SPEC CPU2006 Platform Settings for HP Proliant Intel-based systems

Operating System Tuning Parameters

OS Tuning

submit= MYMASK=`printf '0x%x' \$((1<<\$SPECCOPYNUM))`; /usr/bin/taskset \$MYMASK $command

When running multiple copies of benchmarks, the SPEC config file feature submit is sometimes used to cause individual jobs to be bound to specific processors. This specific submit command is used for Linux. The description of the elements of the command are:

• /usr/bin/taskset [options] [mask] [pid | command [arg] ... ]:
  taskset is used to set or retreive the CPU affinity of a running process given its PID or to launch a new COMMAND with a given CPU affinity. The CPU affinity is represented as a bitmask, with the lowest order bit corresponding to the first logical CPU and highest order bit corresponding to the last logical CPU. When the taskset returns, it is guaranteed that the given program has been scheduled to a legal CPU.
  
  The default behaviour of taskset is to run a new command with a given affinity mask:
  
  taskset [mask] [command] [arguments]
• $MYMASK: The bitmask (in hexadecimal) corresponding to a specific SPECCOPYNUM. For example, $MYMASK value for the first copy of a rate run will be 0x00000001, for the second copy of the rate will be 0x00000002 etc. Thus, the first copy of the rate run will have a CPU affinity of CPU0, the second copy will have the affinity CPU1 etc.
• $command: Program to be started, in this case, the benchmark instance to be started.

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 effect 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 memory on the local node while "-m" specifies which node(s) to place a process memory. For full details on using numactl, please refer to your Linux documentation, 'man numactl'

numactl --interleave=all "runspec command"

Launching a process with numactl --interleave=all sets the memory interleave policy so that memory will be allocated using round robin on nodes. When memory cannot be allocated on the current interleave target fall back to other nodes.

Transparent Huge Pages

On RedHat EL 6 and later, 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. Hugepages are used by default if /sys/kernel/mm/redhat_transparent_hugepage/enabled is set to always.

Drive Write Cache

The Drive Write Cache is an option that can be enabled or disabled in the HP Array Configuration Utility, CLI version. The default value for the Drive Write Cache is set to Disabled, and in order to change this the HP Arracy Configuration Utility, CLI version needs to be installed. When the Drive Write Cache option is enabled on a HP Smart Arrary Controller in a system, it can allow the HP Smart Array Controller to help make drive writes more efficient.

Accelerator Ratio

The Accelerator Ratio is an option that can be set to different percentages (in 25% increments) in the HP Array Configuration Utility, CLI version. The default value for the Accelerator Ratio is set to 0% Read and 100% Write. In order to change this the HP Arracy Configuration Utility, CLI version needs to be installed. Changing the Accelerator Ratio allows the array installed on the HP Smart Arrary Controller to adjust how it priotizes reads and writes.

mysubmit.pl

This perl script is used to ensure that for a system with N cores the first N/2 benchmark copies are bound to a core that does not share its L2 cache with any of the other copies. The script does this by retrieving and using CPU data from /proc/cpuinfo. Note this script will only work for 6-core CPUs.

• Source
  ******************************************************************************************************
  #!/usr/bin/perl
  
  use strict;
  use Cwd;
  
  # The order in which we want copies to be bound to cores
  # Copies: 0, 1, 2, 3
  # Cores: 0, 1, 3, 6
  
  my $rundir = getcwd;
  
  my $copynum = shift @ARGV;
  
  my $i;
  my $j;
  my $tag;
  my $num;
  my $core;
  
  my @proc;
  my @cores;
  
  open(INPUT, "/proc/cpuinfo") or
  die "can't open /proc/cpuinfo\n";
  
  #open(OUTPUT, "STDOUT");
  
  # proc[i][0] = logical processor ID
  # proc[i][1] = physical processor ID
  # proc[i][2] = core ID
  
  $i = 0;
  
  while(<INPUT>)
  {
  chop;
  
  ($tag, $num) = split(/\s+:\s+/, $_);
  
  
  if ($tag eq "processor") {
  $proc[$i][0] = $num;
  }
  
  if ($tag eq "physical id") {
  $proc[$i][1] = $num;
  }
  
  if ($tag eq "core id") {
  $proc[$i][2] = $num;
  $i++;
  }
  }
  
  $i = 0;
  $j = 0;
  
  for $core (0, 4, 2, 1, 5, 3) {
  while ($i < 24) {
  if ($proc[$i][2] == $core) {
  $cores[$j] = $proc[$i][0];
  $j++;
  }
  $i++;
  }
  $i=0;
  }
  
  open RUNCOMMAND, "> runcommand" or die "failed to create run file";
  print RUNCOMMAND "cd $rundir\n";
  print RUNCOMMAND "@ARGV\n";
  close RUNCOMMAND;
  system 'taskset', '-c', $cores[$copynum], 'sh', "$rundir/runcommand";
  

ulimit -s [n | unlimited] (Linux)

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

KMP_STACKSIZE=integer[B|K|M|G|T] (Linux)

Sets the number of bytes to allocate for each parallel thread to use as its private stack. Use the optional suffix B, K, M, G, or T, to specify bytes, kilobytes, megabytes, gigabytes, or terabytes. The default setting is 2M on IA32 and 4M on IA64.

