions", "uniqueinds"]
  • ["inplace"]
  • ["op"]
  • ["tagset"]

Julia versioninfo

Target

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8370C CPU @ 2.80GHz: 
              speed         user         nice          sys         idle          irq
       #1  2793 MHz      10984 s          0 s       1280 s       3936 s          0 s
       #2  2793 MHz        679 s          0 s        162 s      15334 s          0 s
  Memory: 6.78125 GB (1406.00390625 MB free)
  Uptime: 1623.85 sec
  Load Avg:  1.0  1.0  0.8
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, icelake-server)
  Threads: 1 on 2 virtual cores

Baseline

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8370C CPU @ 2.80GHz: 
              speed         user         nice          sys         idle          irq
       #1  2793 MHz      15491 s          0 s       1569 s       6168 s          0 s
       #2  2793 MHz       2403 s          0 s        711 s      20084 s          0 s
  Memory: 6.78125 GB (1674.47265625 MB free)
  Uptime: 2327.3 sec
  Load Avg:  1.0  1.0  0.93
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, icelake-server)
  Threads: 1 on 2 virtual cores

Target result

Benchmark Report for /home/runner/work/ITensors.jl/ITensors.jl

Job Properties

  • Time of benchmark: 7 Sep 2022 - 21:9
  • Package commit: e5ab91
  • Julia commit: 5544a0
  • Julia command flags: None
  • Environment variables: None

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
["autompo", "Quartic Hamiltonian"] 49.194 s (5%) 6.019 s 12.43 GiB (1%) 170946222
["autompo", "Quartic QN Hamiltonian"] 70.380 s (5%) 9.281 s 21.63 GiB (1%) 227269091
["contract", "heff_2site"] 6.872 ms (5%) 19.41 MiB (1%) 196
["contract", "matmul_100"] 37.100 μs (5%) 80.47 KiB (1%) 15
["contract", "matmul_20"] 2.233 μs (5%) 5.55 KiB (1%) 14
["contract", "matmul_40"] 4.029 μs (5%) 14.92 KiB (1%) 14
["contract", "matmul_60"] 11.100 μs (5%) 30.47 KiB (1%) 15
["contract", "matmul_80"] 16.700 μs (5%) 52.34 KiB (1%) 15
["contract", "matmul_inplace_100"] 33.700 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_20"] 1.110 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_40"] 2.889 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_60"] 9.600 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_80"] 14.900 μs (5%) 1.25 KiB (1%) 10
["dmrg", "1d_S=1_heisenberg"] 22.493 s (5%) 745.793 ms 38.86 GiB (1%) 1944739
["dmrg", "1d_S=1_heisenberg_qn"] 9.681 s (5%) 844.377 ms 9.80 GiB (1%) 55581908
["getsetindex", "getindex end"] 226.154 ns (5%) 800 bytes (1%) 5
["getsetindex", "getindex indval end"] 68.033 ns (5%) 384 bytes (1%) 3
["getsetindex", "getindex indval"] 72.979 ns (5%) 400 bytes (1%) 3
["getsetindex", "getindex"] 23.747 ns (5%) 16 bytes (1%) 1
["getsetindex", "setindex! end"] 317.333 ns (5%) 1.14 KiB (1%) 6
["getsetindex", "setindex! indval end"] 110.863 ns (5%) 736 bytes (1%) 3
["getsetindex", "setindex! indval"] 109.373 ns (5%) 752 bytes (1%) 3
["getsetindex", "setindex!"] 78.947 ns (5%) 368 bytes (1%) 1
["indexset", "constructor", "function"] 757.561 ns (5%) 2.20 KiB (1%) 11
["indexset", "constructor", "function, tuple"] 443.439 ns (5%) 2.09 KiB (1%) 7
["indexset", "filter", "function"] 225.112 ns (5%) 1.77 KiB (1%) 1
["indexset", "filter", "function, tuple"] 68.490 ns (5%) 368 bytes (1%) 1
["indexset", "filter", "kwargs"] 193.506 ns (5%) 1.77 KiB (1%) 1
["indexset", "set_functions", "commoninds, ITensor"] 466.667 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "noncommoninds, ITensor"] 519.474 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "prime, ITensor"] 157.576 ns (5%) 1.08 KiB (1%) 3
["indexset", "set_functions", "unioninds, ITensor"] 687.333 ns (5%) 4.23 KiB (1%) 6
["indexset", "set_functions", "uniqueinds", "3_inputs"] 573.889 ns (5%) 3.48 KiB (1%) 9
["indexset", "set_functions", "uniqueinds", "filter_not_tags"] 325.333 ns (5%) 1.23 KiB (1%) 4
["indexset", "set_functions", "uniqueinds", "filter_tags"] 214.770 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter0"] 145.154 ns (5%) 464 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter2"] 168.019 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds, ITensor"] 673.203 ns (5%) 2.92 KiB (1%) 7
["inplace", "axpy!"] 16.700 μs (5%) 79.42 KiB (1%) 16
["op", "op QN"] 8.167 μs (5%) 11.70 KiB (1%) 106
["op", "op"] 4.571 μs (5%) 5.20 KiB (1%) 44
["tagset", "tagset"] 225.055 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_long"] 278.716 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_unicode"] 327.313 ns (5%) 144 bytes (1%) 1

