sdfa

AMD Ryzen Threadripper 3990X 64-Core testing with a Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS) and AMD Radeon RX 5700 8GB on Ubuntu 23.10 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 2312122-PTS-SDFA911983
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
December 11 2023
  22 Hours, 44 Minutes
b
December 12 2023
  7 Hours, 14 Minutes
c
December 12 2023
  21 Hours, 52 Minutes
d
December 12 2023
  21 Hours, 47 Minutes
Invert Hiding All Results Option
  18 Hours, 24 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):

sdfa AMD Ryzen Threadripper 3990X 64-Core testing with a Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS) and AMD Radeon RX 5700 8GB on Ubuntu 23.10 via the Phoronix Test Suite. a: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 23.10, Kernel: 6.5.0-13-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 23.10, Kernel: 6.5.0-13-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 c: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 23.10, Kernel: 6.5.0-13-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 d: Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 23.10, Kernel: 6.5.0-13-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 Apache Spark TPC-H 3.5 Scale Factor: 1 - Geometric Mean Of All Queries Seconds < Lower Is Better a . 2.20328734 |============================================================== b . 2.24531415 |=============================================================== c . 2.23705911 |=============================================================== d . 2.22356446 |============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q01 Seconds < Lower Is Better a . 4.69511843 |============================================================= b . 4.73092079 |============================================================== c . 4.84034109 |=============================================================== d . 4.84622987 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q02 Seconds < Lower Is Better a . 2.19916511 |============================================================= b . 2.20726132 |============================================================= c . 2.27846766 |=============================================================== d . 2.27512868 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q03 Seconds < Lower Is Better a . 3.15890259 |=========================================================== b . 3.23912430 |============================================================= c . 3.34556897 |=============================================================== d . 3.15447322 |=========================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q04 Seconds < Lower Is Better a . 2.96026391 |============================================================ b . 3.09257221 |=============================================================== c . 2.94428595 |============================================================ d . 2.85856040 |========================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q05 Seconds < Lower Is Better a . 3.46156806 |============================================================== b . 3.37768650 |============================================================ c . 3.52418653 |=============================================================== d . 3.30995369 |=========================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q06 Seconds < Lower Is Better a . 0.75870752 |=============================================================== b . 0.73223764 |============================================================= c . 0.71082556 |=========================================================== d . 0.74262398 |============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q07 Seconds < Lower Is Better a . 3.16296500 |============================================================ b . 3.30348134 |=============================================================== c . 3.18430217 |============================================================= d . 3.25330043 |============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q08 Seconds < Lower Is Better a . 2.29091269 |============================================================= b . 2.32780766 |============================================================== c . 2.35779921 |=============================================================== d . 2.22529737 |=========================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q09 Seconds < Lower Is Better a . 4.40090740 |============================================================= b . 4.51510048 |============================================================== c . 4.32967218 |============================================================ d . 4.55872504 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q10 Seconds < Lower Is Better a . 2.83789939 |========================================================= b . 3.07959628 |============================================================== c . 3.02914357 |============================================================= d . 3.14210590 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q11 Seconds < Lower Is Better a . 1.30849856 |============================================================ b . 1.36447799 |=============================================================== c . 1.28974267 |============================================================ d . 1.29190469 |============================================================ Apache Spark TPC-H 3.5 Scale Factor: 1 - Q12 Seconds < Lower Is Better a . 2.14987269 |=============================================================== b . 2.02941990 |=========================================================== c . 2.04039538 |============================================================ d . 2.06954416 |============================================================= Apache Spark TPC-H 3.5 Scale Factor: 1 - Q13 Seconds < Lower Is Better a . 1.40058664 |============================================================ b . 1.45866323 |=============================================================== c . 1.39991681 |============================================================ d . 1.39225551 |============================================================ Apache Spark TPC-H 3.5 Scale Factor: 1 - Q14 Seconds < Lower Is Better a . 1.83231536 |=============================================================== b . 1.78157055 |============================================================= c . 1.83836599 |=============================================================== d . 1.83219139 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q15 Seconds < Lower Is Better a . 1.99491587 |======================================================= b . 2.17460775 |============================================================ c . 2.14363774 |=========================================================== d . 2.27715731 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q16 Seconds < Lower Is Better a . 1.42731291 |========================================================== b . 1.43939853 |=========================================================== c . 1.49448760 |============================================================= d . 1.53928820 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q17 Seconds < Lower Is Better a . 2.66192222 |============================================================== b . 2.72264194 |=============================================================== c . 2.58527072 |============================================================ d . 2.57773050 |============================================================ Apache Spark TPC-H 3.5 Scale Factor: 1 - Q18 Seconds < Lower Is Better a . 4.00372249 |============================================================== b . 4.04589510 |=============================================================== c . 3.99324067 |============================================================== d . 3.86921136 |============================================================ Apache Spark TPC-H 3.5 Scale Factor: 1 - Q19 Seconds < Lower Is Better a . 1.02847038 |====================================================== b . 1.17394590 |============================================================= c . 1.20837911 |=============================================================== d . 0.99435820 |==================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q20 Seconds < Lower Is Better a . 