SPEC CPU®2026 Floating Point Rate Result

Copyright 2026 Standard Performance Evaluation Corporation

Dell Inc.

PowerEdge R7725 (AMD EPYC 9965 192-Core Processor)

SPECrate®2026_fp_base = 99300

SPECrate®2026_fp_peak = 99300

CPU2026 License: 6573 Test Date: Feb-2026
Test Sponsor: Dell Inc. Hardware Availability: Mar-2025
Tested by: Dell Inc. Software Availability: Jan-2026
Benchmark results graph
Hardware
CPU Name: AMD EPYC 9965
  Max MHz: 3700
  Nominal: 2250
Enabled: 384 cores, 2 chips, 2 threads/core
Orderable: 1,2 chips
Cache L1: 32 KB I + 48 KB D on chip per core
  L2: 1 MB I+D on chip per core
  L3: 384 MB I+D on chip per chip, 32 MB shared / 16
cores
  Other: None
Memory: 1536 GB (24 x 64 GB 2Rx4 PC5-6400B-R)
Storage: 350 GB on tmpfs
Cooling: Air
Other: None
Software
OS: Ubuntu 24.04.2 LTS
6.8.0-55-generic
Compiler: C/C++/Fortran: Version 5.1.0 of AOCC
Compiler Category: Vendor
Firmware: Version 1.5.3 released Oct-2025
File System: tmpfs
System State: Run level 3 (multi-user)
Base Pointers: 64-bit
Peak Pointers: 64-bit
Other: None
Power Management: BIOS and OS set to prefer performance at the cost
of additional power usage.

Results Table

Benchmark Base Peak
Copies Seconds Ratio Seconds Ratio Seconds Ratio Copies Seconds Ratio Seconds Ratio Seconds Ratio
709.cactus_r 384 147 2230 148 2230 384 147 2230 148 2230
722.palm_r 384 698 726 697 727 384 698 726 697 727
731.astcenc_r 384 169 1910 170 1900 384 169 1910 170 1900
736.ocio_r 384 290 1160 289 1160 384 290 1160 289 1160
737.gmsh_r 384 196 899 195 903 384 196 899 195 903
748.flightdm_r 384 147 1870 147 1880 384 147 1870 147 1880
749.fotonik3d_r 384 1720 258 1720 258 384 1720 258 1720 258
765.roms_r 384 1755 345 1758 344 384 1755 345 1758 344
766.femflow_r 384 239 2360 240 2350 384 239 2360 240 2350
767.nest_r 384 259 1180 259 1180 384 259 1180 259 1180
772.marian_r 384 337 1800 337 1800 384 337 1800 337 1800
782.lbm_r 384 632 348 633 347 384 632 348 633 347
SPECrate®2026_fp_base 99300
SPECrate®2026_fp_peak 99300
Results appear in the order in which they were run. Bold underlined text indicates a median measurement.

Compiler Notes

The AMD64 AOCC Compiler Suite is available at
http://developer.amd.com/amd-aocc/

Submit Notes

The config file option 'submit' was used.
'numactl' was used to bind copies to the cores.
See the configuration file for details.

Operating System Notes

'ulimit -s unlimited' was used to set environment stack size limit
'ulimit -l 2097152' was used to set environment locked pages in memory limit

runcpu command invoked through numactl i.e.:
numactl --interleave=all runcpu <etc>

To limit dirty cache to 8% of memory, 'sysctl -w vm.dirty_ratio=8' run as root.
To limit swap usage to minimum necessary, 'sysctl -w vm.swappiness=1' run as root.
To free node-local memory and avoid remote memory usage,
'sysctl -w vm.zone_reclaim_mode=1' run as root.
To clear filesystem caches, 'sync; sysctl -w vm.drop_caches=3' run as root.
To disable address space layout randomization (ASLR) to reduce run-to-run
variability, 'sysctl -w kernel.randomize_va_space=0' run as root.
To enable Transparent Hugepages (THP) for all allocations,
'echo always > /sys/kernel/mm/transparent_hugepage/enabled' and
'echo always > /sys/kernel/mm/transparent_hugepage/defrag' run as root.