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["autompo"]
  • ["contract"]
  • ["dmrg"]
  • ["getsetindex"]
  • ["indexset", "constructor"]
  • ["indexset", "filter"]
  • ["indexset", "set_functions"]
  • ["indexset", "set_functions", "uniqueinds"]
  • ["inplace"]
  • ["op"]
  • ["tagset"]

Julia versioninfo

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8370C CPU @ 2.80GHz: 
              speed         user         nice          sys         idle          irq
       #1  2793 MHz      10984 s          0 s       1280 s       3936 s          0 s
       #2  2793 MHz        679 s          0 s        162 s      15334 s          0 s
  Memory: 6.78125 GB (1406.00390625 MB free)
  Uptime: 1623.85 sec
  Load Avg:  1.0  1.0  0.8
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, icelake-server)
  Threads: 1 on 2 virtual cores

Baseline result

Benchmark Report for /home/runner/work/ITensors.jl/ITensors.jl

Job Properties

  • Time of benchmark: 7 Sep 2022 - 21:21
  • Package commit: 8f538b
  • Julia commit: 5544a0
  • Julia command flags: None
  • Environment variables: None

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
["autompo", "Quartic Hamiltonian"] 49.106 s (5%) 6.158 s 12.43 GiB (1%) 170946268
["autompo", "Quartic QN Hamiltonian"] 70.298 s (5%) 8.895 s 21.63 GiB (1%) 227269111
["contract", "heff_2site"] 6.714 ms (5%) 19.41 MiB (1%) 196
["contract", "matmul_100"] 37.200 μs (5%) 80.47 KiB (1%) 15
["contract", "matmul_20"] 2.189 μs (5%) 5.55 KiB (1%) 14
["contract", "matmul_40"] 4.043 μs (5%) 14.92 KiB (1%) 14
["contract", "matmul_60"] 10.900 μs (5%) 30.47 KiB (1%) 15
["contract", "matmul_80"] 17.000 μs (5%) 52.34 KiB (1%) 15
["contract", "matmul_inplace_100"] 33.800 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_20"] 1.130 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_40"] 2.844 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_60"] 9.500 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_80"] 14.900 μs (5%) 1.25 KiB (1%) 10
["dmrg", "1d_S=1_heisenberg"] 22.252 s (5%) 734.250 ms 38.86 GiB (1%) 1944701
["dmrg", "1d_S=1_heisenberg_qn"] 9.636 s (5%) 815.590 ms 9.80 GiB (1%) 55582689
["getsetindex", "getindex end"] 224.615 ns (5%) 800 bytes (1%) 5
["getsetindex", "getindex indval end"] 68.237 ns (5%) 384 bytes (1%) 3
["getsetindex", "getindex indval"] 72.364 ns (5%) 400 bytes (1%) 3
["getsetindex", "getindex"] 22.846 ns (5%) 16 bytes (1%) 1
["getsetindex", "setindex! end"] 307.111 ns (5%) 1.14 KiB (1%) 6
["getsetindex", "setindex! indval end"] 110.862 ns (5%) 736 bytes (1%) 3