2.75555176 |=============================================================== b . 2.58762598 |=========================================================== c . 2.75284823 |=============================================================== d . 2.74797662 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 1 - Q21 Seconds < Lower Is Better a . 7.39505470 |============================================================ b . 7.70369244 |=============================================================== c . 7.46197589 |============================================================= d . 7.40773551 |============================================================= Apache Spark TPC-H 3.5 Scale Factor: 1 - Q22 Seconds < Lower Is Better a . 1.08502284 |=============================================================== b . 0.98886323 |========================================================= c . 1.05880324 |============================================================= d . 1.06113847 |============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Geometric Mean Of All Queries Seconds < Lower Is Better a . 8.17090667 |============================================================== b . 7.89399455 |============================================================ c . 8.11142575 |============================================================== d . 8.24567273 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q01 Seconds < Lower Is Better a . 8.67833742 |=============================================================== b . 8.70151806 |=============================================================== c . 8.66681448 |=============================================================== d . 8.73231697 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q02 Seconds < Lower Is Better a . 4.85099522 |============================================================== b . 4.88495016 |============================================================== c . 4.92897081 |=============================================================== d . 4.79437430 |============================================================= Apache Spark TPC-H 3.5 Scale Factor: 10 - Q03 Seconds < Lower Is Better a . 10.24 |=================================================================== b . 10.32 |==================================================================== c . 10.26 |==================================================================== d . 10.15 |=================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q04 Seconds < Lower Is Better a . 8.63682970 |============================================================== b . 8.70809078 |=============================================================== c . 8.50457668 |============================================================== d . 8.33958340 |============================================================ Apache Spark TPC-H 3.5 Scale Factor: 10 - Q05 Seconds < Lower Is Better a . 12.48 |================================================================== b . 12.92 |==================================================================== c . 12.66 |=================================================================== d . 12.66 |=================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q06 Seconds < Lower Is Better a . 4.40131362 |============================================================ b . 4.62162924 |=============================================================== c . 4.30036068 |=========================================================== d . 4.36710962 |============================================================ Apache Spark TPC-H 3.5 Scale Factor: 10 - Q07 Seconds < Lower Is Better a . 10.63 |=================================================================== b . 10.53 |=================================================================== c . 10.62 |=================================================================== d . 10.75 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q08 Seconds < Lower Is Better a . 10.99 |==================================================================== b . 10.67 |================================================================== c . 10.85 |=================================================================== d . 10.82 |=================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q09 Seconds < Lower Is Better a . 14.90 |==================================================================== b . 14.18 |================================================================= c . 14.82 |==================================================================== d . 14.92 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q10 Seconds < Lower Is Better a . 10.27 |=================================================================== b . 10.18 |================================================================== c . 10.42 |==================================================================== d . 10.36 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q11 Seconds < Lower Is Better a . 4.54931625 |=============================================================== b . 4.26761341 |=========================================================== c . 4.38963429 |============================================================= d . 4.48057460 |============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q12 Seconds < Lower Is Better a . 8.03465001 |============================================================== b . 8.10859299 |=============================================================== c . 8.17116038 |=============================================================== d . 8.09419775 |============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q13 Seconds < Lower Is Better a . 4.45708307 |============================================================= b . 4.03698015 |======================================================= c . 4.09777006 |======================================================== d . 4.61340586 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q14 Seconds < Lower Is Better a . 5.79615275 |============================================================== b . 5.82840872 |=============================================================== c . 5.86177413 |=============================================================== d . 5.73522472 |============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q15 Seconds < Lower Is Better a . 5.83709431 |=============================================================== b . 5.68089533 |============================================================= c . 5.81021436 |=============================================================== d . 5.85565599 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q16 Seconds < Lower Is Better a . 4.32050626 |=============================================================== b . 4.15591764 |============================================================ c . 4.17572975 |============================================================= d . 4.34601260 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q17 Seconds < Lower Is Better a . 12.45 |==================================================================== b . 12.44 |==================================================================== c . 12.42 |==================================================================== d . 12.40 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q18 Seconds < Lower Is Better a . 14.86 |=============================================================== b . 14.88 |=============================================================== c . 16.11 |==================================================================== d . 14.91 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q19 Seconds < Lower Is Better a . 7.21627538 |========================================================= b . 6.04250240 |=============================================== c . 6.54328155 |=================================================== d . 8.02795347 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q20 Seconds < Lower Is Better a . 8.84160964 |=============================================================== b . 8.87663841 |=============================================================== c . 8.91217136 |=============================================================== d . 8.82452583 |============================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q21 Seconds < Lower Is Better a . 