SPEC CPU®2026 Flag Description
Supermicro Hyper A+ Server AS -1116CS-TN (H14DSH , AMD EPYC 9375F)

Test sponsored by Advanced Micro Devices (AMD)

Compilers: AMD Optimizing C/C++ Compiler Suite

Implicitly Included Flags

This section contains descriptions of flags that were included implicitly by other flags, but which do not have a permanent home at SPEC.

• • -O2
  • 

  • Moderate level of optimization which enables most optimizations. This is the default when no "-O" option is specified, or if no value is specified (i.e. "-O").

    If multiple "O" options are used, with or without level numbers, the last such option is the one that is effective.

  • Includes:
    • -O1
• • -O1
  • 

  • Somewhere between -O0 and -O2.

    If multiple "O" options are used, with or without level numbers, the last such option is the one that is effective.

Commands and Options Used to Submit Benchmark Runs

Using numactl to bind processes and memory to cores

For multi-copy runs or single copy runs on systems with multiple sockets, it is advantageous to bind a process to a particular core. Otherwise, the OS may arbitrarily move your process from one core to another. This can affect performance. To help, SPEC allows the use of a "submit" command where users can specify a utility to use to bind processes. We have found the utility 'numactl' to be the best choice.

numactl runs processes with a specific NUMA scheduling or memory placement policy. The policy is set for a command and inherited by all of its children. The numactl flag "--physcpubind" specifies which core(s) to bind the process. "-l" instructs numactl to keep a process's memory on the local node while "-m" specifies which node(s) to place a process's memory. For full details on using numactl, please refer to your Linux documentation, 'man numactl'

Note that some older versions of numactl incorrectly interpret application arguments as its own. For example, with the command "numactl --physcpubind=0 -l a.out -m a", numactl will interpret a.out's "-m" option as its own "-m" option. To work around this problem, we put the command to be run in a shell script and then run the shell script using numactl. For example: "echo 'a.out -m a' > run.sh ; numactl --physcpubind=0 bash run.sh"

Shell, Environment, and Other Software Settings

numactl --interleave=all runcpu

numactl --interleave=all runcpu executes the SPEC CPU command runcpu so that memory is consumed across NUMA nodes rather than consumed from a single node. This helps prevent local node out-of-memory conditions which can occur when runcpu is executed without interleaving. For full details on using numactl, please refer to your Linux documentation, 'man numactl'

Transparent Huge Pages (THP)

THP is an abstraction layer that automates most aspects of creating, managing, and using huge pages. It is designed to hide much of the complexity in using huge pages from system administrators and developers. Huge pages increase the memory page size from 4 kilobytes to 2 megabytes. This provides significant performance advantages on systems with highly contended resources and large memory workloads. If memory utilization is too high or memory is badly fragmented which prevents huge pages being allocated, the kernel will assign smaller 4k pages instead. Most recent Linux OS releases have THP enabled by default.

THP usage is controlled by the sysfs setting /sys/kernel/mm/transparent_hugepage/enabled. Possible values:

• never: entirely disable THP usage.
• madvise: enable THP usage only inside regions marked MADV_HUGEPAGE using madvise(3).
• always: enable THP usage system-wide. This is the default.

The SPEC CPU benchmark codes themselves never explicitly request huge pages, as the mechanism to do that is OS-specific and can change over time. Libraries such as amdalloc which are used by the benchmarks may explicitly request huge pages, and use of such libraries can make the "madvise" setting relevant and useful.

When no huge pages are immediately available and one is requested, how the system handles the request for THP creation is controlled by the sysfs setting /sys/kernel/mm/transparent_hugepage/defrag. Possible values:

• never: if no THP are available to satisfy a request, do not attempt to make any.
• defer: an allocation requesting THP when none are available gets normal pages while requesting THP creation in the background.
• defer+madvise: acts like "always", but only for allocations in regions marked MADV_HUGEPAGE using madvise(3); for all other regions it's like "defer".
• madvise: acts like "always", but only for allocations in regions marked MADV_HUGEPAGE using madvise(3). This is the default.
• always: an allocation requesting THP when none are available will stall until some are made.