["getsetindex", "setindex! indval"] 110.968 ns (5%) 752 bytes (1%) 3
["getsetindex", "setindex!"] 77.399 ns (5%) 368 bytes (1%) 1
["indexset", "constructor", "function"] 690.655 ns (5%) 2.20 KiB (1%) 11
["indexset", "constructor", "function, tuple"] 462.626 ns (5%) 2.09 KiB (1%) 7
["indexset", "filter", "function"] 226.233 ns (5%) 1.77 KiB (1%) 1
["indexset", "filter", "function, tuple"] 60.284 ns (5%) 368 bytes (1%) 1
["indexset", "filter", "kwargs"] 191.560 ns (5%) 1.77 KiB (1%) 1
["indexset", "set_functions", "commoninds, ITensor"] 467.697 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "noncommoninds, ITensor"] 510.526 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "prime, ITensor"] 165.023 ns (5%) 1.08 KiB (1%) 3
["indexset", "set_functions", "unioninds, ITensor"] 674.660 ns (5%) 4.23 KiB (1%) 6
["indexset", "set_functions", "uniqueinds", "3_inputs"] 620.000 ns (5%) 3.48 KiB (1%) 9
["indexset", "set_functions", "uniqueinds", "filter_not_tags"] 330.667 ns (5%) 1.23 KiB (1%) 4
["indexset", "set_functions", "uniqueinds", "filter_tags"] 215.369 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter0"] 144.202 ns (5%) 464 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter2"] 167.083 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds, ITensor"] 643.137 ns (5%) 2.92 KiB (1%) 7
["inplace", "axpy!"] 17.100 μs (5%) 79.42 KiB (1%) 16
["op", "op QN"] 8.333 μs (5%) 11.70 KiB (1%) 106
["op", "op"] 4.714 μs (5%) 5.20 KiB (1%) 44
["tagset", "tagset"] 228.571 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_long"] 291.220 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_unicode"] 330.837 ns (5%) 144 bytes (1%) 1

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["autompo"]
  • ["contract"]
  • ["dmrg"]
  • ["getsetindex"]
  • ["indexset", "constructor"]
  • ["indexset", "filter"]
  • ["indexset", "set_functions"]
  • ["indexset", "set_functions", "uniqueinds"]
  • ["inplace"]
  • ["op"]
  • ["tagset"]

Julia versioninfo

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8370C CPU @ 2.80GHz: 
              speed         user         nice          sys         idle          irq
       #1  2793 MHz      15491 s          0 s       1569 s       6168 s          0 s
       #2  2793 MHz       2403 s          0 s        711 s      20084 s          0 s
  Memory: 6.78125 GB (1674.47265625 MB free)
  Uptime: 2327.3 sec
  Load Avg:  1.0  1.0  0.93
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, icelake-server)
  Threads: 1 on 2 virtual cores