KMP_AFFINITY=physical,n (Linux)

Assigns threads to consecutive physical processors (for example, cores), beginning at processor n. Specifies the static mapping of user threads to physical cores, beginning at processor n. For example, if a system is configured with 8 cores, and OMP_NUM_THREADS=8 and KMP_AFFINITY=physical,2 are set, then thread 0 will mapped to core 2, thread 1 will be mapped to core 3, and so on in a round-robin fashion.

OMP_NUM_THREADS=n

This Environment Variable sets the maximum number of threads to use for OpenMP* parallel regions to n if no other value is specified in the application. This environment variable applies to both -openmp and -parallel (Linux) or /Qopenmp and /Qparallel (Windows). Example syntax on a Linux system with 8 cores:
export OMP_NUM_THREADS=8
Default is the number of cores visible to the OS.

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.

Firmware / BIOS / Microcode Settings

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 Hyperthreading Options (Default = Enabled):

This feature allows enabling/disabling of logical processor cores on processors supporting Intel's Hyper-Threading Technology. This option may improve overall performance for applications that will benefit from higher processor core count.

Power Regulator for ProLiant support (Default=HP Dynamic Power Savings Mode)

Values for this BIOS setting can be:

• HP Dynamic Power Savings Mode: Automatically varies processor speed and power usage based on processor utilization. Allows reducing overall power consumption with little or no impact to performance. Does not require OS support.
• HP Static Low Power Mode: Reduces processor speed and power usage. Guarantees a lower maximum power usage for the system. Performance impacts will be greater for environments with higher processor utilization.
• HP Static High Performance Mode: Processors will run in their maximum power/performance state at all times regardless of the OS power managment policy.
• OS Control Mode: Processors will run in their maximum power/ performance state at all times unless the OS enables' a power management policy.

HP Power Profile (Default = Balanced Power and Performance):

Values for this BIOS setting can be:

• Balanced Power and Performance: Provides the optimum settings to maximize power savings with minimal impact to performance for most Operating Systems and applications.
• Maximum Performance: Disables all power management options that may negatively affect performance.
• Minimum Power Usage: Enables power reduction mechanisms that may negatively affect performance. This mode will guarantee a lower maximum power usage by the system.
• Maximum Performance: Disables all power management options that may negatively affect performance.
• Custom:Allows the user to customize power management options independent of the defaults that each preset Power Profile sets. The HP Power Profile also will automatically change to this value if a power management option such as Energy/Performance Bias, Collaborative Power Control, or Processor Power and Utilization Monitoring is changed from the default value that is associated with one of the preset Power Profiles.

Power Efficiency Mode (Default=Efficiency)

Values for this BIOS setting can be:

• Efficiency: Maximize the power efficiency of the server.
• Performance: Maximize the performance of the server.
• Custom: Allows the user to customize power and performance related options individually.

Minimum Processor Idle Power Core State (Default (w/HP Power Profile=Maximum Performance)=No C-states):

This feature selects the processor's lowest idle core power state (C-state) which the operating system will utilize. The higher the C-State, the lower the power usage of that idle state (Core C6 is the lowest power idle core state supported by the processor). Values for this setting can be:

• C6 State: While in C6, the core PLLs are turned off, the core caches are flushed and the core state is saved to the Last Level Cache. Power Gates are used to reduce power consumption to close to zero. C6 is considered an inactive core.
• C3 State: While in C3 the core PLLs are turned off, and all the core caches are flushed. C3 is considred an inactive core.
• C1E State: C1E is defined as the enhanced halt state. While in C1E no instructions are being executed. C1E considered an active core.
• No C-states: No C-states is defined as C0, which is defined as the active state. While in C0, instructions are being executed by the core.

Minimum Processor Idle Power Package State (Default (w/HP Power Profile=Maximum Performance)=No Package state):

This feature selects the processor's lowest idle package power state (C-state) which is enabled. The proecessor will automatically transition into the package C-states based on the Core C-states which cores on the processor have transitioned to. The higher the package C-state, the lower the power usage of that idle package state (Package C6 (retention) is the lowed power idle package state supported by the processor). Values for this setting can be:

• Package C6 (retention) State: All cores have saved their architectural state and have had their core voltages reduced to zero volts. The LLC retains context, but no accesses can be made to the LLC in this state, the cores must break out to the internaal state package C2 for snoops to occur.
• Package C6 (non-retention) State: All cores have saved their architectural state and have had their core voltages reduced to zero volts. The LLC does not retain context, and no accesses can be made to the LLC in this state, the cores must break out to the internaal state package C2 for snoops to occur.
• No Package State: All cores are in an active state and have not entered any power saving state.