An application that "always" requests THP often can benefit from waiting for an allocation until those huge pages can be assembled.
For more information see the Linux transparent hugepage documentation.

ulimit -s <n>

Sets the stack size to n kbytes, or unlimited to allow the stack size to grow without limit.

ulimit -l <n>

Sets the maximum size of memory that may be locked into physical memory.

powersave -f (on SuSE)

Makes the powersave daemon set the CPUs to the highest supported frequency.

/etc/init.d/cpuspeed stop (on Red Hat)

Disables the cpu frequency scaling program in order to set the CPUs to the highest supported frequency.

LD_LIBRARY_PATH

An environment variable that indicates the location in the filesystem of bundled libraries to use when running the benchmark binaries.

sysctl -w vm.dirty_ratio=8

Limits dirty cache to 8% of memory.

sysctl -w vm.swappiness=1

Limits swap usage to minimum necessary.

sysctl -w vm.zone_reclaim_mode=1

Frees local node memory first to avoid remote memory usage.

kernel/numa_balancing

This OS setting controls automatic NUMA balancing on memory mapping and process placement. NUMA balancing incurs overhead for no benefit on workloads that are already bound to NUMA nodes.

Possible settings:

• 0: disables this feature
• 1: enables the feature (this is the default)

For more information see the numa_balancing entry in the Linux sysctl documentation.

kernel/randomize_va_space (ASLR)

This setting can be used to select the type of process address space randomization. Defaults differ based on whether the architecture supports ASLR, whether the kernel was built with the CONFIG_COMPAT_BRK option or not, or the kernel boot options used.

Possible settings:

• 0 - Turn the process address space randomization off. This is the default for architectures that do not support this feature anyway, and kernels that are booted with the "norandmaps" parameter.
• 1 - Randomize addresses of mmap base, stack, and VDSO pages. This is the default if the CONFIG_COMPAT_BRK option is enabled at kernel build time.
• 2 - Additionally enable heap randomization. This is the default if CONFIG_COMPAT_BRK is disabled.

Disabling ASLR can make process execution more deterministic and runtimes more consistent. For more information see the randomize_va_space entry in the Linux sysctl documentation.

vm/drop_caches

The two commands are equivalent: echo 3> /proc/sys/vm/drop_caches and sysctl -w vm.drop_caches=3 Both must be run as root. The commands are used to free up the filesystem page cache, dentries, and inodes.

Possible settings:

• 1 - Clear pagecache
• 2 - Clear dentries and inodes
• 3 - Clear pagecache, dentries, and inodes

MALLOC_CONF

The amdalloc library is a variant of jemalloc library. The amdalloc library has tunable parameters, many of which may be changed at run-time via several mechanisms, one of which is the MALLOC_CONF environment variable. Other methods, as well as the order in which they're referenced, are detailed in the jemalloc documentation's TUNING section.

The options that can be tuned at run-time are everything in the jemalloc documentation's MALLCTL NAMESPACE section that begins with "opt.".

The options that may be encountered in SPEC CPU 2026 results are detailed here:

• retain:true - Causes unused virtual memory to be retained for later reuse rather than discarding it. This is the default for 64-bit Linux.
• thp:never - Attempts to never utilize huge pages by using MADV_NOHUGEPAGE on all mappings. This option has no effect except when THP is set to "madvise".

PGHPF_ZMEM

An environment variable used to initialize the allocated memory. Setting PGHPF_ZMEM to "Yes" has the effect of initializing all allocated memory to zero.

GOMP_CPU_AFFINITY

This environment variable is used to set the thread affinity for threads spawned by OpenMP.

OMP_DYNAMIC

This environment variable is defined as part of the OpenMP standard. Setting it to "false" prevents the OpenMP runtime from dynamically adjusting the number of threads to use for parallel execution.

For more information, see chapter 4 ("Environment Variables") in the OpenMP 4.5 Specification.

OMP_SCHEDULE

This environment variable is defined as part of the OpenMP standard. Setting it to "static" causes loop iterations to be assigned to threads in round-robin fashion in the order of the thread number.

For more information, see chapter 4 ("Environment Variables") in the OpenMP 4.5 Specification.

OMP_STACKSIZE

This environment variable is defined as part of the OpenMP standard and controls the size of the stack for threads created by OpenMP.

For more information, see chapter 4 ("Environment Variables") in the OpenMP 4.5 Specification.