Runtime information

Runtime Info
BLAS #threads 1
BLAS.vendor() openblas64
Sys.CPU_THREADS 2

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):                          2
On-line CPU(s) list:             0,1
Thread(s) per core:              1
Core(s) per socket:              2
Socket(s):                       1
NUMA node(s):                    1
Vendor ID:                       GenuineIntel
CPU family:                      6
Model:                           106
Model name:                      Intel(R) Xeon(R) Platinum 8370C CPU @ 2.80GHz
Stepping:                        6
CPU MHz:                         2793.436
BogoMIPS:                        5586.87
Hypervisor vendor:               Microsoft
Virtualization type:             full
L1d cache:                       96 KiB
L1i cache:                       64 KiB
L2 cache:                        2.5 MiB
L3 cache:                        48 MiB
NUMA node0 CPU(s):               0,1
Vulnerability Itlb multihit:     KVM: Mitigation: VMX unsupported
Vulnerability L1tf:              Mitigation; PTE Inversion
Vulnerability Mds:               Mitigation; Clear CPU buffers; SMT Host state unknown
Vulnerability Meltdown:          Mitigation; PTI
Vulnerability Mmio stale data:   Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Retbleed:          Not affected
Vulnerability Spec store bypass: Vulnerable
Vulnerability Spectre v1:        Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:        Mitigation; Retpolines, STIBP disabled, RSB filling
Vulnerability Srbds:             Not affected
Vulnerability Tsx async abort:   Mitigation; Clear CPU buffers; SMT Host state unknown
Flags:                           fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology cpuid pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm avx512f avx512dq rdseed adx smap clflushopt avx512cd avx512bw avx512vl xsaveopt xsavec xsaves md_clear
Cpu Property Value
Brand Intel(R) Xeon(R) Platinum 8370C CPU @ 2.80GHz
Vendor :Intel
Architecture :UnknownIntel
Model Family: 0x06, Model: 0x6a, Stepping: 0x06, Type: 0x00
Cores 2 physical cores, 2 logical cores (on executing CPU)
No Hyperthreading hardware capability detected
Clock Frequencies Not supported by CPU
Data Cache Level 1:3 : (48, 1280, 49152) 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 increased at every clock cycle (non-invariant TSC)
Perf. Monitoring Performance Monitoring Counters (PMC) are not supported
Hypervisor Yes, Microsoft

@codecov-commenter
Copy link

codecov-commenter commented Sep 7, 2022 •
edited
Loading

Codecov Report

Merging #971 (d76cb1c) into main (3221d34) will increase coverage by 0.59%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##             main     #971      +/-   ##
==========================================
+ Coverage   65.94%   66.53%   +0.59%     
==========================================
  Files          91       91              
  Lines        9279     9918     +639     
==========================================
+ Hits         6119     6599     +480     
- Misses       3160     3319     +159
Impacted Files Coverage Δ
src/mps/abstractmps.jl 85.20% <100.00%> (+0.46%) ⬆️
src/nullspace.jl 46.87% <0.00%> (-0.91%) ⬇️
src/tagset.jl 88.04% <0.00%> (-0.71%) ⬇️
src/qn/qn.jl 89.36% <0.00%> (-0.45%) ⬇️
src/mps/mps.jl 91.44% <0.00%> (-0.20%) ⬇️
src/readwrite.jl 0.00% <0.00%> (ø)
src/precompile.jl 0.00% <0.00%> (ø)
src/Ops/trotter.jl 100.00% <0.00%> (ø)
src/mps/observer.jl 100.00% <0.00%> (ø)
src/qn/qnindexset.jl 100.00% <0.00%> (ø)
... and 56 more

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

@github-actions
Copy link
Contributor

github-actions bot commented Sep 8, 2022

Benchmark result

Judge result

Benchmark Report for /home/runner/work/ITensors.jl/ITensors.jl

Job Properties

  • Time of benchmarks:
    • Target: 8 Sep 2022 - 14:55
    • Baseline: 8 Sep 2022 - 15:10
  • Package commits:
    • Target: aff919
    • Baseline: 3221d3
  • Julia commits:
    • Target: 5544a0
    • Baseline: 5544a0
  • Julia command flags:
    • Target: None
    • Baseline: None
  • Environment variables:
    • Target: None
    • Baseline: None