Environment Variables Notes

Environment variables set by runcpu before the start of the run:
LD_LIBRARY_PATH =
     "/mnt/ramdisk/cpu2026rc2/amd_rate_aocc510_znver5_A_lib/lib:/mnt/ramdisk/
     cpu2026rc2/amd_rate_aocc510_znver5_A_lib/lib32:"
MALLOC_CONF = "retain:true"

General Notes

Binaries were compiled on a system with 2x AMD EPYC Venice256 CPU + 2TiB Memory using Ubuntu 24.04
 Benchmark run from a 350 GB ramdisk created with the cmd: "mount -t tmpfs -o size=350G tmpfs /mnt/ramdisk"

Platform Notes


 BIOS Settings:
            Virtualization Technology : Disabled
                NUMA Nodes Per Socket : 4

                       System Profile : Custom
                 CPU Power Management : Maximum Performance
                             C-States : Disabled
                  Memory Patrol Scrub : Disabled
    PCI ASPM L1 Link Power Management : Disabled
      Periodic Directory Rinse Tuning : Blended
                  Determinism Control : Manual
                   Determinism Slider : Power Determinism
                       Optimizer Mode : Enabled
  Algorithm Performance Boost Disable : Enabled
              ApbDis Fixed DF P-State : P0
                  Adaptive Allocation : Enabled
                   Dram Refresh Delay : Performance

 Sysinfo program /mnt/ramdisk/cpu2026rc2/bin/sysinfo
 Rev: 069f95da7e7f5d81b2ce48a82150e54f
 running on SLR7753-R7725 Thu Feb  5 19:14:16 2026

 SUT (System Under Test) info as seen by some common utilities.

 ------------------------------------------------------------
 Table of contents
 ------------------------------------------------------------
  1. uname -srvm
  2. w
  3. Username
  4. ulimit -a
  5. sysinfo process ancestry
  6. /proc/cpuinfo
  7. lscpu
  8. numactl --hardware
  9. /proc/meminfo
 10. who -r
 11. Systemd service manager version: systemd 255 (255.4-1ubuntu8.6)
 12. Services, from systemctl list-unit-files
 13. Linux kernel boot-time arguments, from /proc/cmdline
 14. cpupower frequency-info
 15. tuned-adm active
 16. sysctl
 17. /sys/kernel/mm/transparent_hugepage
 18. /sys/kernel/mm/transparent_hugepage/khugepaged
 19. OS release
 20. Disk information
 21. /sys/devices/virtual/dmi/id
 22. dmidecode
 23. BIOS
 ------------------------------------------------------------

 ------------------------------------------------------------
 1. uname -srvm
   Linux 6.8.0-55-generic #57-Ubuntu SMP PREEMPT_DYNAMIC Wed Feb 12 23:42:21 UTC 2025 x86_64

 ------------------------------------------------------------
 2. w
    19:14:16 up  3:16,  1 user,  load average: 181.91, 558.05, 668.92
   USER     TTY      FROM             LOGIN@   IDLE   JCPU   PCPU  WHAT
   root     tty1     -                15:58    3:07m  3.10s  1.65s /bin/bash ./amd_rate_aocc510_znver5_A1.sh

 ------------------------------------------------------------
 3. Username
   From environment variable $USER:  root

 ------------------------------------------------------------
 4. ulimit -a
   time(seconds)        unlimited
   file(blocks)         unlimited
   data(kbytes)         unlimited
   stack(kbytes)        unlimited
   coredump(blocks)     0
   memory(kbytes)       unlimited
   locked memory(kbytes) 2097152
   process              6187509
   nofiles              1024
   vmemory(kbytes)      unlimited
   locks                unlimited
   rtprio               0

