deeprec win

AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG CROSSHAIR X670E HERO (1101 BIOS) and AMD Radeon RX 7900 XTX 24GB on Ubuntu 22.04 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 2304235-PTS-DEEPRECW27
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

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
a
April 21 2023
  16 Hours, 17 Minutes
b
April 22 2023
  21 Hours, 24 Minutes
c
April 22 2023
  18 Hours
Invert Hiding All Results Option
  18 Hours, 34 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

a

Kernel Notes: Transparent Huge Pages: madvise
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203
Python Notes: Python 3.10.9
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

b

c

Processor: AMD Ryzen 9 7950X 16-Core @ 4.50GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (1101 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 2048GB SOLIDIGM SSDPFKKW020X7 + 2000GB, Graphics: AMD Radeon RX 7900 XTX 24GB (2304/1249MHz), Audio: AMD Device ab30, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 22.04, Kernel: 6.3.0-060300rc7daily20230417-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 23.2.0-devel (git-f6fb189 2023-04-18 jammy-oibaf-ppa) (LLVM 15.0.7 DRM 3.52), Vulkan: 1.3.246, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 3840x2160

deeprec winOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 7950X 16-Core @ 4.50GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR X670E HERO (1101 BIOS)AMD Device 14d832GB2048GB SOLIDIGM SSDPFKKW020X7 + 2000GBAMD Radeon RX 7900 XTX 24GB (2304/1249MHz)AMD Device ab30ASUS MG28UIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 22.046.3.0-060300rc7daily20230417-generic (x86_64)GNOME Shell 42.5X Server 1.21.1.3 + Wayland4.6 Mesa 23.2.0-devel (git-f6fb189 2023-04-18 jammy-oibaf-ppa) (LLVM 15.0.7 DRM 3.52)1.3.246GCC 11.3.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionDeeprec Win BenchmarksSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203- Python 3.10.9- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcResult OverviewPhoronix Test Suite100%100%101%101%102%DeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecDeepRecPLE - FP32MMOE - FP32BST - BF16DIN - BF16DIN - FP32DLRM - BF16DLRM - FP32DCNv2 - BF16PLE - BF16BST - FP32DCNv2 - FP32MMOE - BF16BST - BF16BST - FP32DIN - BF16DIN - FP32PLE - BF16PLE - FP32DLRM - BF16DLRM - FP32MMOE - BF16MMOE - FP32DCNv2 - BF16DCNv2 - FP32

deeprec windeeprec: BST - BF16deeprec: BST - BF16deeprec: BST - FP32deeprec: BST - FP32deeprec: DIN - BF16deeprec: DIN - BF16deeprec: DIN - FP32deeprec: DIN - FP32deeprec: PLE - BF16deeprec: PLE - BF16deeprec: PLE - FP32deeprec: PLE - FP32deeprec: DLRM - BF16deeprec: DLRM - BF16deeprec: DLRM - FP32deeprec: DLRM - FP32deeprec: MMOE - BF16deeprec: MMOE - BF16deeprec: MMOE - FP32deeprec: MMOE - FP32deeprec: DCNv2 - BF16deeprec: DCNv2 - BF16deeprec: DCNv2 - FP32deeprec: DCNv2 - FP32abc5442.7610.6310459.3720.4339620.0377.3945933.9489.7119539.8038.1634192.9366.7840034.2878.19153853.71300.5024768.4148.3898473.37192.3310981.0421.4515386.7330.055390.1110.5310469.7320.4539371.4976.9046189.1390.2119521.6438.1333588.2065.6039866.2077.86154485.76301.7324744.9948.3399439.16194.2211010.9021.5115394.5630.075397.2910.5410450.0220.4139664.6277.4746184.2490.2019562.8138.2133755.3365.9339957.4578.04153879.88300.5524737.7848.3299015.53193.3910997.1021.4815407.1530.09OpenBenchmarking.org

DeepRec

DeepRec is a recommendation AI engine based on TensorFlow. This test profile is currently configured just for CPU-based execution. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: BST - Data Type: BF16abc12002400360048006000SE +/- 75.87, N = 3SE +/- 5.26, N = 3SE +/- 4.97, N = 35442.765390.115397.29
OpenBenchmarking.orgGstep / sec, More Is BetterDeepRecModel: BST - Data Type: BF16abc3691215SE +/- 0.15, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 310.6310.5310.54
OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: BST - Data Type: BF16abc9001800270036004500Min: 5365.64 / Avg: 5442.76 / Max: 5594.49Min: 5380.24 / Avg: 5390.11 / Max: 5398.17Min: 5389 / Avg: 5397.29 / Max: 5406.17

OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: BST - Data Type: FP32abc2K4K6K8K10KSE +/- 10.62, N = 3SE +/- 15.53, N = 3SE +/- 7.31, N = 310459.3710469.7310450.02
OpenBenchmarking.orgGstep / sec, More Is BetterDeepRecModel: BST - Data Type: FP32abc510152025SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 320.4320.4520.41
OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: BST - Data Type: FP32abc2K4K6K8K10KMin: 10438.39 / Avg: 10459.37 / Max: 10472.78Min: 10451.78 / Avg: 10469.73 / Max: 10500.65Min: 10441.36 / Avg: 10450.02 / Max: 10464.55

OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: DIN - Data Type: BF16abc8K16K24K32K40KSE +/- 59.19, N = 3SE +/- 283.43, N = 3SE +/- 94.02, N = 339620.0339371.4939664.62
OpenBenchmarking.orgGstep / sec, More Is BetterDeepRecModel: DIN - Data Type: BF16abc20406080100SE +/- 0.12, N = 3SE +/- 0.55, N = 3SE +/- 0.18, N = 377.3976.9077.47
OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: DIN - Data Type: BF16abc7K14K21K28K35KMin: 39518.72 / Avg: 39620.03 / Max: 39723.72Min: 38809.19 / Avg: 39371.49 / Max: 39714.82Min: 39537.2 / Avg: 39664.62 / Max: 39848.09

OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: DIN - Data Type: FP32abc10K20K30K40K50KSE +/- 235.44, N = 3SE +/- 226.20, N = 3SE +/- 158.55, N = 345933.9446189.1346184.24
OpenBenchmarking.orgGstep / sec, More Is BetterDeepRecModel: DIN - Data Type: FP32abc20406080100SE +/- 0.46, N = 3SE +/- 0.44, N = 3SE +/- 0.31, N = 389.7190.2190.20
OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: DIN - Data Type: FP32abc8K16K24K32K40KMin: 45631.13 / Avg: 45933.94 / Max: 46397.64Min: 45787.75 / Avg: 46189.13 / Max: 46570.55Min: 45949.8 / Avg: 46184.24 / Max: 46486.37

OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: PLE - Data Type: BF16abc4K8K12K16K20KSE +/- 5.68, N = 3SE +/- 86.66, N = 3SE +/- 75.93, N = 319539.8019521.6419562.81
OpenBenchmarking.orgGstep / sec, More Is BetterDeepRecModel: PLE - Data Type: BF16abc918273645SE +/- 0.01, N = 3SE +/- 0.17, N = 3SE +/- 0.15, N = 338.1638.1338.21
OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: PLE - Data Type: BF16abc3K6K9K12K15KMin: 19530.2 / Avg: 19539.8 / Max: 19549.85Min: 19356.07 / Avg: 19521.64 / Max: 19648.82Min: 19455.33 / Avg: 19562.81 / Max: 19709.47

OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: PLE - Data Type: FP32abc7K14K21K28K35KSE +/- 81.30, N = 3SE +/- 302.32, N = 9SE +/- 358.30, N = 534192.9333588.2033755.33
OpenBenchmarking.orgGstep / sec, More Is BetterDeepRecModel: PLE - Data Type: FP32abc1530456075SE +/- 0.16, N = 3SE +/- 0.59, N = 9SE +/- 0.70, N = 566.7865.6065.93
OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: PLE - Data Type: FP32abc6K12K18K24K30KMin: 34052.53 / Avg: 34192.93 / Max: 34334.15Min: 32347.6 / Avg: 33588.2 / Max: 34408.17Min: 32334.63 / Avg: 33755.33 / Max: 34203.76

OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: DLRM - Data Type: BF16abc9K18K27K36K45KSE +/- 101.42, N = 3SE +/- 46.34, N = 3SE +/- 88.98, N = 340034.2839866.2039957.45
OpenBenchmarking.orgGstep / sec, More Is BetterDeepRecModel: DLRM - Data Type: BF16abc20406080100SE +/- 0.20, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 378.1977.8678.04
OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: DLRM - Data Type: BF16abc7K14K21K28K35KMin: 39838.6 / Avg: 40034.28 / Max: 40178.38Min: 39773.91 / Avg: 39866.2 / Max: 39919.76Min: 39840.1 / Avg: 39957.45 / Max: 40131.98

OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: DLRM - Data Type: FP32abc30K60K90K120K150KSE +/- 554.46, N = 3SE +/- 611.96, N = 3SE +/- 661.29, N = 3153853.71154485.76153879.88
OpenBenchmarking.orgGstep / sec, More Is BetterDeepRecModel: DLRM - Data Type: FP32abc70140210280350SE +/- 1.08, N = 3SE +/- 1.20, N = 3SE +/- 1.29, N = 3300.50301.73300.55
OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: DLRM - Data Type: FP32abc30K60K90K120K150KMin: 152857.19 / Avg: 153853.71 / Max: 154773.25Min: 153852.77 / Avg: 154485.76 / Max: 155709.44Min: 152856.27 / Avg: 153879.88 / Max: 155117

OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: MMOE - Data Type: BF16abc5K10K15K20K25KSE +/- 8.20, N = 3SE +/- 17.25, N = 3SE +/- 16.28, N = 324768.4124744.9924737.78
OpenBenchmarking.orgGstep / sec, More Is BetterDeepRecModel: MMOE - Data Type: BF16abc1122334455SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 348.3848.3348.32
OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: MMOE - Data Type: BF16abc4K8K12K16K20KMin: 24755.55 / Avg: 24768.41 / Max: 24783.66Min: 24713.88 / Avg: 24744.99 / Max: 24773.48Min: 24707.61 / Avg: 24737.78 / Max: 24763.45

OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: MMOE - Data Type: FP32abc20K40K60K80K100KSE +/- 607.13, N = 3SE +/- 189.62, N = 3SE +/- 204.46, N = 398473.3799439.1699015.53
OpenBenchmarking.orgGstep / sec, More Is BetterDeepRecModel: MMOE - Data Type: FP32abc4080120160200SE +/- 1.19, N = 3SE +/- 0.37, N = 3SE +/- 0.40, N = 3192.33194.22193.39
OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: MMOE - Data Type: FP32abc20K40K60K80K100KMin: 97799.99 / Avg: 98473.37 / Max: 99685.12Min: 99079.48 / Avg: 99439.16 / Max: 99723.11Min: 98608.59 / Avg: 99015.53 / Max: 99253.81

OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: DCNv2 - Data Type: BF16abc2K4K6K8K10KSE +/- 29.29, N = 3SE +/- 11.07, N = 3SE +/- 14.84, N = 310981.0411010.9010997.10
OpenBenchmarking.orgGstep / sec, More Is BetterDeepRecModel: DCNv2 - Data Type: BF16abc510152025SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 321.4521.5121.48
OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: DCNv2 - Data Type: BF16abc2K4K6K8K10KMin: 10922.56 / Avg: 10981.04 / Max: 11013.27Min: 10991.05 / Avg: 11010.9 / Max: 11029.31Min: 10973.19 / Avg: 10997.1 / Max: 11024.28

OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: DCNv2 - Data Type: FP32abc3K6K9K12K15KSE +/- 19.76, N = 3SE +/- 11.07, N = 3SE +/- 13.19, N = 315386.7315394.5615407.15
OpenBenchmarking.orgGstep / sec, More Is BetterDeepRecModel: DCNv2 - Data Type: FP32abc714212835SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 330.0530.0730.09
OpenBenchmarking.orgThroughput, More Is BetterDeepRecModel: DCNv2 - Data Type: FP32abc3K6K9K12K15KMin: 15364.47 / Avg: 15386.73 / Max: 15426.14Min: 15376.65 / Avg: 15394.56 / Max: 15414.78Min: 15387.66 / Avg: 15407.15 / Max: 15432.3

a

Kernel Notes: Transparent Huge Pages: madvise
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203
Python Notes: Python 3.10.9
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 21 April 2023 19:39 by user pts.

b

Kernel Notes: Transparent Huge Pages: madvise
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203
Python Notes: Python 3.10.9
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 22 April 2023 05:21 by user pts.

c

Processor: AMD Ryzen 9 7950X 16-Core @ 4.50GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (1101 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 2048GB SOLIDIGM SSDPFKKW020X7 + 2000GB, Graphics: AMD Radeon RX 7900 XTX 24GB (2304/1249MHz), Audio: AMD Device ab30, Monitor: ASUS MG28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 22.04, Kernel: 6.3.0-060300rc7daily20230417-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 23.2.0-devel (git-f6fb189 2023-04-18 jammy-oibaf-ppa) (LLVM 15.0.7 DRM 3.52), Vulkan: 1.3.246, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203
Python Notes: Python 3.10.9
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 22 April 2023 17:03 by user pts.