New H3C Technologies Co., Ltd. H3C UniServer R3750 G7 698446 SPECjbb2015-MultiJVM max-jOPS
389235 SPECjbb2015-MultiJVM critical-jOPS
Tested by: New H3C Technologies Co., Ltd. Test Sponsor: New H3C Technologies Co., Ltd. Test location: Hangzhou, China Test date: Apr 10, 2026
SPEC license #: 9066 Hardware Availability: Apr-2026 Software Availability: Mar-2026 Publication: Thu Apr 30 11:35:11 EDT 2026
Benchmark Results Summary
 
Overall Throughput RT curve
Overall SUT (System Under Test) Description
VendorNew H3C Technologies Co., Ltd.
Vendor URLhttps://www.h3c.com/
System SourceSingle Supplier
System DesignationServer Rack
Total Systems1
All SUT Systems IdenticalYES
Total Nodes1
All Nodes IdenticalYES
Nodes Per System1
Total Chips1
Total Cores192
Total Threads384
Total Memory Amount (GB)768
Total OS Images1
SW EnvironmentNon-virtual
 
Hardware hw_1
NameH3C UniServer R3750 G7
VendorNew H3C Technologies Co., Ltd.
Vendor URLhttps://www.h3c.com/
AvailableApr-2026
ModelH3C UniServer R3750 G7
Form Factor1U
CPU NameAMD EPYC 9965
CPU Characteristics192 Core, 2.25GHz, 384 MB L3 Cache (Max. Boost Clock up to 3.70 GHz)
Number of Systems1
Nodes Per System1
Chips Per System1
Cores Per System192
Cores Per Chip192
Threads Per System384
Threads Per Core2
Version7.30.21
CPU Frequency (MHz)2250
Primary Cache32 KB(I)+ 48 KB(D) per core
Secondary Cache1 MB (I+D) per core
Tertiary Cache384 MB (I+D) per chip
Other CacheNone
Disk1 x 7.68 TB NVMe SSD
File Systemxfs
Memory Amount (GB)768
# and size of DIMM(s)12 x 64 GB
Memory Details64 GB 2Rx4 PC5-6400B
# and type of Network Interface Cards (NICs)2 x 10 Gbit NICs
Power Supply Quantity and Rating (W)2 x 1300W
Other HardwareNone
Cabinet/Housing/EnclosureNone
Shared DescriptionNone
Shared CommentNone
Notes
  • NA: The test sponsor attests, as of date of publication, that CVE-2017-5754 (Meltdown) is mitigated in the system as tested and documented.
  • Yes: The test sponsor attests, as of date of publication, that CVE-2017-5753 (Spectre variant 1) is mitigated in the system as tested and documented.
  • Yes: The test sponsor attests, as of date of publication, that CVE-2017-5715 (Spectre variant 2) is mitigated in the system as tested and documented.
Other Hardware network_1
NameNone
VendorNone
Vendor URLNone
VersionNone
AvailableNone
BitnessNone
NotesNone
Operating System os_1
NameSUSE Linux Enterprise Server 15 SP6
VendorSUSE
Vendor URLhttps://www.suse.com/
Version6.4.0-150600.21-default
AvailableJun-2024
Bitness64
NotesNone
Java Virtual Machine jvm_1
NameOracle Java SE 26
VendorOracle
Vendor URLhttp://www.oracle.com/
VersionJava HotSpot 64-Bit Server VM, version 26
AvailableMar-2026
Bitness64
Notesnote
Other Software other_1
NameNone
VendorNone
Vendor URLNone
VersionNone
AvailableNone
BitnessNone
NotesNone
Hardware
OS Images os_Image_1(1)
Hardware Description hw_1
Number of Systems 1
SW Environment non-virtual
Tuning BIOS tuning
  • NUMA nodes per socket = NPS4
  • ACPI SRAT L3 Cache as NUMA Domain = Enabled
  • L1 Stream HW Prefetcher = Disabled
  • L2 Stream HW Prefetcher = Disabled
  • TDP Control = Manual
  • TDP = 500
  • PPT Control = Manual
  • PPT = 500
  • Determinism Control = Manual
  • Determinism Enable = Power
Notes None
OS Image os_Image_1
JVM Instances jvm_Ctr_1(1), jvm_Backend_1(12), jvm_TxInjector_1(12)
OS Image Description os_1
Tuning
  • ulimit -n 1024000
  • cpupower frequency-set -g performance