 ------------------------------------------------------------
 5. sysinfo process ancestry
  /sbin/init
  /bin/login -p --
  -bash
  /bin/bash /home/DellFiles/bin/DELL_rate.sh
  /bin/bash /home/DellFiles/bin/dell-run-main.sh rate
  /bin/bash /home/DellFiles/bin/dell-run-main.sh rate
  /bin/bash /home/DellFiles/bin/AMD/dell-run-speccpu.sh rate --define DL-VERS=7.0_T01 --output_format
    html,pdf,txt
  python3 ./run_amd_rate_aocc510_znver5_A1.py
  /bin/bash ./amd_rate_aocc510_znver5_A1.sh
  runcpu --config amd_rate_aocc510_znver5_A1.cfg --tune base --reportable --iterations 2 --define
    DL-VERS=7.0_T01 --output_format html,pdf,txt fprate
  runcpu --configfile amd_rate_aocc510_znver5_A1.cfg --tune base --reportable --iterations 2 --define
    DL-VERS=7.0_T01 --output_format html,pdf,txt --nopower --runmode rate --tune base --size
    test:train:refrate fprate --nopreenv --note-preenv --logfile
    $SPEC/tmp/CPU2026.002/templogs/preenv.fprate.002.0.log --lognum 002.0 --from_runcpu 2
  specperl $SPEC/bin/sysinfo
 $SPEC = /mnt/ramdisk/cpu2026rc2

 ------------------------------------------------------------
 6. /proc/cpuinfo
     model name      : AMD EPYC 9965 192-Core Processor
     vendor_id       : AuthenticAMD
     cpu family      : 26
     model           : 17
     stepping        : 0
     microcode       : 0xb101054
     bugs            : sysret_ss_attrs spectre_v1 spectre_v2 spec_store_bypass
     TLB size        : 192 4K pages
     cpu cores       : 192
     siblings        : 384
     2 physical ids (chips)
     768 processors (hardware threads)
     physical id 0: core ids 0-191
     physical id 1: core ids 0-191
     physical id 0: apicids 0-383
     physical id 1: apicids 512-895
   Caution: /proc/cpuinfo data regarding chips, cores, and threads is not necessarily reliable, especially for
   virtualized systems.  Use the above data carefully.

 ------------------------------------------------------------
 7. lscpu

 From lscpu from util-linux 2.39.3:
   Architecture:                         x86_64
   CPU op-mode(s):                       32-bit, 64-bit
   Address sizes:                        52 bits physical, 57 bits virtual
   Byte Order:                           Little Endian
   CPU(s):                               768
   On-line CPU(s) list:                  0-767
   Vendor ID:                            AuthenticAMD
   BIOS Vendor ID:                       AMD
   Model name:                           AMD EPYC 9965 192-Core Processor
   BIOS Model name:                      AMD EPYC 9965 192-Core Processor                 CPU @ 2.2GHz
   BIOS CPU family:                      107
   CPU family:                           26
   Model:                                17
   Thread(s) per core:                   2
   Core(s) per socket:                   192
   Socket(s):                            2
   Stepping:                             0
   Frequency boost:                      enabled
   CPU(s) scaling MHz:                   61%
   CPU max MHz:                          3700.1951
   CPU min MHz:                          1500.0000
   BogoMIPS:                             4493.33
   Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat
                                         pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb
                                         rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl nonstop_tsc cpuid
                                         extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid
                                         sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm
                                         cmp_legacy extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch
                                         osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext
                                         perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2
                                         ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase tsc_adjust bmi1 avx2
                                         smep bmi2 invpcid cqm rdt_a avx512f avx512dq rdseed adx smap
                                         avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt
                                         xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total
                                         cqm_mbm_local user_shstk avx_vnni avx512_bf16 clzero irperf
                                         xsaveerptr rdpru wbnoinvd amd_ppin cppc arat npt lbrv svm_lock
                                         nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter
                                         pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi
                                         avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq
                                         avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect
                                         movdiri movdir64b overflow_recov succor smca avx512_vp2intersect
                                         flush_l1d debug_swap
   L1d cache:                            18 MiB (384 instances)
   L1i cache:                            12 MiB (384 instances)
   L2 cache:                             384 MiB (384 instances)
   L3 cache:                             768 MiB (24 instances)
   NUMA node(s):                         8
   NUMA node0 CPU(s):                    0-47,384-431
   NUMA node1 CPU(s):                    48-95,432-479
   NUMA node2 CPU(s):                    96-143,480-527
   NUMA node3 CPU(s):                    144-191,528-575
   NUMA node4 CPU(s):                    192-239,576-623
   NUMA node5 CPU(s):                    240-287,624-671
   NUMA node6 CPU(s):                    288-335,672-719
   NUMA node7 CPU(s):                    336-383,720-767
   Vulnerability Gather data sampling:   Not affected
   Vulnerability Itlb multihit:          Not affected
   Vulnerability L1tf:                   Not affected
   Vulnerability Mds:                    Not affected
   Vulnerability Meltdown:               Not affected
   Vulnerability Mmio stale data:        Not affected
   Vulnerability Reg file data sampling: Not affected
   Vulnerability Retbleed:               Not affected
   Vulnerability Spec rstack overflow:   Not affected
   Vulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl
   Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
   Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; STIBP
                                         always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
   Vulnerability Srbds:                  Not affected
   Vulnerability Tsx async abort:        Not affected

