Copyright © 2016 Intel Corporation. All Rights Reserved.
Invoke the Intel C compiler driver
Invoke the Intel C++ compiler driver
Invoke the Intel Fortran compiler driver
This macro specifies that the target system uses the LP64 data model; specifically, that integers are 32 bits, while longs and pointers are 64 bits.
This macro indicates that the benchmark is being compiled on an AMD64-compatible system running the Linux operating system.
This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.
This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.
This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.
This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.
This flag can be set for SPEC compilation for LINUX using default compiler.
This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.
This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.
This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.
This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.
This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.
Enable SmartHeap and/or other library usage by forcing the linker to ignore multiple definitions if present
Code is optimized for Intel(R) processors with support for CORE-AVX512 instructions. The resulting code may contain unconditional use of features that are not supported on other processors. This option also enables new optimizations in addition to Intel processor-specific optimizations including advanced data layout and code restructuring optimizations to improve memory accesses for Intel processors.
Do not use this option if you are executing a program on a processor that is not an Intel processor. If you use this option on a non-compatible processor to compile the main program (in Fortran) or the function main() in C/C++, the program will display a fatal run-time error if they are executed on unsupported processors.
Multi-file ip optimizations that includes:
- inline function expansion
- interprocedural constant propogation
- dead code elimination
- propagation of function characteristics
- passing arguments in registers
- loop-invariant code motion
Enables O2 optimizations plus more aggressive optimizations, such as prefetching, scalar replacement, and loop and memory access transformations. Enables optimizations for maximum speed, such as:
On IA-32 and Intel EM64T processors, when O3 is used with options -ax or -x (Linux) or with options /Qax or /Qx (Windows), the compiler performs more aggressive data dependency analysis than for O2, which may result in longer compilation times. The O3 optimizations may not cause higher performance unless loop and memory access transformations take place. The optimizations may slow down code in some cases compared to O2 optimizations. The O3 option is recommended for applications that have loops that heavily use floating-point calculations and process large data sets.
-no-prec-div enables optimizations that give slightly less precise results than full IEEE division.
When you specify -no-prec-div along with some optimizations, such as -xN and -xB (Linux) or /QxN and /QxB (Windows), the compiler may change floating-point division computations into multiplication by the reciprocal of the denominator. For example, A/B is computed as A * (1/B) to improve the speed of the computation.
However, sometimes the value produced by this transformation is not as accurate as full IEEE division. When it is important to have fully precise IEEE division, do not use -no-prec-div. This will enable the default -prec-div and the result will be more accurate, with some loss of performance.
Controls the level of memory layout transformations performed by the compiler. This option can improve cache reuse and cache locality.
Definition of this macro indicates that compilation for parallel operation is enabled, and that any OpenMP directives or pragmas will be visible to the compiler.
Specify build time link path for jemalloc 64bit built to support the CPU2017/2006 build. See jemalloc.net for more information.
Linker toggle to specify jemalloc linker library. See jemalloc.net for more information.
Enable SmartHeap and/or other library usage by forcing the linker to ignore multiple definitions if present
Code is optimized for Intel(R) processors with support for CORE-AVX512 instructions. The resulting code may contain unconditional use of features that are not supported on other processors. This option also enables new optimizations in addition to Intel processor-specific optimizations including advanced data layout and code restructuring optimizations to improve memory accesses for Intel processors.
Do not use this option if you are executing a program on a processor that is not an Intel processor. If you use this option on a non-compatible processor to compile the main program (in Fortran) or the function main() in C/C++, the program will display a fatal run-time error if they are executed on unsupported processors.
Multi-file ip optimizations that includes:
- inline function expansion
- interprocedural constant propogation
- dead code elimination
- propagation of function characteristics
- passing arguments in registers
- loop-invariant code motion
Enables O2 optimizations plus more aggressive optimizations, such as prefetching, scalar replacement, and loop and memory access transformations. Enables optimizations for maximum speed, such as:
On IA-32 and Intel EM64T processors, when O3 is used with options -ax or -x (Linux) or with options /Qax or /Qx (Windows), the compiler performs more aggressive data dependency analysis than for O2, which may result in longer compilation times. The O3 optimizations may not cause higher performance unless loop and memory access transformations take place. The optimizations may slow down code in some cases compared to O2 optimizations. The O3 option is recommended for applications that have loops that heavily use floating-point calculations and process large data sets.