Energy/Performance Bias (Default = Balanced Performance):

This option configures several processor subsystems to optimize the processor's performance and power usage. Values for this BIOS setting can be:

• Maximum Performance Mode: Should be used for environments that require the highes performance and lowest latency but are not sensitive to power consumption.
• Balanced Performance: Provides optimum performance efficiency.
• Balanced Power: Provieds optimum power efficiency and is recommended for most environments.
• Power Savings Mode: Should only be used in environments that are power sensitive and are willing to accept reduced performance.

Collaborative Power Control (Default = Enabled):

This BIOS option allows the enabling/disabling of the Processor Clocking Controll (PCC) Interface, for operating systems which support this feature. Enabling this option allows the Operating System to request processor frequency changes even when the server has the Power Regulator option configured for Dynamic Power Savings Mode.

For Operating Systems that do not support the PCC Interface or when the Power Regulator Mode is not configured for Dynamic Power Savings Mode, this option has no impact on system operation.

Dynamic Power Capping Functionality (Default = Enabled):

This BIOS option allows the user to disable the System ROM Power Calibration feature that is executed during the boot process. When disabled, the user can expect faster boot times but will not be able to enable a Dynamic Power Cap until this feature is re-enabled.

Memory Power Savings Mode (Default = Balanced):

This option configures several memory parameters to optmizie the memory subsystems performance and power usage. Values for this BIOS setting can be:

• Balanced: Balanced provieds optimum power efficiency and is recommended for most environments.
• Maximum Performance: Maximum Performance Mode should be used for environments that require the highest performance and/or lowest latency but are not sensitive to power consumption.

Adjacent Sector Prefetch (Default = Enabled):

This BIOS option allows the enabling/disabling of a processor mechanism to fetch the adjacent cache line within an 128-byte sector that contains the data needed due to a cache line miss.

In some limited cases, setting this option to Disabled may improve performance. In the majority of cases, the default value of Enabled provides better performance. Users should only disable this option after performing application benchmarking to verify improved performance in their environment.

Hardware Prefetch (Default = Enabled):

This BIOS option allows allows the enabling/disabling of a processor mechanism to prefetch data into the cache according to a pattern recognition algorithm.

In some limited cases, setting this option to Disabled may improve performance. In the majority of cases, the default value of Enabled provides better performance. Users should only disable this option after performing application benchmarking to verify improved performance in their environment.

Data Reuse (Default = Enabled):

This BIOS option allows the enabling/disabling of the Data Reuse optimization.

Enabling this option reduces the frequency of L3 cache updates from the L1 cache. This may improve performance by reducing the internal bandwidth consumed by constantly updating L1 cache lines in the L3 cache.

Since this optimization results in more fetches to main memory, in some limited cases, setting this option to Disabled may improve performance. In the majority of cases, the default value of Enabled provides better performance. Users should only disable this option after performing application benchmarking to verify improved performance in their environment.

Turbo Mode (Default = Enabled):

Turbo Boost Technology is a processor feature which allows the processor to transition to a higher frequency than the processor's rate speed if the processor has available power headroom and is within tempereature specifications. Disabling this feature will reduce power usage but will reduce the system's maximum achievable performance under some workloads.

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:

• Optimal Cooling: Provides the most efficient solution by configuring fan speeds to the minimum required to provide adequate cooling.
• Increased Cooling: Will run fans at higher speeds to provide aditional cooling. Increased Cooling should be selected when non-HP storage controllers are cabled to the embedded hard drive cage, or if the system is experiencing thermal issues that cannot be resolved in another manner.
• Maximum Cooling: Will provide the maximum cooling available by this platform.

Defer All Transactions Mode (Default = Disabled):

When this option is enabled, front-side bus bandwidth may be increased on systems with heavy I/O workload because CPU initiated I/O transactions can be deferred enabling other transactions to make progress while data is retrieved. However, latency for completing transactions may also increase. The system's workload will determine which setting will provide highest performance.

Memory Speed with 2DPC (Default=1066MHz@1.35V)

Sets the memory speed and voltage setting for system when there are 2 DIMMs per channel (2DPC). Values for this BIOS setting can be:

• 1333MHz@1.5V
• 1066MHz@1.35V

SATA #1 Controller (Default=Auto)

Sets the mode for the embedded controller. The values for this BIOS setting can be:

• Disabled: Disables SATA controller
• Compatible: Sets controller to IDE Compatiblity mode
• RAID: Sets controller to RAID mode
• AHCI: Sets controller to Advanced Host Controller Interface mode

Processor Power and Utilization Monitoring (Default = Enabled):

This BIOS option allows allows the enabling/disabling of iLo4 Processor State Mode Switching and Insight Power Management Processor Utilization Monitoring.

When set to disabled, the system will also set the HP Power Regulator mode to HP Static High Performance mode and the HP Power Profile mode to Custom. This option may be useful in some environments that require absolute minimum latency.