 From lscpu --cache:
      NAME ONE-SIZE ALL-SIZE WAYS TYPE        LEVEL  SETS PHY-LINE COHERENCY-SIZE
      L1d       48K      18M   12 Data            1    64        1             64
      L1i       32K      12M    8 Instruction     1    64        1             64
      L2         1M     384M   16 Unified         2  1024        1             64
      L3        32M     768M   16 Unified         3 32768        1             64

 ------------------------------------------------------------
 8. numactl --hardware
 NOTE: a numactl 'node' might or might not correspond to a physical chip.
   available: 8 nodes (0-7)
   node 0 cpus: 0-47,384-431
   node 0 size: 192584 MB
   node 0 free: 187967 MB
   node 1 cpus: 48-95,432-479
   node 1 size: 193497 MB
   node 1 free: 190158 MB
   node 2 cpus: 96-143,480-527
   node 2 size: 193497 MB
   node 2 free: 190087 MB
   node 3 cpus: 144-191,528-575
   node 3 size: 193481 MB
   node 3 free: 179785 MB
   node 4 cpus: 192-239,576-623
   node 4 size: 193497 MB
   node 4 free: 189977 MB
   node 5 cpus: 240-287,624-671
   node 5 size: 193454 MB
   node 5 free: 190041 MB
   node 6 cpus: 288-335,672-719
   node 6 size: 193497 MB
   node 6 free: 190148 MB
   node 7 cpus: 336-383,720-767
   node 7 size: 193441 MB
   node 7 free: 189924 MB
   node distances:
   node   0   1   2   3   4   5   6   7
     0:  10  12  12  12  32  32  32  32
     1:  12  10  12  12  32  32  32  32
     2:  12  12  10  12  32  32  32  32
     3:  12  12  12  10  32  32  32  32
     4:  32  32  32  32  10  12  12  12
     5:  32  32  32  32  12  10  12  12
     6:  32  32  32  32  12  12  10  12
     7:  32  32  32  32  12  12  12  10

 ------------------------------------------------------------
 9. /proc/meminfo
    MemTotal:       1584078168 kB

 ------------------------------------------------------------
 10. who -r
   run-level 3 Feb 5 15:57

 ------------------------------------------------------------
 11. Systemd service manager version: systemd 255 (255.4-1ubuntu8.6)
   Default Target  Status
   multi-user      running