OMP_THREAD_LIMIT

This environment variable is defined as part of the OpenMP standard and limits the maximum number of OpenMP threads that can be created.

For more information, see chapter 4 ("Environment Variables") in the OpenMP 4.5 Specification.

Operating System Tuning Parameters

kernel.randomize_va_space (ASLR)

This setting can be used to select the type of process address space randomization. Defaults differ based on whether the architecture supports ASLR, whether the kernel was built with the CONFIG_COMPAT_BRK option or not, or the kernel boot options used.
Possible settings:

• 0: Turn process address space randomization off.
• 1: Randomize addresses of mmap base, stack, and VDSO pages.
• 2: Additionally randomize the heap. (This is probably the default.)

Disabling ASLR can make process execution more deterministic and runtimes more consistent. For more information see the randomize_va_space entry in the Linux sysctl documentation.

Transparent Hugepages (THP)

THP is an abstraction layer that automates most aspects of creating, managing, and using huge pages. It is designed to hide much of the complexity in using huge pages from system administrators and developers. Huge pages increase the memory page size from 4 kilobytes to 2 megabytes. This provides significant performance advantages on systems with highly contended resources and large memory workloads. If memory utilization is too high or memory is badly fragmented which prevents hugepages being allocated, the kernel will assign smaller 4k pages instead. Most recent Linux OS releases have THP enabled by default.
THP usage is controlled by the sysfs setting /sys/kernel/mm/transparent_hugepage/enabled. Possible values:

• never: entirely disable THP usage.
• madvise: enable THP usage only inside regions marked MADV_HUGEPAGE using madvise(3).
• always: enable THP usage system-wide. This is the default.

THP creation is controlled by the sysfs setting /sys/kernel/mm/transparent_hugepage/defrag. Possible values:

• never: if no THP are available to satisfy a request, do not attempt to make any.
• defer: an allocation requesting THP when none are available get normal pages while requesting THP creation in the background.
• defer+madvise: acts like "always", but only for allocations in regions marked MADV_HUGEPAGE using madvise(3); for all other regions it's like "defer".
• madvise: acts like "always", but only for allocations in regions marked MADV_HUGEPAGE using madvise(3). This is the default.
• always: an allocation requesting THP when none are available will stall until some are made.

An application that "always" requests THP often can benefit from waiting for an allocation until those huge pages can be assembled.
For more information see the Linux transparent hugepage documentation.

dirty_ratio

This is a percentage value of total available memory that can be filled with dirty data before writing the modifications to disk. Set through "sysctl -w vm.dirty_ratio=8".

swappiness

This control is used to define how aggressive the kernel will swap memory pages. Increaasing the value causes swapping more frequently. The default value is 60. A value of 1 tells the kernel to only swap processes to disk if absolutely necessary. This can be set through a command like "sysctl -w vm.swappiness=1"

zone_reclaim_mode

Zone_reclaim_mode allows someone to set more or less aggressive approaches to reclaim memory when a zone runs out of memory. It controls whether memory reclaim is performed on a local NUMA node or other nodes. To tell the kernel to free local node memory rather than grabbing free memory from remote nodes, it can be set through a command like "sysctl -w vm.zone_reclaim_mode=1".

drop_caches

Writing this will cause kernel to drop clean caches, as well as reclaimable slab objects like dentries and inodes. Once dropped, their memory becomes free. Set through "sysctl -w vm.drop_caches=3" to free slab objects and pagecache.

CPUFreq scaling governor:

Governors are power schemes for the CPU. It is in-kernel pre-configured power schemes for the CPU and allows you to change the clock speed of the CPUs on the fly. On Linux systems can set the govenor for all CPUs through the cpupower utility with the following command:

• "cpupower -c all frequency-set -g governor"

Below are govenors in the Linux kernel.

• performance: Run the CPU at the maximum frequency.
• powersave: Run the CPU at the minimum frequency.
• userspace: Run the CPU at user specified frequencies.
• ondemand: Scales the frequency dynamically according to current load. Jumps to the highest frequency and then possibly back off as the idle time increases.
• conservative: Scales the frequency dynamically according to current load. Scales the frequency more gradually than ondemand.
• schedutil: Scheduler-driven CPU frequency selection.

tuned-adm:

A commandline interface for switching between different tuning profiles available in supported Linux distributions. The distribution provided profiles are located in /usr/lib/tuned and the user defined profiles in /etc/tuned. To set a profile, one can issue the command "tuned-adm profile (profile_name)". Below are details about some relevant profiles.