-no-prec-div enables optimizations that give slightly less precise results than full IEEE division.
When you specify -no-prec-div along with some optimizations, such as -xN and -xB (Linux) or /QxN and /QxB (Windows), the compiler may change floating-point division computations into multiplication by the reciprocal of the denominator. For example, A/B is computed as A * (1/B) to improve the speed of the computation.
However, sometimes the value produced by this transformation is not as accurate as full IEEE division. When it is important to have fully precise IEEE division, do not use -no-prec-div. This will enable the default -prec-div and the result will be more accurate, with some loss of performance.
Controls the level of memory layout transformations performed by the compiler. This option can improve cache reuse and cache locality.
Specify build time link path for jemalloc 64bit built to support the CPU2017/2006 build. See jemalloc.net for more information.
Linker toggle to specify jemalloc linker library. See jemalloc.net for more information.
Enable SmartHeap and/or other library usage by forcing the linker to ignore multiple definitions if present
Code is optimized for Intel(R) processors with support for CORE-AVX512 instructions. The resulting code may contain unconditional use of features that are not supported on other processors. This option also enables new optimizations in addition to Intel processor-specific optimizations including advanced data layout and code restructuring optimizations to improve memory accesses for Intel processors.
Do not use this option if you are executing a program on a processor that is not an Intel processor. If you use this option on a non-compatible processor to compile the main program (in Fortran) or the function main() in C/C++, the program will display a fatal run-time error if they are executed on unsupported processors.
Multi-file ip optimizations that includes:
- inline function expansion
- interprocedural constant propogation
- dead code elimination
- propagation of function characteristics
- passing arguments in registers
- loop-invariant code motion
Enables O2 optimizations plus more aggressive optimizations, such as prefetching, scalar replacement, and loop and memory access transformations. Enables optimizations for maximum speed, such as:
On IA-32 and Intel EM64T processors, when O3 is used with options -ax or -x (Linux) or with options /Qax or /Qx (Windows), the compiler performs more aggressive data dependency analysis than for O2, which may result in longer compilation times. The O3 optimizations may not cause higher performance unless loop and memory access transformations take place. The optimizations may slow down code in some cases compared to O2 optimizations. The O3 option is recommended for applications that have loops that heavily use floating-point calculations and process large data sets.
-no-prec-div enables optimizations that give slightly less precise results than full IEEE division.
When you specify -no-prec-div along with some optimizations, such as -xN and -xB (Linux) or /QxN and /QxB (Windows), the compiler may change floating-point division computations into multiplication by the reciprocal of the denominator. For example, A/B is computed as A * (1/B) to improve the speed of the computation.
However, sometimes the value produced by this transformation is not as accurate as full IEEE division. When it is important to have fully precise IEEE division, do not use -no-prec-div. This will enable the default -prec-div and the result will be more accurate, with some loss of performance.
Controls the level of memory layout transformations performed by the compiler. This option can improve cache reuse and cache locality.
Option standard-realloc-lhs (the default), tells the compiler that when the left-hand side of an assignment is an allocatable object, it should be reallocated to the shape of the right-hand side of the assignment before the assignment occurs. This is the current Fortran Standard definition. This feature may cause extra overhead at run time. This option has the same effect as option assume realloc_lhs.
If you specify nostandard-realloc-lhs, the compiler uses the old Fortran 2003 rules when interpreting assignment statements. The left-hand side is assumed to be allocated with the correct shape to hold the right-hand side. If it is not, incorrect behavior will occur. This option has the same effect as option assume norealloc_lhs.
