deunan

AMD Ryzen 9 5900X 12-Core testing with a Gigabyte X570 AORUS MASTER (F34 BIOS) and AMD Radeon Pro W5500 8GB on Red Hat Enterprise Linux 8.4 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2110099-GREM-DEUNAN356
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

NVIDIA GPU Compute 4 Tests
Vulkan Compute 4 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
deunan 20210527 1737
May 27
  43 Minutes
deunan 20210527 1749
May 27
  42 Minutes
deunan 20210527 1802
May 27
 
deunan 20210527 1814
May 27
 
deunan 20210527 1819
May 27
  1 Hour, 47 Minutes
deunan 20210527 2011
May 27
  1 Hour, 7 Minutes
deunan 20211009 1100
October 09
  1 Minute
deunan 20211009 1106
October 09
  10 Minutes
deunan 20211009 1215
October 09
  2 Hours, 33 Minutes
Invert Hiding All Results Option
  47 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):


deunanProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionOpenGLdeunan 20210527 1737deunan 20210527 1749deunan 20210527 1802deunan 20210527 1814deunan 20210527 1819deunan 20210527 2011deunan 20211009 1100deunan 20211009 1106deunan 20211009 1215AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads)Gigabyte X570 AORUS MASTER (F33j BIOS)AMD Starship/Matisse2 x 16 GB DDR4-3600MT/s Kingston KHX3600C17D41000GB Samsung SSD 980 PRO 1TB + 500GB Seagate ST500LM000-1EJ16AMD Radeon Pro W5500 8GB (1900/875MHz)AMD Navi 10 HDMI AudioPHL 345B1C + SyncMasterIntel I211 + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200Red Hat Enterprise Linux 8.45.4.121-1.el8.elrepo.x86_64 (x86_64)GNOME Shell 3.32.2X Server1.2.145GCC 8.4.1 20200928ext43440x14404.6.147565120x14403440x1440Gigabyte X570 AORUS MASTER (F34 BIOS)5.14.10-1.el8.elrepo.x86_64 (x86_64)OpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysProcessor Details- deunan 20210527 1737: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009- deunan 20210527 1749: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009- deunan 20210527 1802: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009- deunan 20210527 1814: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009- deunan 20210527 1819: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009- deunan 20210527 2011: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009- deunan 20211009 1100: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016- deunan 20211009 1106: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016- deunan 20211009 1215: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected Compiler Details- deunan 20210527 1802, deunan 20211009 1106, deunan 20211009 1215: --build=x86_64-redhat-linux --disable-libmpx --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver Python Details- deunan 20210527 1802, deunan 20211009 1100: Python 3.6.8