29.31 |==================================================================== b . 28.80 |=================================================================== c . 29.03 |=================================================================== d . 28.91 |=================================================================== Apache Spark TPC-H 3.5 Scale Factor: 10 - Q22 Seconds < Lower Is Better a . 3.53586213 |============================================================ b . 3.40110779 |========================================================== c . 3.69966158 |=============================================================== d . 3.59682607 |============================================================= Apache Spark TPC-H 3.5 Scale Factor: 50 - Geometric Mean Of All Queries Seconds < Lower Is Better a . 27.98 |==================================================================== b . 27.79 |=================================================================== c . 28.11 |==================================================================== d . 28.12 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q01 Seconds < Lower Is Better a . 26.02 |==================================================================== b . 25.99 |==================================================================== c . 26.00 |==================================================================== d . 26.12 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q02 Seconds < Lower Is Better a . 10.48 |=================================================================== b . 10.45 |=================================================================== c . 10.56 |==================================================================== d . 10.44 |=================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q03 Seconds < Lower Is Better a . 36.61 |=================================================================== b . 36.03 |================================================================== c . 37.06 |==================================================================== d . 35.99 |================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q04 Seconds < Lower Is Better a . 30.58 |==================================================================== b . 30.27 |=================================================================== c . 30.22 |=================================================================== d . 30.56 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q05 Seconds < Lower Is Better a . 41.17 |================================================================= b . 43.25 |==================================================================== c . 39.70 |============================================================== d . 38.99 |============================================================= Apache Spark TPC-H 3.5 Scale Factor: 50 - Q06 Seconds < Lower Is Better a . 20.38 |==================================================================== b . 20.30 |==================================================================== c . 20.34 |==================================================================== d . 20.38 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q07 Seconds < Lower Is Better a . 35.63 |==================================================================== b . 35.34 |=================================================================== c . 35.46 |==================================================================== d . 35.40 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q08 Seconds < Lower Is Better a . 38.36 |==================================================================== b . 37.97 |=================================================================== c . 37.81 |=================================================================== d . 38.38 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q09 Seconds < Lower Is Better a . 46.90 |==================================================================== b . 46.32 |=================================================================== c . 47.11 |==================================================================== d . 47.00 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q10 Seconds < Lower Is Better a . 35.93 |================================================================== b . 36.27 |=================================================================== c . 36.82 |==================================================================== d . 35.93 |================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q11 Seconds < Lower Is Better a . 9.06239065 |=============================================================== b . 8.69320774 |============================================================ c . 8.75260639 |============================================================= d . 9.01768939 |=============================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q12 Seconds < Lower Is Better a . 30.43 |=================================================================== b . 30.41 |=================================================================== c . 30.89 |==================================================================== d . 30.04 |================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q13 Seconds < Lower Is Better a . 12.34 |============================================================= b . 12.13 |============================================================ c . 13.14 |================================================================= d . 13.68 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q14 Seconds < Lower Is Better a . 25.49 |==================================================================== b . 25.40 |==================================================================== c . 25.46 |==================================================================== d . 25.42 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q15 Seconds < Lower Is Better a . 23.05 |==================================================================== b . 22.89 |==================================================================== c . 22.95 |==================================================================== d . 23.00 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q16 Seconds < Lower Is Better a . 10.59 |================================================================== b . 10.53 |================================================================== c . 10.82 |=================================================================== d . 10.91 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q17 Seconds < Lower Is Better a . 55.61 |==================================================================== b . 55.28 |==================================================================== c . 55.33 |==================================================================== d . 55.42 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q18 Seconds < Lower Is Better a . 62.51 |==================================================================== b . 61.96 |=================================================================== c . 62.30 |==================================================================== d . 62.73 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q19 Seconds < Lower Is Better a . 24.72 |=================================================================== b . 25.08 |==================================================================== c . 24.89 |=================================================================== d . 25.03 |==================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q20 Seconds < Lower Is Better a . 30.71 |==================================================================== b . 30.54 |=================================================================== c . 30.79 |==================================================================== d . 30.52 |=================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q21 Seconds < Lower Is Better a . 130.87 |=================================================================== b . 131.46 |=================================================================== c . 131.42 |=================================================================== d . 131.01 |=================================================================== Apache Spark TPC-H 3.5 Scale Factor: 50 - Q22 Seconds < Lower Is Better a . 