• throughput-performance: For typical throughput performance tuning. Disables power saving mechanisms and enables sysctl settings that improve the throughput performance of disk and network I/O. CPU governor is set to performance and CPU energy performance bias is set to performance. Disk readahead values are increased.
• latency-performance: For low latency performance tuning. Disables power saving mechanisms. CPU governor is set to performance and locked to the low C states. CPU energy performance bias to performance.
• balanced: Default profile provides balanced power saving and performance. It enables CPU and disk plugins of tuned and makes the conservative governor is active and also sets the CPU energy performance bias to normal. It also enables power saving on audio and graphics card.
• powersave: Maximal power saving for whole system. It sets the CPU governor to ondemand governor and energy performance bias to powersave. It also enable power saving on USB, SATA, audio and graphics card.

Firmware / BIOS / Microcode Settings

Determinism Control:

This BIOS option allows for choose AGESA determinism control. AGESA is an acronym for "AMD Generic Encapsulated Software Architecture." AGESA is a bootstrap protocol by which system devices on AMD64-architecture mainboards are initialized, it responsible for the initialization of the processor cores, memory, and the HyperTransport controller. Available settings are:

• Manual: User can customize determinism slider.
• Auto (Default setting): Use the processor fused determinism control.

Determinism Enable:

This BIOS option allows for Enable/Disable AGESA determinism to control performance. AGESA is an acronym for "AMD Generic Encapsulated Software Architecture." AGESA is a bootstrap protocol by which system devices on AMD64-architecture mainboards are initialized, it responsible for the initialization of the processor cores, memory, and the HyperTransport controller. "Performance determinism" tells the processor to run in a consistent manner which allows consistent repeatability when doing benchmarks or performance testing. The processor will run at the best performance with little deviation allowing repeatable runs. Available settings are:

• Performance: AGESA will enable 100% deterministic performance control.
• Power: AGESA will not enable deterministic performance control.

TDP Control:

This BIOS option is for "Configurable TDP (cTDP)", it allows user can set customized value for TDP. Available settings are:

• Auto (Default setting): Use the fused TDP value.
• Manual: Let user specifies customized TDP value.

TDP:

TDP is an acronym for “Thermal Design Power.” TDP is the recommended target for power used when designing the cooling capacity for a server. EPYC processors are able to control this target power consumption within certain limits. This capability is referred to as “configurable TDP” or "cTDP." cTDP can be used to reduce power consumption for greater efficiency, or in some cases, increase power consumption above the default value to provide additional performance. cTDP is controlled using a BIOS option.

The default EPYC cTDP value corresponds with the microprocessor’s nominal TDP. For the EPYC 9355, the default value is 280W. The default cTDP value is set at a good balance between performance and energy efficiency. The EPYC 9355 cTDP can be reduced as low as 240W, which will minimize the power consumption for the processor under load, but at the expense of peak performance. Increasing the EPYC 9355 cTDP to 300W will maximize peak performance by allowing the CPU to maintain higher dynamic clock speeds, but will make the microprocessor less energy efficient. Note that at maximum cTDP, the CPU thermal solution must be capable of dissipating at least 300W or the EPYC 9354 processor might engage in thermal throttling under load.

The available cTDP ranges for each EPYC model are in the table below:

Model	Nominal TDP	Minimum cTDP	Maximum cTDP*
EPYC 9965	500W	450W	500W
EPYC 9845	390W	320W	400W
EPYC 9745	400W	320W	400W
EPYC 9755	500W	450W	500W
EPYC 9655	400W	320W	400W
EPYC 9655P	400W	320W	400W
EPYC 9575F	400W	320W	400W
EPYC 9565	400W	320W	400W
EPYC 9555	360W	320W	400W
EPYC 9555P	360W	320W	400W
EPYC 9535	300W	240W	300W
EPYC 9475F	400W	320W	400W
EPYC 9455	300W	240W	300W
EPYC 9455P	300W	240W	300W
EPYC 9375F	320W	320W	400W
EPYC 9355	280W	240W	300W
EPYC 9355P	280W	240W	300W
EPYC 9135	200W	200W	240W
EPYC 9115	125W	120W	155W
EPYC 9015	125W	120W	155W

* cTDP must remain below the thermal solution design parameters or thermal throttling could be frequently encountered.

