CPU2017 Flag Description
Oracle Corporation 1-Chip VM with SPARC M7
| Compilers |
Oracle Solaris Studio 12.5
- "cc": Oracle Developer Studio C
- "CC": Oracle Developer Studio C++
- "f95": Oracle Developer Studio Fortran
|
| Operating systems: |
Solaris 10 and 11 |
| Copyright: |
The text for many of the descriptions below was excerpted from the Oracle Developer Studio Compiler
Documentation, which is copyright © 2016 Oracle Corporation. The original documentation can be found at http://docs.oracle.com/.
|
Base Optimization Flags
-
-
-
-
-
- -xipo=2
![[user]](https://www.spec.org/auto/cpu2017/images/user.png)
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
-
-
-
-
-
-
-
-
-
- -xipo=2
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
-
-
- -g
- oracle_studio_cc,oracle_studio_f90,oracle_studio_CC
- EXTRA_CXXFLAGS
-
Includes symbols in the executable. If the optimization level is -xO3 or lower, some optimizations may be
disabled when -g is present. At -xO4 or higher, full optimization is performed, even when -g is present.
-
-
-
-
-
-
- -xipo=2
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
-
-
-
-
-
-
-
-
- -xipo=2
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
-
-
-
-
-
-
-
-
-
-
- -xipo=2
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
-
-
-
-
- -g
- oracle_studio_cc,oracle_studio_f90,oracle_studio_CC
- EXTRA_CXXFLAGS
-
Includes symbols in the executable. If the optimization level is -xO3 or lower, some optimizations may be
disabled when -g is present. At -xO4 or higher, full optimization is performed, even when -g is present.
-
-
-
-
-
-
-
-
-
- -xipo=2
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
-
-
-
-
- -g
- oracle_studio_cc,oracle_studio_f90,oracle_studio_CC
- EXTRA_CXXFLAGS
-
Includes symbols in the executable. If the optimization level is -xO3 or lower, some optimizations may be
disabled when -g is present. At -xO4 or higher, full optimization is performed, even when -g is present.
-
Peak Optimization Flags
-
-
-
-
-
- -xipo=2
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
-
- -xprefetch_level=2
- OPTIMIZE
-
Control the level of searching that the compiler does for prefetch opportunities by setting n to 1, 2, or 3,
where higher numbers mean to do more searching. The default for Oracle Solaris Studio C and Oracle Solaris Studio C++ is 1.
The default for Oracle Solaris Studio Fortran is 2.
-
-
-
-
-
-
-
-
-
- -xprefetch_level=2
- OPTIMIZE
-
Control the level of searching that the compiler does for prefetch opportunities by setting n to 1, 2, or 3,
where higher numbers mean to do more searching. The default for Oracle Solaris Studio C and Oracle Solaris Studio C++ is 1.
The default for Oracle Solaris Studio Fortran is 2.
-
-
- -xprofile=collect:./feedback
- PASS1_OPTIMIZE
-
Collect profile data for feedback-directed optimization. If an option directory is named, the feedback will be stored
there.
When FDO is used, the training run gathers information regarding execution paths and data values. Hardware performance
counters are not used. FDO improves existing optimizations but does not introduce new classes of optimization.
-
-
-
-
-
-
-
-
- -xipo=2
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
-
-
- -xprofile=collect:./feedback
- PASS1_OPTIMIZE
-
Collect profile data for feedback-directed optimization. If an option directory is named, the feedback will be stored
there.
When FDO is used, the training run gathers information regarding execution paths and data values. Hardware performance
counters are not used. FDO improves existing optimizations but does not introduce new classes of optimization.
-
-
-
-
-
-
-
-
- -xipo=1
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
-
-
- -xprofile=collect:./feedback
- PASS1_OPTIMIZE
-
Collect profile data for feedback-directed optimization. If an option directory is named, the feedback will be stored
there.
When FDO is used, the training run gathers information regarding execution paths and data values. Hardware performance
counters are not used. FDO improves existing optimizations but does not introduce new classes of optimization.