  • tuned-adm profile throughput-performance
  • echo 999000000 > /proc/sys/kernel/sched_min_granularity_ns
  • echo 999000000 > /proc/sys/kernel/sched_wakeup_granularity_ns
  • echo 9000 > /proc/sys/kernel/sched_nr_migrate
  • echo 40 > /proc/sys/vm/dirty_ratio
  • echo 10 > /proc/sys/vm/dirty_background_ratio
  • echo 10 > /proc/sys/vm/swappiness
  • echo 0 > /proc/sys/kernel/numa_balancing
  • echo 0 > /proc/sys/vm/numa_stat
  • echo always > /sys/kernel/mm/transparent_hugepage/defrag
  • echo always > /sys/kernel/mm/transparent_hugepage/enabled
Notes None
JVM Instance jvm_Ctr_1
Parts of Benchmark Controller
JVM Instance Description jvm_1
Command Line -Xms5g -Xmx5g -Xmn4g -XX:+UseParallelGC -XX:ParallelGCThreads=1 -XX:CICompilerCount=2
Tuning None
Notes None
JVM Instance jvm_Backend_1
Parts of Benchmark Backend
JVM Instance Description jvm_1
Command Line -Xms31g -Xmx31g -Xmn28g -XX:AllocatePrefetchInstr=2 -XX:+UseParallelGC -XX:ParallelGCThreads=32 -XX:LargePageSizeInBytes=1G -XX:-UseAdaptiveSizePolicy -XX:+AlwaysPreTouch -XX:+UseLargePages -XX:SurvivorRatio=12 -XX:TargetSurvivorRatio=95 -XX:MaxTenuringThreshold=15 -XX:InlineSmallCode=11k -XX:MaxGCPauseMillis=100 -XX:LoopUnrollLimit=200 -XX:+UseTransparentHugePages -XX:TLABAllocationWeight=2 -XX:ThreadStackSize=140 -XX:CompileThresholdScaling=120 -XX:CICompilerCount=4 -XX:AutoBoxCacheMax=32 -XX:OnStackReplacePercentage=100 -XX:TLABSize=64k -XX:MinTLABSize=64k -XX:-ResizeTLAB -XX:TLABWasteTargetPercent=1 -XX:TLABWasteIncrement=1 -XX:YoungPLABSize=64k -XX:OldPLABSize=64k
Tuning numactl used to affinitize one Backend JVM to each NUMA node, eg:
  • Group1:numactl --cpunodebind=0 --localalloc
  • Group2:numactl --cpunodebind=1 --localalloc
  • Group3:numactl --cpunodebind=2 --localalloc
  • Group4:numactl --cpunodebind=3 --localalloc
  • Group5:numactl --cpunodebind=4 --localalloc
  • Group6:numactl --cpunodebind=5 --localalloc
  • Group7:numactl --cpunodebind=6 --localalloc
  • Group8:numactl --cpunodebind=7 --localalloc
  • Group9:numactl --cpunodebind=8 --localalloc
  • Group10:numactl --cpunodebind=9 --localalloc
  • Group11:numactl --cpunodebind=10 --localalloc
  • Group12:numactl --cpunodebind=11 --localalloc
Notes None
JVM Instance jvm_TxInjector_1
Parts of Benchmark TxInjector
JVM Instance Description jvm_1
Command Line -Xms5g -Xmx5g -Xmn4g -XX:+UseParallelGC -XX:ParallelGCThreads=1 -XX:CICompilerCount=2
Tuning numactl used to affinitize one Backend JVM to each NUMA node, eg:
  • Group1:numactl --cpunodebind=0 --localalloc
  • Group2:numactl --cpunodebind=1 --localalloc
  • Group3:numactl --cpunodebind=2 --localalloc
  • Group4:numactl --cpunodebind=3 --localalloc
  • Group5:numactl --cpunodebind=4 --localalloc
  • Group6:numactl --cpunodebind=5 --localalloc
  • Group7:numactl --cpunodebind=6 --localalloc
  • Group8:numactl --cpunodebind=7 --localalloc
  • Group9:numactl --cpunodebind=8 --localalloc
  • Group10:numactl --cpunodebind=9 --localalloc
  • Group11:numactl --cpunodebind=10 --localalloc
  • Group12:numactl --cpunodebind=11 --localalloc
Notes None
max-jOPS = jOPS passed before the First Failure
Pass/Fail Pass Pass Pass Fail Fail
jOPS 681410 689928 698446 706963 715481
critical-jOPS = Geomean ( jOPS @ 10000; 25000; 50000; 75000; 100000; SLAs )
Response time percentile is 99-th
SLA (us) 10000 25000 50000 75000 100000 Geomean
jOPS 268305 310041 427301 479826 523834 389235
  Percentile