IOMMU:

The I/O Memory Management Unit (IOMMU) extends the AMD64 system architecture by adding support for address translation and system memory access protection on DMA transfers from periph-eral devices. IOMMU also helps filter and remap interrupts from peripheral devices. Available settings are:

• Disabled: Disable IOMMU support.
• Enabled: Enable IOMMU support.
• Auto (Default setting): Use default value for IOMMU. The default value is disable.

Package Power Limit Control:

This is a per processor Package Power Limit (PPT) value applicable for all populated processors in the system. This can be set to limit the PPT to a certain value. Available settings are:

• Auto (Default setting): Use the fused processor PPT value.
• Manual: Let user specifies customized processor PPT value.

Package Power Limit:

Set customize processor Package Power Limit (PPT) value to be used on all populated processors in the system. If set to 240 = Use the 240W PPT ***PPT will be used as the ASIC power limit***

APBDIS:

APBDis is an IO Boost disable on uncore. For any system user that needs to block these uncore optimizations that are impacting base core clock speed, we are exposing a method to disable this behavior called APBDis. This locks the fabric clock to the non-boosted speeds. Available settings are:

• 0: Disable APBDIS, locks the fabric clock to the non-boosted speeds.
• 1: Enable APBDIS, unlocks the fabric clock to the boosted speeds.
• Auto (Default setting): Use default value for APBDIS. The default value is 0.

NUMA Nodes Per Socket:

Specifies the number of desired NUMA nodes per socket. This option allows the user to divide the memory that each socket has into a certain number of NUMA memory nodes for optimal memory bandwidth. Available settings are:

• NPS0: It will attempt to interleave the two sockets together.
• NPS1: Each processor socket will have one NUMA memory node.
• NPS2: Each processor socket will have two NUMA memory nodes.
• NPS4: Each processor socket will have four NUMA memory nodes.
• Auto (Default setting): Use default value for NUMA nodes per socket. The default value is NPS1.

SMT Control:

This controls enable or disable the logical processor cores on the processor. Enable SMT Control can improve overall performance for most workloads. For some floating point or HPC workloads may result in highr performance if disable SMT Control. Available settings are:

• Disabled: It will disable all logical cores on the processor.
• Auto (Default setting): Enable all logical cores on the processor.

ACPI SRAT L3 cache As NUMA Domain:

Controls generation of distance information in the ACPI System Locality Information Table (SLIT) and NUMA proximity domains in the System Resource Affinity Table (SRAT). Enabling this feature can increase performance for workloads that are NUMA aware and optimized. Available settings are:

• Disabled: Not seperate each CCX within the processor as a NUMA domain.
• Enabled: Each CCX within the processor will be declared as a NUMA domain.
• Auto (Default setting): Use default value. Which is not seperate each CCX as a NUMA domain.

TSME:

This controls enable or disable the Transparent Secure Memory Encryption. Enable TSME can improve security by encrypt the data in memory. Disable for lower memory latency. Available settings are:

• Disabled: It will disable Transparent Secure Memory Encryption function.
• Enabled: It will enable Transparent Secure Memory Encryption function.
• Auto (Default setting): Enable TSME.

SEV Control:

This controls enable or disable the Secure Encrypted Virtualization. SEV is an extension of SME that effectively enables a per-virtual machine SME. In other words, SEV enables running encrypted virtual machines in which the code and data of the VM are private to the VM and may only be decrypted within the VM itself. Available settings are:

• Disabled: It will disable Secure Encrypted Virtualization function.
• Enabled (Default setting): It will enable Secure Encrypted Virtualization function.

Core Performance Boost:

Core Performance Boost (CPB) is a dynamic frequency scaling technology implemented by AMD that allows the processor to dynamically adjust and control the processor operating frequency in certain versions of its processors which allows for increased performance when needed while maintaining lower power and thermal parameters during normal operation. Available settings are:

• Disabled: It will disable Core Performance Boost function.
• Auto (Default setting): It will enable Core Performance Boost function.