-
-
- oracle_studio_cc,oracle_studio_f90,oracle_studio_CC
- EXTRA_CXXFLAGS
-
Includes symbols in the executable. If the optimization level is -xO3 or lower, some optimizations may be
disabled when -g is present. At -xO4 or higher, full optimization is performed, even when -g is present.
-
-
-
-
-
-
- -xipo=2
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
- -xprefetch=no%auto
- OPTIMIZE
-
Control generation of prefetch instructions.
- auto enables automatic generation of prefetch instructions.
- no%auto disables automatic generation of prefetch instructions.
- explicit enables explicit prefetch macros.
- no%explicit disables explicit prefetch macros.
- -xprefetch=yes and -xprefetch are synonyms for -xprefetch=auto,explicit.
- -xprefetch=no is a synonym for -xprefetch=no%auto,no%explicit.
(Explicit prefetch macros are not used in the source code of the SPEC CPU2006 benchmarks; therefore, in the context
of CPU2006, -xprefetch=yes is effectively a synonym for -xprefetch=auto.)
-
-
- -xprofile=collect:./feedback
- PASS1_OPTIMIZE
-
Collect profile data for feedback-directed optimization. If an option directory is named, the feedback will be stored
there.
When FDO is used, the training run gathers information regarding execution paths and data values. Hardware performance
counters are not used. FDO improves existing optimizations but does not introduce new classes of optimization.
-
-
- oracle_studio_cc,oracle_studio_f90,oracle_studio_CC
- EXTRA_CXXFLAGS
-
Includes symbols in the executable. If the optimization level is -xO3 or lower, some optimizations may be
disabled when -g is present. At -xO4 or higher, full optimization is performed, even when -g is present.
-
-
-
-
-
- -xprefetch_level=2
- OPTIMIZE
-
Control the level of searching that the compiler does for prefetch opportunities by setting n to 1, 2, or 3,
where higher numbers mean to do more searching. The default for Oracle Solaris Studio C and Oracle Solaris Studio C++ is 1.
The default for Oracle Solaris Studio Fortran is 2.
-
- -xprofile=collect:./feedback
- PASS1_OPTIMIZE
-
Collect profile data for feedback-directed optimization. If an option directory is named, the feedback will be stored
there.
When FDO is used, the training run gathers information regarding execution paths and data values. Hardware performance
counters are not used. FDO improves existing optimizations but does not introduce new classes of optimization.
-
-
-
-
-
-
-
-
-
- -xprefetch_level=3
- OPTIMIZE
-
Control the level of searching that the compiler does for prefetch opportunities by setting n to 1, 2, or 3,
where higher numbers mean to do more searching. The default for Oracle Solaris Studio C and Oracle Solaris Studio C++ is 1.
The default for Oracle Solaris Studio Fortran is 2.
-
-
- -xprofile=collect:./feedback
- PASS1_OPTIMIZE
-
Collect profile data for feedback-directed optimization. If an option directory is named, the feedback will be stored
there.
When FDO is used, the training run gathers information regarding execution paths and data values. Hardware performance
counters are not used. FDO improves existing optimizations but does not introduce new classes of optimization.
-
-
-
-
-
-
-
-
-
- -xprefetch_level=2
- OPTIMIZE
-
Control the level of searching that the compiler does for prefetch opportunities by setting n to 1, 2, or 3,
where higher numbers mean to do more searching. The default for Oracle Solaris Studio C and Oracle Solaris Studio C++ is 1.
The default for Oracle Solaris Studio Fortran is 2.
-
-
- -xprofile=collect:./feedback
- PASS1_OPTIMIZE
-
Collect profile data for feedback-directed optimization. If an option directory is named, the feedback will be stored
there.
When FDO is used, the training run gathers information regarding execution paths and data values. Hardware performance
counters are not used. FDO improves existing optimizations but does not introduce new classes of optimization.
-
-
-
-
-
-
-
-
-
-
-
-
-
- -xipo=1
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
-
-
-
- -xprofile=collect:./feedback
- PASS1_OPTIMIZE
-
Collect profile data for feedback-directed optimization. If an option directory is named, the feedback will be stored
there.
When FDO is used, the training run gathers information regarding execution paths and data values. Hardware performance
counters are not used. FDO improves existing optimizations but does not introduce new classes of optimization.