The align toggle changes how data elements are aligned. Variables and arrays are analyzed and memory layout can be altered. Specifying array32byte will look for opportunities to transform and reailgn arrays to 32byte boundaries.
Specify build time link path for jemalloc 64bit built to support the CPU2017/2006 build. See jemalloc.net for more information.
Linker toggle to specify jemalloc linker library. See jemalloc.net for more information.
Specify the uarch target for the compiled executable to be intel64. Seperate, further toggles may add various other instruction set features. Particularly useful in 32bit mode.
Invoke the Intel C compiler in C99 mode
Specify the uarch target for the compiled executable to be intel64. Seperate, further toggles may add various other instruction set features. Particularly useful in 32bit mode.
Specify the uarch target for the compiled executable to be intel64. Seperate, further toggles may add various other instruction set features. Particularly useful in 32bit mode.
This section contains descriptions of flags that were included implicitly by other flags, but which do not have a permanent home at SPEC.
Enables optimizations for speed. This is the generally recommended
optimization level. This option also enables:
- Inlining of intrinsics
- Intra-file interprocedural optimizations, which include:
- inlining
- constant propagation
- forward substitution
- routine attribute propagation
- variable address-taken analysis
- dead static function elimination
- removal of unreferenced variables
- The following capabilities for performance gain:
- constant propagation
- copy propagation
- dead-code elimination
- global register allocation
- global instruction scheduling and control speculation
- loop unrolling
- optimized code selection
- partial redundancy elimination
- strength reduction/induction variable simplification
- variable renaming
- exception handling optimizations
- tail recursions
- peephole optimizations
- structure assignment lowering and optimizations
- dead store elimination
Enables optimizations for speed and disables some optimizations that increase code size and affect speed.
To limit code size, this option:
The O1 option may improve performance for applications with very large code size, many branches, and execution time not dominated by code within loops.
-O1 sets the following options:Tells the compiler the maximum number of times to unroll loops. For example -funroll-loops0 would disable unrolling of loops.
-fno-builtin disables inline expansion for all intrinsic functions.
This option trades off floating-point precision for speed by removing the restriction to conform to the IEEE standard.
EBP is used as a general-purpose register in optimizations.
Places each function in its own COMDAT section.
Flushes denormal results to zero.
OS Tuning
ulimit:
Used to set user limits of system-wide resources. Provides control over resources available to the shell and processes started by it. Some common ulimit commands may include:
vm.max_map_count-n (Linux):
The maximum number of memory map areas a process may have. Memory map areas are used as a side-effect of calling malloc, directly by mmap and mprotect, and also when loading shared libraries.
Zone Reclaim:
Zone reclaim allows the reclaiming of pages from a zone if the number of free pages falls below a watermark even if other zones still have enough pages available. Reclaiming a page can be more beneficial than taking the performance penalties that are associated with allocating a page on a remote zone, especially for NUMA machines.
Performance Governors (Linux):
In-kernel CPU frequency governors are pre-configured power schemes for the CPU. The CPUfreq governors use P-states to change frequencies and lower power consumption. The dynamic governors can switch between CPU frequencies, based on CPU utilization to allow for power savings while not sacrificing performance.
Other options beside a generic performance governor can be set, such as the perf-bias:
--perf-bias, -b
On supported Intel processors, this option sets a register which allows the cpupower utility (or other software/firmware) to set a policy that controls the relative importance of performance versus energy savings to the processor. The range of valid numbers is 0-15, where 0 is maximum performance and 15 is maximum energy efficiency.
The processor uses this information in model-specific ways when it must select trade-offs between performance and energy efficiency. This policy hint does not supersede Processor Performance states (P-states) or CPU Idle power states (C-states), but allows software to have influence where it would otherwise be unable to express a preference.