10.67 |==================================================================== b . 10.53 |=================================================================== c . 10.64 |==================================================================== d . 10.27 |================================================================= Apache Spark TPC-H 3.5 Scale Factor: 100 Seconds < Lower Is Better Neural Magic DeepSparse 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 37.93 |================================================================= b . 39.38 |==================================================================== c . 37.78 |================================================================= d . 38.72 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 836.92 |=================================================================== b . 806.39 |================================================================ c . 841.34 |=================================================================== d . 820.12 |================================================================= Neural Magic DeepSparse 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 13.90 |================================================================== b . 14.40 |==================================================================== c . 13.88 |================================================================== d . 13.90 |================================================================== Neural Magic DeepSparse 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 71.94 |==================================================================== b . 69.42 |================================================================== c . 72.03 |==================================================================== d . 71.92 |==================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 980.45 |================================================================== b . 993.60 |=================================================================== c . 988.49 |=================================================================== d . 989.06 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 32.60 |==================================================================== b . 32.16 |=================================================================== c . 32.34 |=================================================================== d . 32.31 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 129.70 |================================================================= b . 131.17 |================================================================= c . 132.10 |================================================================== d . 134.40 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 7.7066 |=================================================================== b . 7.6192 |================================================================== c . 7.5689 |================================================================== d . 7.4402 |================================================================= Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 441.44 |================================================================== b . 450.81 |=================================================================== c . 445.16 |================================================================== d . 441.39 |================================================================== Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 72.42 |==================================================================== b . 70.94 |=================================================================== c . 71.81 |=================================================================== d . 72.46 |==================================================================== Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 103.56 |================================================================= b . 106.93 |=================================================================== c . 106.03 |================================================================== d . 103.98 |================================================================= Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 9.6462 |=================================================================== b . 9.3424 |================================================================= c . 9.4215 |================================================================= d . 9.6084 |=================================================================== Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 2555.42 |================================================================ b . 2635.57 |================================================================== c . 2548.38 |================================================================ d . 2543.11 |================================================================ Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 12.49 |==================================================================== b . 12.11 |================================================================== c . 12.52 |==================================================================== d . 12.55 |==================================================================== Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 627.75 |=================================================================== b . 599.19 |================================================================ c . 591.26 |=============================================================== d . 620.24 |================================================================== Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 1.5897 |=============================================================== b . 1.6656 |================================================================== c . 1.6887 |=================================================================== d . 1.6090 |================================================================ Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 201.91 |================================================================= b . 206.96 |=================================================================== c . 199.22 |================================================================ d . 201.94 |================================================================= Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 158.15 |================================================================== b . 154.30 |================================================================= c . 160.28 |=================================================================== d . 158.11 |================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 86.38 |=================================================================== b . 88.17 |==================================================================== c . 87.93 |==================================================================== d . 87.47 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 11.56 |==================================================================== b . 11.33 |=================================================================== c . 11.36 |=================================================================== d . 11.42 |=================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 49.22 |==================================================================== b . 49.33 |==================================================================== c . 49.08 |==================================================================== d . 49.17 |==================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 649.93 |=================================================================== b . 648.52 |=================================================================== c . 649.76 |=================================================================== d . 650.69 |=================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 11.31 |================================================================= b . 11.61 |=================================================================== c . 11.84 |==================================================================== d . 11.74 |=================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 88.47 |==================================================================== b . 