-
-
-
- oracle_studio_cc,oracle_studio_f90,oracle_studio_CC
- EXTRA_CXXFLAGS
-
Includes symbols in the executable. If the optimization level is -xO3 or lower, some optimizations may be
disabled when -g is present. At -xO4 or higher, full optimization is performed, even when -g is present.
-
-
-
-
-
-
-
-
- -xipo=2
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
- -xprofile=collect:./feedback
- PASS1_OPTIMIZE
-
Collect profile data for feedback-directed optimization. If an option directory is named, the feedback will be stored
there.
When FDO is used, the training run gathers information regarding execution paths and data values. Hardware performance
counters are not used. FDO improves existing optimizations but does not introduce new classes of optimization.
-
-
-
- oracle_studio_cc,oracle_studio_f90,oracle_studio_CC
- EXTRA_CXXFLAGS
-
Includes symbols in the executable. If the optimization level is -xO3 or lower, some optimizations may be
disabled when -g is present. At -xO4 or higher, full optimization is performed, even when -g is present.
-
-
-
-
-
-
-
-
- -xipo=2
- OPTIMIZE
-
Perform optimizations across all object files in the link step:
- 0 = off
- 1 = on
- 2 = performs whole-program detection and analysis.
At -xipo=2, the compiler performs inter-procedural aliasing analysis as well as optimization of memory allocation and
layout to improve cache performance.
-
-
- -g
- oracle_studio_cc,oracle_studio_f90,oracle_studio_CC
- EXTRA_CXXFLAGS
-
Includes symbols in the executable. If the optimization level is -xO3 or lower, some optimizations may be
disabled when -g is present. At -xO4 or higher, full optimization is performed, even when -g is present.
Base Other Flags
-
- -xjobs=64
- CC, LD
-
Specify the -xjobs option to set how many processes the compiler creates to complete its work. Currently,
-xjobs works only with the -xipo option. When you specify -xjobs=n, the interprocedural
optimizer uses n as the maximum number of code generator instances it can invoke to compile different files.
-
-
- -xjobs=64
- CXX, LD
-
Specify the -xjobs option to set how many processes the compiler creates to complete its work. Currently,
-xjobs works only with the -xipo option. When you specify -xjobs=n, the interprocedural
optimizer uses n as the maximum number of code generator instances it can invoke to compile different files.
-
- -xjobs=64
- FC, LD
-
Specify the -xjobs option to set how many processes the compiler creates to complete its work. Currently,
-xjobs works only with the -xipo option. When you specify -xjobs=n, the interprocedural
optimizer uses n as the maximum number of code generator instances it can invoke to compile different files.
-
- -xjobs=64
- CC, FC, LD
-
Specify the -xjobs option to set how many processes the compiler creates to complete its work. Currently,
-xjobs works only with the -xipo option. When you specify -xjobs=n, the interprocedural
optimizer uses n as the maximum number of code generator instances it can invoke to compile different files.
-
-
- -xjobs=64
- CC, CXX, LD
-
Specify the -xjobs option to set how many processes the compiler creates to complete its work. Currently,
-xjobs works only with the -xipo option. When you specify -xjobs=n, the interprocedural
optimizer uses n as the maximum number of code generator instances it can invoke to compile different files.
-
-
- -xjobs=64
- CC, CXX, FC, LD
-
Specify the -xjobs option to set how many processes the compiler creates to complete its work. Currently,
-xjobs works only with the -xipo option. When you specify -xjobs=n, the interprocedural
optimizer uses n as the maximum number of code generator instances it can invoke to compile different files.
-
Peak Other Flags
-
- -xjobs=64
- CC, LD
-
Specify the -xjobs option to set how many processes the compiler creates to complete its work. Currently,
-xjobs works only with the -xipo option. When you specify -xjobs=n, the interprocedural
optimizer uses n as the maximum number of code generator instances it can invoke to compile different files.
-
-
- -xjobs=64
- CXX, LD
-
Specify the -xjobs option to set how many processes the compiler creates to complete its work. Currently,
-xjobs works only with the -xipo option. When you specify -xjobs=n, the interprocedural
optimizer uses n as the maximum number of code generator instances it can invoke to compile different files.