On many Linux systems one can set the perf-bias for all CPUs through the cpupower utility with one of the following commands:
Disabling Linux services:
Certain Linux services may be disabled to minimize tasks that may consume CPU cycles.
irqbalance:
Disabled through "service irqbalance stop". Depending on the workload involved, the irqbalance service reassigns various IRQ's to system CPUs. Though this service might help in some situations, disabling it can also help environments which need to minimize or eliminate latency to more quickly respond to events.
numa_balancing:
Disabled through "echo 0 > /proc/sys/kernel/numa_balancing". This feature will automatically migrate data on demand so memory nodes are aligned to the local CPU that is accessing data. Depending on the workload involved, enabling this can boost the performance if the workload performs well on NUMA hardware. If the workload is statically set to balance between nodes, then this service may not provide a benefit.
Tuning Kernel parameters:
The following Linux Kernel parameters were tuned to better optimize performance of some areas of the system:
swappiness:
The swappiness value can range from 1 to 100. A value of 100 will cause the kernel to swap out inactive processes frequently in favor of file system performance, resulting in large disk cache sizes. A value of 1 tells the kernel to only swap processes to disk if absolutely necessary.
tuned-adm:
The tuned-adm tool is a commandline interface for switching between different tuning profiles available to the tuned tuning daeomn available in supported Linux distros. The default configuration file is located in /etc/tuned.conf and the supported profiles can be found in /etc/tune-profiles.
Some profiles that may be available by default include: default, desktop-powersave, server-powersave, laptop-ac-powersave, laptop-battery-powersave, spindown-disk, throughput-performance, latency-performance, enterprise-storage
To set a profile, one can issue the command "tuned-adm profile (profile_name)". Here are details about relevant profiles.
Transparent Huge Pages (THP):
THP is an abstraction layer that automates most aspects of creating, managing, and using huge pages. THP is designed to hide much of the complexity in using huge pages from system administrators and developers, as normal huge pages must be assigned at boot time, can be difficult to manage manually, and often require significant changes to code in order to be used effectively. Transparent Hugepages increase the memory page size from 4 kilobytes to 2 megabytes. Transparent Hugepages provide 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.
Linux Huge Page settings:
If you need finer control and manually set the Huge Pages you can follow the below steps:
Note that further information about huge pages may be found in your Linux documentation file: /usr/src/linux/Documentation/vm/hugetlbpage.txt
Firmware Settings
One or more of the following settings may have been set. If so, the "Platform Notes" section of the report will say so; and you can read below to find out more about what these settings mean.
Intel Hyper-Threading (Default = Enabled):
This feature allows enabling or disabling of logical processor cores on processors supporting Intel Hyper-Threading (HT). When enabled, each physical processor core operates as two logical processor cores. When disabled, each physical core operates as only one logical processor core. Enabling this option can improve overall performance for applications that benefit from a higher processor core count.
Thermal Configuration (Default = Optimal Cooling):
This feature allows the user to select the fan cooling solution for the system. Values for this BIOS option can be:
Last Level Cache (LLC) Dead Line Allocation (Default = Enabled):
In the Skylake cache scheme, mid-level cache (MLC) evictions are filled into the last level cache (LLC). If a line is evicted from the MLC to the LLC, the Skylake core can flag the evicted MLC lines as "dead". This means that the lines are not likely to be read again. This option allows dead lines to be dropped and never fill the LLC if the option is disabled. Values for this BIOS option can be:
Stale A to S (Default = Disabled):
The in-memory directory has three states: invalid (I), snoopAll (A), and shared (S). Invalid (I) state means the data is clean and does not exist in any other socket`s cache. The snoopAll (A) state means the data may exist in another socket in exclusive or modified state. Shared (S) state means the data is clean and may be shared across one or more socket`s caches. When doing a read to memory, if the directory line is in the A state we must snoop all the other sockets because another socket may have the line in modified state. If this is the case, the snoop will return the modified data. However, it may be the case that a line is read in A state and all the snoops come back a miss. This can happen if another socket read the line earlier and then silently dropped it from its cache without modifying it. Values for this BIOS option can be:
Stale A to S may be beneficial in a workload where there are many cross-socket reads.