  10-th 50-th 90-th 95-th 99-th 100-th
500us 17035 / 25553 8518 / 17035 - / 8518 - / 8518 - / 8518 - / 8518
1000us 528093 / 536611 34071 / 42588 25553 / 34071 25553 / 34071 17035 / 25553 - / 8518
5000us 630305 / 638822 596234 / 604752 374776 / 357740 281082 / 289599 178870 / 187388 17035 / 8518
10000us 638822 / 647340 604752 / 613269 511058 / 519575 451434 / 459952 264047 / 272564 17035 / 8518
25000us 638822 / 647340 621787 / 630305 562164 / 570681 511058 / 519575 323670 / 289599 17035 / 8518
50000us 647340 / 655857 621787 / 630305 570681 / 579199 528093 / 536611 434399 / 391811 17035 / 8518
75000us 655857 / 664375 630305 / 638822 579199 / 587716 562164 / 570681 485505 / 468470 187388 / 25553
100000us 655857 / 664375 630305 / 638822 596234 / 604752 579199 / 587716 519575 / 528093 255529 / 25553
200000us 672893 / 681410 647340 / 655857 621787 / 630305 613269 / 621787 579199 / 587716 442917 / 281082
500000us 698446 / - 672893 / 681410 655857 / 664375 647340 / 655857 630305 / 638822 553646 / 281082
1000000us 698446 / - 698446 / - 681410 / 689928 672893 / 681410 672893 / 681410 621787 / 528093
Probes jOPS / Total jOPS
Request Mix Accuracy
Note
(Actual % in the Mix - Expected % in the Mix) must be within:
'Main Tx' limit of +/-5.0% for the requests whose expected % in the mix is >= 10.0%
'Minor Tx' limit of +/-1.0% for the requests whose expected % in the mix is < 10.0%
There were no non-critical failures in Response Time curve building
Delay between status pings
IR/PR Accuracy
This section lists properties only set by user
Property Name Default Controller Group1.Backend.beJVM Group1.TxInjector.txiJVM1 Group10.Backend.beJVM Group10.TxInjector.txiJVM1 Group11.Backend.beJVM Group11.TxInjector.txiJVM1 Group12.Backend.beJVM Group12.TxInjector.txiJVM1 Group2.Backend.beJVM Group2.TxInjector.txiJVM1 Group3.Backend.beJVM Group3.TxInjector.txiJVM1 Group4.Backend.beJVM Group4.TxInjector.txiJVM1 Group5.Backend.beJVM Group5.TxInjector.txiJVM1 Group6.Backend.beJVM Group6.TxInjector.txiJVM1 Group7.Backend.beJVM Group7.TxInjector.txiJVM1 Group8.Backend.beJVM Group8.TxInjector.txiJVM1 Group9.Backend.beJVM Group9.TxInjector.txiJVM1
specjbb.comm.connect.client.pool.size 256 150 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320
specjbb.comm.connect.selector.runner.count 0 8 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5
specjbb.comm.connect.timeouts.connect 60000 900000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000
specjbb.comm.connect.timeouts.read 60000 800000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000
specjbb.comm.connect.timeouts.write 60000 800000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000 60000
specjbb.comm.connect.worker.pool.max 256 150 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320 320
specjbb.comm.connect.worker.pool.min 1 16 32 1 32 1 32 1 32 1 32 1 32 1 32 1 32 1 32 1 32 1 32 1 32 1
specjbb.controller.maxir.maxFailedPoints 3 1
specjbb.customerDriver.threads 64 {probe=80, saturate=170, service=90}
specjbb.forkjoin.workers 384 {Tier1=555, Tier2=12, Tier3=76}
specjbb.group.count 1 12
specjbb.mapreducer.pool.size 384 8
specjbb.txi.pergroup.count 1 1
View table in csv format
 
Level: COMPLIANCE
Check Agent Result
Check properties on compliance All PASSED
 
Level: CORRECTNESS
Check Agent Result
Compare SM and HQ Inventory All PASSED
High-bound (max attempted) is 851763 IR
High-bound (settled) is 736626 IR