Results

A ratio greater than 1.0 denotes a possible regression (marked with ❌), while a ratio less
than 1.0 denotes a possible improvement (marked with ✅). 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
["contract", "matmul_80"] 1.08 (5%) ❌ 1.00 (1%)
["contract", "matmul_inplace_40"] 0.94 (5%) ✅ 1.00 (1%)
["contract", "matmul_inplace_60"] 0.94 (5%) ✅ 1.00 (1%)
["contract", "matmul_inplace_80"] 1.09 (5%) ❌ 1.00 (1%)
["getsetindex", "getindex"] 1.09 (5%) ❌ 1.00 (1%)
["getsetindex", "setindex! end"] 1.09 (5%) ❌ 1.00 (1%)
["getsetindex", "setindex! indval"] 1.07 (5%) ❌ 1.00 (1%)
["indexset", "constructor", "function"] 0.86 (5%) ✅ 1.00 (1%)
["indexset", "filter", "function"] 0.91 (5%) ✅ 1.00 (1%)
["indexset", "filter", "function, tuple"] 1.07 (5%) ❌ 1.00 (1%)
["indexset", "filter", "kwargs"] 0.81 (5%) ✅ 1.00 (1%)
["indexset", "set_functions", "prime, ITensor"] 1.08 (5%) ❌ 1.00 (1%)
["indexset", "set_functions", "uniqueinds", "nofilter0"] 1.39 (5%) ❌ 1.00 (1%)
["inplace", "axpy!"] 0.91 (5%) ✅ 1.00 (1%)
["op", "op"] 1.09 (5%) ❌ 1.00 (1%)
["tagset", "tagset"] 0.93 (5%) ✅ 1.00 (1%)
["tagset", "tagset_unicode"] 0.93 (5%) ✅ 1.00 (1%)

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["autompo"]
  • ["contract"]
  • ["dmrg"]
  • ["getsetindex"]
  • ["indexset", "constructor"]
  • ["indexset", "filter"]
  • ["indexset", "set_functions"]
  • ["indexset", "set_functions", "uniqueinds"]
  • ["inplace"]
  • ["op"]
  • ["tagset"]

Julia versioninfo

Target

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz        995 s          2 s        215 s      15098 s          0 s
       #2  2095 MHz      13255 s          1 s       1523 s       1654 s          0 s
  Memory: 6.781253814697266 GB (1231.96875 MB free)
  Uptime: 1648.64 sec
  Load Avg:  1.05  1.04  0.9
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, skylake-avx512)
  Threads: 1 on 2 virtual cores

Baseline

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz       2875 s          2 s        472 s      21567 s          0 s
       #2  2095 MHz      19145 s          1 s       2196 s       3718 s          0 s
  Memory: 6.781253814697266 GB (1206.34375 MB free)
  Uptime: 2512.5 sec
  Load Avg:  1.02  1.03  1.0
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, skylake-avx512)
  Threads: 1 on 2 virtual cores

Target result

Benchmark Report for /home/runner/work/ITensors.jl/ITensors.jl

Job Properties

  • Time of benchmark: 8 Sep 2022 - 14:55
  • Package commit: aff919
  • Julia commit: 5544a0
  • Julia command flags: None
  • Environment variables: None