Last Level Cache (LLC) Prefetch (Default = Disabled):
This option configures the processor Last Level Cache (LLC) prefetch feature as a result of the non-inclusive cache architecture. The LLC prefetcher exists on top of other prefetchers that that can prefetch data in the core data cache unit (DCU) and mid-level cache(MLC). In some cases, setting this option to disabled can improve performance. Typically, setting this option to enable provides better performance. Values for this BIOS option can be:
NUMA Group Size Optimization (Default = Clustered):
This feature allows the user to configure how the BIOS reports the size of a NUMA node (number of logical processors), which assists the Operating System in grouping processors for application use (referred to as Kgroups). Values for this BIOS option can be:
Sub-NUMA Cluster (SNC) (Default = Enabled):
SNC breaks up the last level cache (LLC) into disjoint clusters based on address range, with each cluster bound to a subset of the memory controllers in the system. SNC improves average latency to the LLC and memory. SNC is a replacement for the cluster on die (COD) feature found in previous processor families. For a multi-socketed system, all SNC clusters are mapped to unique NUMA domains. (See also IMC interleaving.) Values for this BIOS option can be:
Xtended Prediciton Table (XPT) Prefetch (Default = Enabled):
This option configures the processor Xtended Prediciton Table (XPT) prefetch feature. The XPT prefetcher exists on top of other prefetchers that that can prefetch data in the core DCU, MLC, and LLC. The XPT prefetcher will issue a speculative DRAM read request in parallel to an LLC lookup. This prefetch bypasses the LLC, saving latency. In some cases, setting this option to disabled can improve performance. In some cases, setting this option to disabled can improve performance. Typically, setting this option to enable provides better performance. This option must be enabled when Sub-NUMA Clustering is enabled. Values for this BIOS option can be:
Uncore Frequency Scaling (Default = Auto):
This option controls the frequency scaling of the processor`s internal buses (the uncore). Values for this BIOS option can be:
Workload Profile (Default = General Power Efficient Compute):
This option allows a user to choose one workload profile that best fits the user`s needs. The workload profiles control many power and performance settings that are relevant to general workload areas. Values for this BIOS option can be:
Minimum Processor Idle Power Core C-State (Default = C6 State):
This option can only be configured if the Workload Profile is set to Custom, or this option is not a dependent value for the Workload Profile. This feature selects the processor's lowest idle power state (C-state) that the operating system uses. The higher the C-state, the lower the power usage of that idle state (C6 is the lowest power idle state supported by the processor). Values for this setting can be:
Minimum Processor Idle Power Package C-State (Default = Package C6 (retention) State):
This option can only be configured if the Workload Profile is set to Custom, or this option is not a dependent value for the Workload Profile. This feature selects the processor's lowest idle package power state (C-state) that is enabled. The processor will automatically transition into the package C-states based on the Core C-states, in which cores on the processor have transitioned. The higher the package C-state, the lower the power usage of that idle package state. Package C6 (retention) is the lowest power idle package state supported by the processor). Values for this setting can be:
Energy/Performance Bias (Default = Balanced Performance):
This option can only be configured if the Workload Profile is set to Custom, or this option is not a dependent value for the Workload Profile. This option configures several processor subsystems to optimize the processor's performance and power usage. Values for this BIOS setting can be:
AHS PCI Logging Level (Default = Verbose Logging):
This option allows the AHS PCI Logging size to be changed. This is a boot time option that should have no effect on run time performance. Values for this BIOS setting can be:
Memory Patrol Scrubbing (Default = Enabled):
This option allows for correction of soft memory errors. Over the length of system runtime, the risk of producing multi-bit and uncorrected errors is reduced with this option. Values for this BIOS setting can be:
Last updated December 11, 2017.
Flag description origin markings:
For questions about the meanings of these flags, please contact the tester.
For other inquiries, please contact info@spec.org
Copyright 2017-2018 Standard Performance Evaluation Corporation
Tested with SPEC CPU2017 v1.0.2.
Report generated on 2018-10-31 14:56:50 by SPEC CPU2017 flags formatter v5178.