 ------------------------------------------------------------
 12. Services, from systemctl list-unit-files
   STATE            UNIT FILES
   enabled          apparmor apport blk-availability cloud-config cloud-final cloud-init cloud-init-local
                    console-setup e2scrub_reap finalrd getty@ gpu-manager grub-common grub-initrd-fallback
                    keyboard-setup lm-sensors lvm2-monitor multipathd networkd-dispatcher
                    nvmefc-boot-connections nvmf-autoconnect open-iscsi pollinate secureboot-db setvtrgb
                    systemd-networkd systemd-networkd-wait-online systemd-pstore systemd-resolved
                    systemd-timesyncd thermald tuned
   enabled-runtime  netplan-ovs-cleanup systemd-fsck-root systemd-remount-fs
   disabled         console-getty debug-shell fio iscsid serial-getty@ ssh systemd-boot-check-no-failures
                    systemd-confext systemd-network-generator systemd-networkd-wait-online@
                    systemd-pcrlock-file-system systemd-pcrlock-firmware-code systemd-pcrlock-firmware-config
                    systemd-pcrlock-machine-id systemd-pcrlock-make-policy
                    systemd-pcrlock-secureboot-authority systemd-pcrlock-secureboot-policy systemd-sysext
                    systemd-time-wait-sync upower
   indirect         systemd-sysupdate systemd-sysupdate-reboot uuidd
   masked           cryptdisks cryptdisks-early hwclock multipath-tools-boot sudo x11-common

 ------------------------------------------------------------
 13. Linux kernel boot-time arguments, from /proc/cmdline
   BOOT_IMAGE=/boot/vmlinuz-6.8.0-55-generic
   root=UUID=12012b0a-8b6b-4db0-98ad-44c145a96bdb
   ro

 ------------------------------------------------------------
 14. cpupower frequency-info
   analyzing CPU 757:
     current policy: frequency should be within 1.50 GHz and 2.25 GHz.
                     The governor "performance" may decide which speed to use
                     within this range.
     boost state support:
       Supported: yes
       Active: yes
       Boost States: 0
       Total States: 3
       Pstate-P0:  2250MHz

 ------------------------------------------------------------
 15. tuned-adm active
   Current active profile: latency-performance

 ------------------------------------------------------------
 16. sysctl
   kernel.numa_balancing               1
   kernel.randomize_va_space           0
   vm.compaction_proactiveness        20
   vm.dirty_background_bytes           0
   vm.dirty_background_ratio           3
   vm.dirty_bytes                      0
   vm.dirty_expire_centisecs        3000
   vm.dirty_ratio                      8
   vm.dirty_writeback_centisecs      500
   vm.dirtytime_expire_seconds     43200
   vm.extfrag_threshold              500
   vm.min_unmapped_ratio               1
   vm.nr_hugepages                     0
   vm.nr_hugepages_mempolicy           0
   vm.nr_overcommit_hugepages          0
   vm.swappiness                       1
   vm.watermark_boost_factor       15000
   vm.watermark_scale_factor          10
   vm.zone_reclaim_mode                1

 ------------------------------------------------------------
 17. /sys/kernel/mm/transparent_hugepage
   defrag          [always] defer defer+madvise madvise never
   enabled         [always] madvise never
   hpage_pmd_size  2097152
   shmem_enabled   always within_size advise [never] deny force

 ------------------------------------------------------------
 18. /sys/kernel/mm/transparent_hugepage/khugepaged
   alloc_sleep_millisecs   60000
   defrag                      1
   max_ptes_none             511
   max_ptes_shared           256
   max_ptes_swap              64
   pages_to_scan            4096
   scan_sleep_millisecs    10000

 ------------------------------------------------------------
 19. OS release
   From /etc/*-release /etc/*-version
   os-release Ubuntu 24.04.2 LTS

 ------------------------------------------------------------
 20. Disk information
 SPEC is set to: /mnt/ramdisk/cpu2026rc2
   Filesystem     Type   Size  Used Avail Use% Mounted on
   tmpfs          tmpfs  350G   10G  341G   3% /mnt/ramdisk