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
["autompo", "Quartic Hamiltonian"] 62.121 s (5%) 7.605 s 12.49 GiB (1%) 171115648
["autompo", "Quartic QN Hamiltonian"] 86.345 s (5%) 11.370 s 21.63 GiB (1%) 227269669
["contract", "heff_2site"] 8.149 ms (5%) 19.41 MiB (1%) 196
["contract", "matmul_100"] 38.700 μs (5%) 80.47 KiB (1%) 15
["contract", "matmul_20"] 2.611 μs (5%) 5.55 KiB (1%) 14
["contract", "matmul_40"] 4.414 μs (5%) 14.92 KiB (1%) 14
["contract", "matmul_60"] 10.600 μs (5%) 30.47 KiB (1%) 15
["contract", "matmul_80"] 18.700 μs (5%) 52.34 KiB (1%) 15
["contract", "matmul_inplace_100"] 32.101 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_20"] 1.290 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_40"] 2.850 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_60"] 7.767 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_80"] 15.100 μs (5%) 1.25 KiB (1%) 10
["dmrg", "1d_S=1_heisenberg"] 26.821 s (5%) 1.126 s 38.86 GiB (1%) 1932453
["dmrg", "1d_S=1_heisenberg_qn"] 12.053 s (5%) 1.191 s 9.80 GiB (1%) 55580930
["getsetindex", "getindex end"] 280.970 ns (5%) 800 bytes (1%) 5
["getsetindex", "getindex indval end"] 87.294 ns (5%) 384 bytes (1%) 3
["getsetindex", "getindex indval"] 95.968 ns (5%) 400 bytes (1%) 3
["getsetindex", "getindex"] 28.844 ns (5%) 16 bytes (1%) 1
["getsetindex", "setindex! end"] 392.579 ns (5%) 1.14 KiB (1%) 6
["getsetindex", "setindex! indval end"] 147.027 ns (5%) 736 bytes (1%) 3
["getsetindex", "setindex! indval"] 150.902 ns (5%) 752 bytes (1%) 3
["getsetindex", "setindex!"] 102.317 ns (5%) 368 bytes (1%) 1
["indexset", "constructor", "function"] 791.511 ns (5%) 2.20 KiB (1%) 11
["indexset", "constructor", "function, tuple"] 540.989 ns (5%) 2.09 KiB (1%) 7
["indexset", "filter", "function"] 264.896 ns (5%) 1.77 KiB (1%) 1
["indexset", "filter", "function, tuple"] 91.412 ns (5%) 368 bytes (1%) 1
["indexset", "filter", "kwargs"] 247.499 ns (5%) 1.77 KiB (1%) 1
["indexset", "set_functions", "commoninds, ITensor"] 587.851 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "noncommoninds, ITensor"] 745.263 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "prime, ITensor"] 212.957 ns (5%) 1.08 KiB (1%) 3
["indexset", "set_functions", "unioninds, ITensor"] 904.181 ns (5%) 4.23 KiB (1%) 6
["indexset", "set_functions", "uniqueinds", "3_inputs"] 743.128 ns (5%) 3.48 KiB (1%) 9
["indexset", "set_functions", "uniqueinds", "filter_not_tags"] 418.598 ns (5%) 1.23 KiB (1%) 4
["indexset", "set_functions", "uniqueinds", "filter_tags"] 288.301 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter0"] 249.884 ns (5%) 464 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter2"] 226.382 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds, ITensor"] 818.824 ns (5%) 2.92 KiB (1%) 7
["inplace", "axpy!"] 19.101 μs (5%) 79.42 KiB (1%) 16
["op", "op QN"] 9.600 μs (5%) 11.70 KiB (1%) 106
["op", "op"] 5.534 μs (5%) 5.55 KiB (1%) 45
["tagset", "tagset"] 322.120 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_long"] 444.955 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_unicode"] 480.734 ns (5%) 144 bytes (1%) 1

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["autompo"]
  • ["contract"]
  • ["dmrg"]
  • ["getsetindex"]
  • ["indexset", "constructor"]
  • ["indexset", "filter"]
  • ["indexset", "set_functions"]
  • ["indexset", "set_functions", "uniqueinds"]
  • ["inplace"]
  • ["op"]
  • ["tagset"]

Julia versioninfo

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz        995 s          2 s        215 s      15098 s          0 s
       #2  2095 MHz      13255 s          1 s       1523 s       1654 s          0 s
  Memory: 6.781253814697266 GB (1231.96875 MB free)
  Uptime: 1648.64 sec
  Load Avg:  1.05  1.04  0.9
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, skylake-avx512)
  Threads: 1 on 2 virtual cores

Baseline result

Benchmark Report for /home/runner/work/ITensors.jl/ITensors.jl

Job Properties

  • Time of benchmark: 8 Sep 2022 - 15:10
  • Package commit: 3221d3
  • Julia commit: 5544a0
  • Julia command flags: None
  • Environment variables: None