Memory Target Speed:

Specifies the memory target speed on the system in MT/s. Available settings are:

• DDR3600: It will set memory at 3600 MT/s.
• DDR4000: It will set memory at 4000 MT/s.
• DDR4400: It will set memory at 4400 MT/s.
• DDR4800: It will set memory at 4800 MT/s.
• DDR5200: It will set memory at 5200 MT/s.
• DDR5600: It will set memory at 5600 MT/s.
• DDR6000: It will set memory at 6000 MT/s.
• DDR6400: It will set memory at 6400 MT/s.
• Auto (Default setting): It will set memory at highest supported speed.

DRAM Scrub Time:

Specifies the time to perform memory scrubbing action. It consists of reading from each computer memory location, correcting bit errors (if any) with an error-correcting code (ECC), and writing the corrected data back to the same location. Available settings are:

• Disabled: It will disable memory scrubbing.
• 1 hour: It will set memory scrubbing action to be performed every 1 hour.
• 4 hours: It will set memory scrubbing action to be performed every 4 hours.
• 6 hours: It will set memory scrubbing action to be performed every 6 hours.
• 8 hours: It will set memory scrubbing action to be performed every 8 hours.
• 12 hours: It will set memory scrubbing action to be performed every 12 hours.
• 24 hours (Default setting): It will set memory scrubbing action to be performed every 24 hours.
• 48 hours: It will set memory scrubbing action to be performed every 48 hours.

xGMI Force Link Width:

Force the xGMI link width at specified value. Available settings are:

• x4: Forced the xGMI link width to x4.
• x8: Forced the xGMI link width to x8.
• x16 (Default setting): Forced the xGMI link width to x16.

xGMI Max Link Width:

Specifies the maximum xGMI link width. Available settings are:

• x4: Set the maximum xGMI link width to x4.
• x8: Set the maximum xGMI link width to x8.
• x16 (Default setting): Set the maximum xGMI link width to x16.

4-link xGMI max speed:

Specifies the maximum 4-link xGMI link speed between 2 CPUs. Available settings are: 10.667Gbps, 11Gbps, 12Gbps, 13Gbps, 14Gbps, 15Gbps, 16Gbps, 17Gbps, 18Gbps, 19Gbps, 20Gbps, 21Gbps, 22Gbps and Auto (Default setting).

BoostFmax:

Specifies the maximum CPU core boost frequency value in MHz.

ACPI CST C2 Latency:

C2 Latency is a value that the BIOS communicates to the OS that helps it determine when it should enter lower power states. This defines C2 latency values in microseconds. Lower C2 latency values will reduce the number of C2 transitions and C2 residency. With higher values may allow higher frequency boost and reduce idle core power. Default value is "100"

Workload Profile: (Default = "Disabled")

Workload Profile loads pre-configured BIOS settings for specific workload type. Available options are:

• Disabled: Do not load any pre-configured BIOS settings.
• HPC: Load BIOS settings for HPC related workloads.
• I/O: Load BIOS settings for I/O intensive workloads.
• Virtualization: Load BIOS settings for Virtualization related workloads.
• Telco NFVI: Load BIOS settings for server runs NFVI in telecommunication environment.
• Telco NFVI-FP: Load BIOS settings for server runs NFVI-FP in telecommunication environment.
• Telco FlexRAN: Load BIOS settings for server runs FlexRAN in telecommunication environment.

SMEE:

This controls enable or disable the Secure Memory Encryption Enable. Enable SMEE can improve security by encrypt the data in memory. Disable for lower memory latency. Available settings are:

• Disabled: It will disable Secure Memory Encryption Enable function.
• Enabled: It will enable Secure Memory Encryption Enable function.
• Auto (Default setting): Enable SMEE.

Flag description origin markings:

	Indicates that the flag description came from the user flags file.
	Indicates that the flag description came from the suite-wide flags file.
	Indicates that the flag description came from a per-benchmark flags file.

For questions about the meanings of these flags, please contact the tester.
For other inquiries, please contact info@spec.org
Copyright 2026 Standard Performance Evaluation Corporation
Tested with SPEC CPU®2026 v0.902.0.
Report generated on 2026-05-04 23:30:43 by SPEC CPU®2026 flags formatter (5b352a85).