 ------------------------------------------------------------
 21. /sys/devices/virtual/dmi/id
     Vendor:         Dell Inc.
     Product:        PowerEdge R7725
     Product Family: PowerEdge
     Serial:         SLR7753

 ------------------------------------------------------------
 22. dmidecode
   Additional information from dmidecode 3.5 follows.  WARNING: Use caution when you interpret this section.
   The 'dmidecode' program reads system data which is "intended to allow hardware to be accurately
   determined", but the intent may not be met, as there are frequent changes to hardware, firmware, and the
   "DMTF SMBIOS" standard.
   Memory:
     23x 80AD000080AD HMCG94AHBRA277N 64 GB 2 rank 6400
     1x 80AD000080AD HMCG94AHBRA480N 64 GB 2 rank 6400


 ------------------------------------------------------------
 23. BIOS
 (This section combines info from /sys/devices and dmidecode.)
    BIOS Vendor:       Dell Inc.
    BIOS Version:      1.5.3
    BIOS Date:         10/29/2025
    BIOS Revision:     1.5

Compiler Version Notes

==============================================================================
C       | 782.lbm_r(base)
------------------------------------------------------------------------------
AMD clang version 17.0.6 (CLANG: AOCC_5.1.0-Build#1994 2025_12_23)
Target: x86_64-unknown-linux-gnu
Thread model: posix
InstalledDir: /opt/AMD/aocc/aocc-compiler-5.1.0/bin
------------------------------------------------------------------------------

==============================================================================
C++     | 731.astcenc_r(base) 736.ocio_r(base) 748.flightdm_r(base)
        | 766.femflow_r(base) 767.nest_r(base) 772.marian_r(base)
------------------------------------------------------------------------------
AMD clang version 17.0.6 (CLANG: AOCC_5.1.0-Build#1994 2025_12_23)
Target: x86_64-unknown-linux-gnu
Thread model: posix
InstalledDir: /opt/AMD/aocc/aocc-compiler-5.1.0/bin
------------------------------------------------------------------------------

==============================================================================
C++, C  | 709.cactus_r(base) 737.gmsh_r(base)
------------------------------------------------------------------------------
AMD clang version 17.0.6 (CLANG: AOCC_5.1.0-Build#1994 2025_12_23)
Target: x86_64-unknown-linux-gnu
Thread model: posix
InstalledDir: /opt/AMD/aocc/aocc-compiler-5.1.0/bin
------------------------------------------------------------------------------

==============================================================================
Fortran | 722.palm_r(base) 749.fotonik3d_r(base) 765.roms_r(base)
------------------------------------------------------------------------------
AMD clang version 17.0.6 (CLANG: AOCC_5.1.0-Build#1994 2025_12_23)
Target: x86_64-unknown-linux-gnu
Thread model: posix
InstalledDir: /opt/AMD/aocc/aocc-compiler-5.1.0/bin
------------------------------------------------------------------------------

Base Compiler Invocation

C benchmarks:

 clang 

C++ benchmarks:

 clang++ 

Fortran benchmarks:

 flang 

Benchmarks using both C and C++:

 clang++   clang 

Base Portability Flags

709.cactus_r:  -DSPEC_LP64 
722.palm_r:  -DSPEC_LP64 
731.astcenc_r:  -DSPEC_LP64 
736.ocio_r:  -fno-finite-math-only   -DSPEC_LP64 
737.gmsh_r:  -fno-fast-math   -DSPEC_LP64 
748.flightdm_r:  -fno-reciprocal-math   -DSPEC_LP64 
749.fotonik3d_r:  -DSPEC_LP64 
765.roms_r:  -DSPEC_LP64 
766.femflow_r:  -DSPEC_LP64 
767.nest_r:  -fno-finite-math-only   -DSPEC_LP64 
772.marian_r:  -DSPEC_LP64 
782.lbm_r:  -DSPEC_LP64 

