Benchmark for Gigabyte R152-P30

From Leo's Notes
Last edited on 2 August 2023, at 20:57.

This is the new ARM server that Computer Science purchased to replace the old APM X-C1 (Mustang). Interestingly, the benchmark results for the APM X-Gene X-C1 has similar results for single core performance.


Results Overview[edit source]

Hardware Gigabyte R152-P30
CPU ARM Neoverse-N1
Memory 32 GB
Disk SSD
Operating System Fedora 38 (aarch64)
Score 996.8 / 28970.7

Raw Output

========================================================================
   BYTE UNIX Benchmarks (Version 5.1.3)

   System: csa1.uc.ucalgary.ca: GNU/Linux
   OS: GNU/Linux -- 6.3.8-200.fc38.aarch64 -- #1 SMP PREEMPT_DYNAMIC Thu Jun 15 02:15:18 UTC 2023
   Machine: aarch64 (unknown)
   Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
          
   13:45:06  up 31 days  9:42,  1 user,  load average: 0.03, 0.02, 0.00; runlevel Jul

------------------------------------------------------------------------
Benchmark Run: Wed Aug 02 2023 13:45:06 - 14:13:10
64 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       24956208.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     4356.1 MWIPS (10.0 s, 7 samples)
Execl Throughput                               2679.8 lps   (29.8 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        598792.0 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          162251.4 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1757085.7 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1057651.7 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 101132.2 lps   (10.0 s, 7 samples)
Process Creation                               3508.8 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   3806.0 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   4086.6 lpm   (60.0 s, 2 samples)
System Call Overhead                         832270.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   24956208.4   2138.5
Double-Precision Whetstone                       55.0       4356.1    792.0
Execl Throughput                                 43.0       2679.8    623.2
File Copy 1024 bufsize 2000 maxblocks          3960.0     598792.0   1512.1
File Copy 256 bufsize 500 maxblocks            1655.0     162251.4    980.4
File Copy 4096 bufsize 8000 maxblocks          5800.0    1757085.7   3029.5
Pipe Throughput                               12440.0    1057651.7    850.2
Pipe-based Context Switching                   4000.0     101132.2    252.8
Process Creation                                126.0       3508.8    278.5
Shell Scripts (1 concurrent)                     42.4       3806.0    897.6
Shell Scripts (8 concurrent)                      6.0       4086.6   6810.9
System Call Overhead                          15000.0     832270.2    554.8
                                                                   ========
System Benchmarks Index Score                                         996.8

------------------------------------------------------------------------
Benchmark Run: Wed Aug 02 2023 14:13:10 - 14:41:21
64 CPUs in system; running 64 parallel copies of tests

Dhrystone 2 using register variables     1592986913.3 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                   278738.0 MWIPS (10.0 s, 7 samples)
Execl Throughput                              45438.1 lps   (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks      15103931.0 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks        10376720.8 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks      13000980.5 KBps  (30.0 s, 2 samples)
Pipe Throughput                            67676063.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                5938105.4 lps   (10.0 s, 7 samples)
Process Creation                             104840.5 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  87407.6 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                  10888.6 lpm   (60.1 s, 2 samples)
System Call Overhead                       53223051.5 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0 1592986913.3 136502.7
Double-Precision Whetstone                       55.0     278738.0  50679.6
Execl Throughput                                 43.0      45438.1  10567.0
File Copy 1024 bufsize 2000 maxblocks          3960.0   15103931.0  38141.2
File Copy 256 bufsize 500 maxblocks            1655.0   10376720.8  62699.2
File Copy 4096 bufsize 8000 maxblocks          5800.0   13000980.5  22415.5
Pipe Throughput                               12440.0   67676063.4  54402.0
Pipe-based Context Switching                   4000.0    5938105.4  14845.3
Process Creation                                126.0     104840.5   8320.7
Shell Scripts (1 concurrent)                     42.4      87407.6  20615.0
Shell Scripts (8 concurrent)                      6.0      10888.6  18147.6
System Call Overhead                          15000.0   53223051.5  35482.0
                                                                   ========
System Benchmarks Index Score                                       28970.7