deunanintel-mlc: Idle Latencyintel-mlc: Max Bandwidth - All Readsintel-mlc: Max Bandwidth - 3:1 Reads-Writesintel-mlc: Max Bandwidth - 2:1 Reads-Writesintel-mlc: Max Bandwidth - 1:1 Reads-Writesintel-mlc: Max Bandwidth - Stream-Triad Likeintel-mlc: Peak Injection Bandwidth - All Readsintel-mlc: Peak Injection Bandwidth - 3:1 Reads-Writesintel-mlc: Peak Injection Bandwidth - 2:1 Reads-Writesintel-mlc: Peak Injection Bandwidth - 1:1 Reads-Writesintel-mlc: Peak Injection Bandwidth - Stream-Triad Likeunigine-heaven: 800 x 600 - Fullscreen - OpenGLunigine-heaven: 1024 x 768 - Fullscreen - OpenGLunigine-heaven: 1280 x 1024 - Fullscreen - OpenGLunigine-heaven: 1600 x 1200 - Fullscreen - OpenGLunigine-heaven: 1920 x 1080 - Fullscreen - OpenGLunigine-heaven: 1920 x 1200 - Fullscreen - OpenGLunigine-heaven: 2560 x 1440 - Fullscreen - OpenGLunigine-heaven: 3440 x 1440 - Fullscreen - OpenGLunigine-heaven: 800 x 600 - Windowed - OpenGLunigine-heaven: 1024 x 768 - Windowed - OpenGLunigine-heaven: 1280 x 1024 - Windowed - OpenGLunigine-heaven: 1600 x 1200 - Windowed - OpenGLunigine-heaven: 1920 x 1080 - Windowed - OpenGLsystemd-boot-total: Totalperf-bench: Epoll Waitperf-bench: Futex Hashperf-bench: Memcpy 1MBperf-bench: Memset 1MBperf-bench: Sched Pipeperf-bench: Futex Lock-Piperf-bench: Syscall Basicvkpeak: fp32-scalarvkpeak: fp32-vec4vkpeak: fp16-scalarvkpeak: fp16-vec4vkpeak: fp64-scalarvkpeak: fp64-vec4vkpeak: int32-scalarvkpeak: int32-vec4vkpeak: int16-scalarvkpeak: int16-vec4realsr-ncnn: 4x - Norealsr-ncnn: 4x - Yeswaifu2x-ncnn: 2x - 3 - Yesvkresample: 2x - Singledeunan 20210527 1737deunan 20210527 1749deunan 20210527 1802deunan 20210527 1814deunan 20210527 1819deunan 20210527 2011deunan 20211009 1100deunan 20211009 1106deunan 20211009 121575.752240.3644182.3142454.9543311.6046614.7051672.144077.242444.942823.646371.072.551934.5744143.9042485.2042999.2946368.1051745.543948.742385.342694.046399.650.629650.682251.009851.073051.138450.699750.722850.7109211.065177.904136.960106.785104.8111480664456475728524.80701626.217933546383705179626145209.885194.004916.058735.66328.26327.921047.251047.824916.614751.7816.951122.2676.93528.522OpenBenchmarking.org

Intel Memory Latency Checker

Intel Memory Latency Checker (MLC) is a binary-only system memory bandwidth and latency benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns, Fewer Is BetterIntel Memory Latency CheckerTest: Idle Latencydeunan 20210527 1737deunan 20210527 174920406080100SE +/- 0.88, N = 4SE +/- 0.03, N = 375.772.5
OpenBenchmarking.orgns, Fewer Is BetterIntel Memory Latency CheckerTest: Idle Latencydeunan 20210527 1737deunan 20210527 17491530456075Min: 74.5 / Avg: 75.68 / Max: 78.3Min: 72.4 / Avg: 72.47 / Max: 72.5

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - All Readsdeunan 20210527 1737deunan 20210527 174911K22K33K44K55KSE +/- 240.54, N = 3SE +/- 422.11, N = 352240.3651934.57
OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - All Readsdeunan 20210527 1737deunan 20210527 17499K18K27K36K45KMin: 51763.27 / Avg: 52240.36 / Max: 52532.45Min: 51090.53 / Avg: 51934.57 / Max: 52372.03

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - 3:1 Reads-Writesdeunan 20210527 1737deunan 20210527 17499K18K27K36K45KSE +/- 35.81, N = 3SE +/- 161.41, N = 344182.3144143.90
OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - 3:1 Reads-Writesdeunan 20210527 1737deunan 20210527 17498K16K24K32K40KMin: 44118.24 / Avg: 44182.31 / Max: 44242.05Min: 43946.94 / Avg: 44143.9 / Max: 44463.88

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - 2:1 Reads-Writesdeunan 20210527 1737deunan 20210527 17499K18K27K36K45KSE +/- 165.22, N = 3SE +/- 76.52, N = 342454.9542485.20
OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - 2:1 Reads-Writesdeunan 20210527 1737deunan 20210527 17497K14K21K28K35KMin: 42124.65 / Avg: 42454.95 / Max: 42628.55Min: 42338.96 / Avg: 42485.2 / Max: 42597.36

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - 1:1 Reads-Writesdeunan 20210527 1737deunan 20210527 17499K18K27K36K45KSE +/- 17.65, N = 3SE +/- 138.59, N = 343311.6042999.29
OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - 1:1 Reads-Writesdeunan 20210527 1737deunan 20210527 17498K16K24K32K40KMin: 43281.76 / Avg: 43311.6 / Max: 43342.86Min: 42781.84 / Avg: 42999.29 / Max: 43256.87