86.15 |================================================================== c . 84.46 |================================================================= d . 85.16 |================================================================= Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 449.31 |=================================================================== b . 448.76 |=================================================================== c . 452.04 |=================================================================== d . 450.06 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 71.17 |==================================================================== b . 71.27 |==================================================================== c . 70.74 |=================================================================== d . 71.05 |==================================================================== Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 106.44 |=================================================================== b . 106.54 |=================================================================== c . 107.10 |=================================================================== d . 104.29 |================================================================= Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 9.3853 |================================================================== b . 9.3770 |================================================================== c . 9.3277 |================================================================= d . 9.5802 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 215.83 |=================================================================== b . 212.76 |================================================================== c . 216.39 |=================================================================== d . 215.29 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 147.96 |================================================================== b . 150.23 |=================================================================== c . 147.49 |================================================================== d . 148.28 |================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 91.14 |==================================================================== b . 89.80 |=================================================================== c . 91.16 |==================================================================== d . 89.59 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 10.96 |=================================================================== b . 11.13 |==================================================================== c . 10.96 |=================================================================== d . 11.15 |==================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 336.19 |=================================================================== b . 337.08 |=================================================================== c . 337.78 |=================================================================== d . 335.10 |================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 95.02 |==================================================================== b . 94.88 |==================================================================== c . 94.68 |=================================================================== d . 95.45 |==================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 56.79 |================================================================= b . 59.01 |==================================================================== c . 57.18 |================================================================== d . 56.86 |================================================================== Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 17.60 |==================================================================== b . 16.94 |================================================================= c . 17.48 |==================================================================== d . 17.58 |==================================================================== Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 43.19 |=================================================================== b . 43.84 |==================================================================== c . 43.05 |=================================================================== d . 43.06 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 736.77 |=================================================================== b . 726.25 |================================================================== c . 737.98 |=================================================================== d . 737.85 |=================================================================== Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 17.07 |================================================================= b . 17.99 |==================================================================== c . 16.99 |================================================================ d . 17.09 |================================================================= Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 58.55 |==================================================================== b . 55.56 |================================================================ c . 58.85 |==================================================================== d . 58.50 |==================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 503.41 |================================================================== b . 508.59 |=================================================================== c . 506.13 |=================================================================== d . 504.84 |=================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 63.48 |==================================================================== b . 62.81 |=================================================================== c . 63.13 |==================================================================== d . 63.30 |==================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 64.71 |==================================================================== b . 64.40 |==================================================================== c . 64.12 |=================================================================== d . 64.08 |=================================================================== Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 15.45 |=================================================================== b . 15.52 |==================================================================== c . 15.59 |==================================================================== d . 15.60 |==================================================================== Neural Magic DeepSparse 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 37.74 |==================================================================== b . 37.95 |==================================================================== c . 37.94 |==================================================================== d . 37.45 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 841.43 |=================================================================== b . 837.46 |================================================================== c . 837.14 |================================================================== d . 845.44 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 14.08 |=================================================================== b . 14.31 |==================================================================== c . 14.10 |=================================================================== d . 14.00 |=================================================================== Neural Magic DeepSparse 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 71.04 |==================================================================== b . 69.88 |=================================================================== c . 70.90 |==================================================================== d . 71.42 |====================================================================