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
["autompo", "Quartic Hamiltonian"] 63.262 s (5%) 8.125 s 12.49 GiB (1%) 171115661
["autompo", "Quartic QN Hamiltonian"] 87.130 s (5%) 11.542 s 21.63 GiB (1%) 227269097
["contract", "heff_2site"] 8.171 ms (5%) 19.41 MiB (1%) 196
["contract", "matmul_100"] 39.001 μs (5%) 80.47 KiB (1%) 15
["contract", "matmul_20"] 2.633 μs (5%) 5.55 KiB (1%) 14
["contract", "matmul_40"] 4.300 μs (5%) 14.92 KiB (1%) 14
["contract", "matmul_60"] 10.400 μs (5%) 30.47 KiB (1%) 15
["contract", "matmul_80"] 17.301 μs (5%) 52.34 KiB (1%) 15
["contract", "matmul_inplace_100"] 33.100 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_20"] 1.320 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_40"] 3.038 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_60"] 8.300 μs (5%) 1.25 KiB (1%) 10
["contract", "matmul_inplace_80"] 13.900 μs (5%) 1.25 KiB (1%) 10
["dmrg", "1d_S=1_heisenberg"] 27.238 s (5%) 1.244 s 38.86 GiB (1%) 1932453
["dmrg", "1d_S=1_heisenberg_qn"] 12.319 s (5%) 1.259 s 9.80 GiB (1%) 55581158
["getsetindex", "getindex end"] 273.719 ns (5%) 800 bytes (1%) 5
["getsetindex", "getindex indval end"] 87.604 ns (5%) 384 bytes (1%) 3
["getsetindex", "getindex indval"] 94.934 ns (5%) 400 bytes (1%) 3
["getsetindex", "getindex"] 26.533 ns (5%) 16 bytes (1%) 1
["getsetindex", "setindex! end"] 359.906 ns (5%) 1.14 KiB (1%) 6
["getsetindex", "setindex! indval end"] 146.579 ns (5%) 736 bytes (1%) 3
["getsetindex", "setindex! indval"] 140.992 ns (5%) 752 bytes (1%) 3
["getsetindex", "setindex!"] 98.949 ns (5%) 368 bytes (1%) 1
["indexset", "constructor", "function"] 919.170 ns (5%) 2.20 KiB (1%) 11
["indexset", "constructor", "function, tuple"] 539.896 ns (5%) 2.09 KiB (1%) 7
["indexset", "filter", "function"] 292.293 ns (5%) 1.77 KiB (1%) 1
["indexset", "filter", "function, tuple"] 85.788 ns (5%) 368 bytes (1%) 1
["indexset", "filter", "kwargs"] 303.699 ns (5%) 1.77 KiB (1%) 1
["indexset", "set_functions", "commoninds, ITensor"] 591.166 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "noncommoninds, ITensor"] 756.942 ns (5%) 2.84 KiB (1%) 5
["indexset", "set_functions", "prime, ITensor"] 196.495 ns (5%) 1.08 KiB (1%) 3
["indexset", "set_functions", "unioninds, ITensor"] 886.111 ns (5%) 4.23 KiB (1%) 6
["indexset", "set_functions", "uniqueinds", "3_inputs"] 725.697 ns (5%) 3.48 KiB (1%) 9
["indexset", "set_functions", "uniqueinds", "filter_not_tags"] 420.106 ns (5%) 1.23 KiB (1%) 4
["indexset", "set_functions", "uniqueinds", "filter_tags"] 279.436 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter0"] 179.575 ns (5%) 464 bytes (1%) 2
["indexset", "set_functions", "uniqueinds", "nofilter2"] 218.344 ns (5%) 976 bytes (1%) 2
["indexset", "set_functions", "uniqueinds, ITensor"] 816.471 ns (5%) 2.92 KiB (1%) 7
["inplace", "axpy!"] 20.900 μs (5%) 79.42 KiB (1%) 16
["op", "op QN"] 9.600 μs (5%) 11.70 KiB (1%) 106
["op", "op"] 5.067 μs (5%) 5.55 KiB (1%) 45
["tagset", "tagset"] 346.083 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_long"] 442.429 ns (5%) 144 bytes (1%) 1
["tagset", "tagset_unicode"] 519.276 ns (5%) 144 bytes (1%) 1