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - Stream-Triad Likedeunan 20210527 1737deunan 20210527 174910K20K30K40K50KSE +/- 20.63, N = 3SE +/- 12.45, N = 346614.7046368.10
OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - Stream-Triad Likedeunan 20210527 1737deunan 20210527 17498K16K24K32K40KMin: 46590.45 / Avg: 46614.7 / Max: 46655.74Min: 46344.45 / Avg: 46368.1 / Max: 46386.66

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - All Readsdeunan 20210527 1737deunan 20210527 174911K22K33K44K55KSE +/- 199.66, N = 3SE +/- 76.39, N = 351672.151745.5
OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - All Readsdeunan 20210527 1737deunan 20210527 17499K18K27K36K45KMin: 51272.8 / Avg: 51672.1 / Max: 51874.9Min: 51592.7 / Avg: 51745.47 / Max: 51823.6

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - 3:1 Reads-Writesdeunan 20210527 1737deunan 20210527 17499K18K27K36K45KSE +/- 51.19, N = 3SE +/- 27.92, N = 344077.243948.7
OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - 3:1 Reads-Writesdeunan 20210527 1737deunan 20210527 17498K16K24K32K40KMin: 43974.8 / Avg: 44077.17 / Max: 44129.2Min: 43893.8 / Avg: 43948.67 / Max: 43985.1

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - 2:1 Reads-Writesdeunan 20210527 1737deunan 20210527 17499K18K27K36K45KSE +/- 22.91, N = 3SE +/- 19.89, N = 342444.942385.3
OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - 2:1 Reads-Writesdeunan 20210527 1737deunan 20210527 17497K14K21K28K35KMin: 42399.6 / Avg: 42444.87 / Max: 42473.6Min: 42358.7 / Avg: 42385.27 / Max: 42424.2

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - 1:1 Reads-Writesdeunan 20210527 1737deunan 20210527 17499K18K27K36K45KSE +/- 148.24, N = 3SE +/- 44.98, N = 342823.642694.0
OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - 1:1 Reads-Writesdeunan 20210527 1737deunan 20210527 17497K14K21K28K35KMin: 42547.3 / Avg: 42823.57 / Max: 43054.9Min: 42616.3 / Avg: 42693.97 / Max: 42772.1

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - Stream-Triad Likedeunan 20210527 1737deunan 20210527 174910K20K30K40K50KSE +/- 108.70, N = 3SE +/- 57.91, N = 346371.046399.6
OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - Stream-Triad Likedeunan 20210527 1737deunan 20210527 17498K16K24K32K40KMin: 46165.7 / Avg: 46371 / Max: 46535.6Min: 46313.6 / Avg: 46399.63 / Max: 46509.8

Unigine Heaven

This test calculates the average frame-rate within the Heaven demo for the Unigine engine. This engine is extremely demanding on the system's graphics card. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 800 x 600 - Mode: Fullscreen - Renderer: OpenGLdeunan 20210527 18191122334455SE +/- 0.07, N = 350.63

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 1024 x 768 - Mode: Fullscreen - Renderer: OpenGLdeunan 20210527 18191122334455SE +/- 0.01, N = 350.68

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 1280 x 1024 - Mode: Fullscreen - Renderer: OpenGLdeunan 20210527 18191224364860SE +/- 0.16, N = 351.01

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 1600 x 1200 - Mode: Fullscreen - Renderer: OpenGLdeunan 20210527 18191224364860SE +/- 0.39, N = 351.07

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGLdeunan 20210527 18191224364860SE +/- 0.35, N = 351.14

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 1920 x 1200 - Mode: Fullscreen - Renderer: OpenGLdeunan 20210527 18191122334455SE +/- 0.02, N = 350.70

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 2560 x 1440 - Mode: Fullscreen - Renderer: OpenGLdeunan 20210527 18191122334455SE +/- 0.00, N = 350.72

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 3440 x 1440 - Mode: Fullscreen - Renderer: OpenGLdeunan 20210527 18191122334455SE +/- 0.00, N = 350.71

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 800 x 600 - Mode: Windowed - Renderer: OpenGLdeunan 20210527 201150100150200250SE +/- 0.83, N = 3211.07