Base Optimization Flags

C benchmarks:

 -m64   -std=c18   -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6   -Wl,-mllvm -Wl,-reduce-array-computations=3   -Wl,-mllvm -Wl,-ldist-scalar-expand   -fenable-aggressive-gather   -ffast-math   -O3   -march=znver5   -fveclib=AMDLIBM   -fno-PIE   -no-pie   -flto   -fstruct-layout=7   -mllvm -unroll-threshold=50   -mllvm -inline-threshold=1000   -fremap-arrays   -fstrip-mining   -mllvm -reduce-array-computations=3   -zopt   -lamdlibm   -lamdalloc   -lflang 

C++ benchmarks:

 -m64   -std=c++17   -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6   -Wl,-mllvm -Wl,-reduce-array-computations=3   -Wl,-mllvm -Wl,-x86-use-vzeroupper=false   -Wl,-mllvm -Wl,-extra-inliner   -ffast-math   -O3   -march=znver5   -fveclib=AMDLIBM   -flto   -mllvm -unroll-threshold=100   -mllvm -loop-unswitch-threshold=200000   -mllvm -reduce-array-computations=3   -zopt   -lamdlibm   -lamdalloc   -lflang 

Fortran benchmarks:

 -m64   -Mstandard   -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6   -Wl,-mllvm -Wl,-reduce-array-computations=3   -Wl,-mllvm -Wl,-enable-X86-prefetching   -Wl,-mllvm -Wl,-enable-aggressive-gather=true   -Wl,-mllvm -Wl,-enable-masked-gather-sequence=false   -ffast-math   -O3   -march=znver5   -fveclib=AMDLIBM   -flto   -Mrecursive   -funroll-loops   -mllvm -lsr-in-nested-loop   -mllvm -reduce-array-computations=3   -fepilog-vectorization-of-inductions   -zopt   -lamdlibm   -lamdalloc   -lflang 

Benchmarks using both C and C++:

 -m64   -std=c++17   -std=c18   -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6   -Wl,-mllvm -Wl,-reduce-array-computations=3   -Wl,-mllvm -Wl,-x86-use-vzeroupper=false   -Wl,-mllvm -Wl,-extra-inliner   -ffast-math   -O3   -march=znver5   -fveclib=AMDLIBM   -fno-PIE   -no-pie   -flto   -fstruct-layout=7   -mllvm -unroll-threshold=50   -mllvm -inline-threshold=1000   -fremap-arrays   -fstrip-mining   -mllvm -reduce-array-computations=3   -zopt   -mllvm -unroll-threshold=100   -mllvm -loop-unswitch-threshold=200000   -lamdlibm   -lamdalloc   -lflang 

Peak Optimization Flags

C benchmarks:

782.lbm_r:  basepeak = yes 

C++ benchmarks:

731.astcenc_r:  basepeak = yes 
736.ocio_r:  basepeak = yes 
748.flightdm_r:  basepeak = yes 
766.femflow_r:  basepeak = yes 
767.nest_r:  basepeak = yes 
772.marian_r:  basepeak = yes 

Fortran benchmarks:

722.palm_r:  basepeak = yes 
749.fotonik3d_r:  basepeak = yes 
765.roms_r:  basepeak = yes 

Benchmarks using both C and C++:

709.cactus_r:  basepeak = yes 
737.gmsh_r:  basepeak = yes 

The flags files that were used to format this result can be browsed at
http://www.spec.org/cpu2026/results/flags/aocc-flags.2026-05-04.html,
http://www.spec.org/cpu2026/results/flags/Dell-Platform-Flags-PowerEdge-AMD-EPYC-v1.8.html.

You can also download the XML flags sources by saving the following links:
http://www.spec.org/cpu2026/results/flags/aocc-flags.2026-05-04.xml,
http://www.spec.org/cpu2026/results/flags/Dell-Platform-Flags-PowerEdge-AMD-EPYC-v1.8.xml.