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["autompo"]
  • ["contract"]
  • ["dmrg"]
  • ["getsetindex"]
  • ["indexset", "constructor"]
  • ["indexset", "filter"]
  • ["indexset", "set_functions"]
  • ["indexset", "set_functions", "uniqueinds"]
  • ["inplace"]
  • ["op"]
  • ["tagset"]

Julia versioninfo

Julia Version 1.8.0
Commit 5544a0fab76 (2022-08-17 13:38 UTC)
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 20.04.5 LTS
  uname: Linux 5.15.0-1019-azure #24~20.04.1-Ubuntu SMP Tue Aug 23 15:52:52 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz       2875 s          2 s        472 s      21567 s          0 s
       #2  2095 MHz      19145 s          1 s       2196 s       3718 s          0 s
  Memory: 6.781253814697266 GB (1206.34375 MB free)
  Uptime: 2512.5 sec
  Load Avg:  1.02  1.03  1.0
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-13.0.1 (ORCJIT, skylake-avx512)
  Threads: 1 on 2 virtual cores

Runtime information

Runtime Info
BLAS #threads 1
BLAS.vendor() openblas64
Sys.CPU_THREADS 2

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):                          2
On-line CPU(s) list:             0,1
Thread(s) per core:              1
Core(s) per socket:              2
Socket(s):                       1
NUMA node(s):                    1
Vendor ID:                       GenuineIntel
CPU family:                      6
Model:                           85
Model name:                      Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz
Stepping:                        4
CPU MHz:                         2095.077
BogoMIPS:                        4190.15
Hypervisor vendor:               Microsoft
Virtualization type:             full
L1d cache:                       64 KiB
L1i cache:                       64 KiB
L2 cache:                        2 MiB
L3 cache:                        35.8 MiB
NUMA node0 CPU(s):               0,1
Vulnerability Itlb multihit:     KVM: Mitigation: VMX unsupported
Vulnerability L1tf:              Mitigation; PTE Inversion
Vulnerability Mds:               Mitigation; Clear CPU buffers; SMT Host state unknown
Vulnerability Meltdown:          Mitigation; PTI
Vulnerability Mmio stale data:   Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Vulnerability Retbleed:          Vulnerable
Vulnerability Spec store bypass: Vulnerable
Vulnerability Spectre v1:        Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:        Mitigation; Retpolines, STIBP disabled, RSB filling
Vulnerability Srbds:             Not affected
Vulnerability Tsx async abort:   Mitigation; Clear CPU buffers; SMT Host state unknown
Flags:                           fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology cpuid pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx avx512f avx512dq rdseed adx smap clflushopt avx512cd avx512bw avx512vl xsaveopt xsavec xsaves md_clear
Cpu Property Value
Brand Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz
Vendor :Intel
Architecture :Skylake
Model Family: 0x06, Model: 0x55, Stepping: 0x04, Type: 0x00
Cores 2 physical cores, 2 logical cores (on executing CPU)
No Hyperthreading hardware capability detected
Clock Frequencies Not supported by CPU
Data Cache Level 1:3 : (32, 1024, 36608) 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 increased at every clock cycle (non-invariant TSC)
Perf. Monitoring Performance Monitoring Counters (PMC) are not supported
Hypervisor Yes, Microsoft

@mtfishman
Copy link
Member

Looks good to me, feel free to merge when ready.

@emstoudenmire emstoudenmire merged commit d36f198 into main Sep 8, 2022
@emstoudenmire emstoudenmire deleted the ranged_truncate_mps branch September 8, 2022 19:52
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@mtfishman mtfishman mtfishman left review comments

@github-actions github-actions[bot] github-actions[bot] left review comments

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@emstoudenmire @mtfishman @codecov-commenter