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 1024 x 768 - Mode: Windowed - Renderer: OpenGLdeunan 20210527 20114080120160200SE +/- 0.22, N = 3177.90

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 1280 x 1024 - Mode: Windowed - Renderer: OpenGLdeunan 20210527 2011306090120150SE +/- 0.18, N = 3136.96

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 1600 x 1200 - Mode: Windowed - Renderer: OpenGLdeunan 20210527 201120406080100SE +/- 0.65, N = 3106.79

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 1920 x 1080 - Mode: Windowed - Renderer: OpenGLdeunan 20210527 201120406080100SE +/- 0.03, N = 3104.81

Systemd Total Boot Time

This test uses systemd-analyze to report the entire boot time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: Totaldeunan 20211009 11003K6K9K12K15K14806

perf-bench

This test profile is used for running Linux perf-bench, the benchmark support within the Linux kernel's perf tool. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Epoll Waitdeunan 20211009 110614K28K42K56K70KSE +/- 169.45, N = 3644561. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lperl -lresolv -lcrypt -lutil -lc -lz -llzma -lnuma

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex Hashdeunan 20211009 11061000K2000K3000K4000K5000KSE +/- 8327.50, N = 347572851. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lperl -lresolv -lcrypt -lutil -lc -lz -llzma -lnuma

OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memcpy 1MBdeunan 20211009 1106612182430SE +/- 1.47, N = 1524.811. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lperl -lresolv -lcrypt -lutil -lc -lz -llzma -lnuma

OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memset 1MBdeunan 20211009 1106612182430SE +/- 0.01, N = 326.221. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lperl -lresolv -lcrypt -lutil -lc -lz -llzma -lnuma

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Sched Pipedeunan 20211009 1106120K240K360K480K600KSE +/- 5173.93, N = 35463831. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lperl -lresolv -lcrypt -lutil -lc -lz -llzma -lnuma

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex Lock-Pideunan 20211009 1106150300450600750SE +/- 0.88, N = 37051. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lperl -lresolv -lcrypt -lutil -lc -lz -llzma -lnuma

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Syscall Basicdeunan 20211009 11064M8M12M16M20MSE +/- 196932.28, N = 4179626141. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lperl -lresolv -lcrypt -lutil -lc -lz -llzma -lnuma

vkpeak

Vkpeak is a Vulkan compute benchmark inspired by OpenCL's clpeak. Vkpeak provides Vulkan compute performance measurements for FP16 / FP32 / FP64 / INT16 / INT32 scalar and vec4 performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-scalardeunan 20211009 121511002200330044005500SE +/- 0.40, N = 35209.88

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-vec4deunan 20211009 121511002200330044005500SE +/- 0.24, N = 35194.00

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-scalardeunan 20211009 121511002200330044005500SE +/- 0.15, N = 34916.05

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-vec4deunan 20211009 12152K4K6K8K10KSE +/- 1.30, N = 38735.66

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-scalardeunan 20211009 121570140210280350SE +/- 0.02, N = 3328.26

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-vec4deunan 20211009 121570140210280350SE +/- 0.03, N = 3327.92

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-scalardeunan 20211009 12152004006008001000SE +/- 0.05, N = 31047.25

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-vec4deunan 20211009 12152004006008001000SE +/- 0.08, N = 31047.82

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-scalardeunan 20211009 121511002200330044005500SE +/- 0.49, N = 34916.61

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-vec4deunan 20211009 121510002000300040005000SE +/- 0.25, N = 34751.78

RealSR-NCNN

RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: Nodeunan 20211009 121548121620SE +/- 0.04, N = 316.95

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: Yesdeunan 20211009 1215306090120150SE +/- 0.05, N = 3122.27

Waifu2x-NCNN Vulkan

Waifu2x-NCNN is an NCNN neural network implementation of the Waifu2x converter project and accelerated using the Vulkan API. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: Yesdeunan 20211009 1215246810SE +/- 0.008, N = 36.935

VkResample

VkResample is a Vulkan-based image upscaling library based on VkFFT. The sample input file is upscaling a 4K image to 8K using Vulkan-based GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Singledeunan 20211009 1215714212835SE +/- 0.10, N = 328.521. (CXX) g++ options: -O2 -pthread