-
- -xjobs=64
- FC, LD
-
Specify the -xjobs option to set how many processes the compiler creates to complete its work. Currently,
-xjobs works only with the -xipo option. When you specify -xjobs=n, the interprocedural
optimizer uses n as the maximum number of code generator instances it can invoke to compile different files.
-
- -xjobs=64
- CC, FC, LD
-
Specify the -xjobs option to set how many processes the compiler creates to complete its work. Currently,
-xjobs works only with the -xipo option. When you specify -xjobs=n, the interprocedural
optimizer uses n as the maximum number of code generator instances it can invoke to compile different files.
-
-
- -xjobs=64
- CC, CXX, LD
-
Specify the -xjobs option to set how many processes the compiler creates to complete its work. Currently,
-xjobs works only with the -xipo option. When you specify -xjobs=n, the interprocedural
optimizer uses n as the maximum number of code generator instances it can invoke to compile different files.
-
-
- -xjobs=64
- CC, CXX, FC, LD
-
Specify the -xjobs option to set how many processes the compiler creates to complete its work. Currently,
-xjobs works only with the -xipo option. When you specify -xjobs=n, the interprocedural
optimizer uses n as the maximum number of code generator instances it can invoke to compile different files.
-
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.
-
-
-
-
-
-
-
-
-
- -xdepend
-
Analyze loops for inter-iteration data dependencies, and do loop restructuring.
Loop restructuring includes loop interchange, loop fusion,
scalar replacement, and elimination of "dead" array assignments.
-
-
-
-
- -xtarget=native
-
Selects options for architecture, chip timing, and cache sizes. These can also be controlled separately, via
-xarch, -xchip, and -xcache, respectively. A wide variety of targets can be selected, including
ultra3, ultra3cu, ultra3i, ultra3iplus, ultra4, ultra4plus, ultraT1, ultraT2, sparc64vi. In each case, appropriate options
are selected for architecture, chip timing, and cache size to match that target.
If -xtarget=native is selected, options that are appropriate for the system where the compile is being done.
The default is -xtarget=generic, which sets the parameters for the best performance over most 32-bit platform
architectures.
On Solaris SPARC systems, the default pointer size with -xtarget=native is 32-bit.
- Includes:
-
-
- -xcache=...
-
xcache defines the cache properties for use by the optimizer. It can specify
use of default assumptions ("generic"); use of whatever the compiler can assume
about the current platform ("native"); or an explicit description of up to three
levels of cache, using colon-separated specifiers of the form si/li/ai[/ti],
where:
- si is the size of the cache, in kb
- li is the line size, in bytes
- ai is the associativity
- ti (optional) is the number of hardware threads share the cache
-
-
-
- -depend
- oracle_studio_f90
-
Synonym for -xdepend.
- Includes:
-
-
-
submit=echo 'pbind -b...' > dobmk; sh dobmk (SPEC tools, Unix shell)
When running multiple copies of benchmarks, the SPEC config file feature submit is often used to
cause individual jobs to be bound to specific processors. If so, the specific command may be found in the config file; here
is a guide to understanding that command:
- submit= causes the SPEC tools to use this line when submitting jobs.
- echo ...> dobmk causes the generated commands to be written to a file, namely
dobmk.
pbind -b causes this copy's processes to be bound to the CPU specified by the expression that
follows it. See the config file used in the submission for the exact syntax, which tends to be cumbersome because of
the need to carefully quote parts of the expression. When all expressions are evaluated, the jobs are typically
distributed evenly across the system, with each chip running the same number of jobs as all other chips, and each core
running the same number of jobs as all other cores.
The pbind expression may include various elements from the SPEC toolset and from standard Unix commands, such as:
- $BIND: a reference to a value from the bind line, a line of the form
"bind = n n n n", where each "n" is a processor number. See
http://www.spec.org/cpu2006/docs/config.html#bind
for details on this feature.
- $$: the current process id
- $SPECCOPYNUM: the SPEC tools-assigned number for this copy of the benchmark.
- psrinfo: find out what processors are available
- grep on-line: search the psrinfo output for information regarding on-line cpus
- expr: Calculate simple arithmetic expressions. For example, the effect of binding jobs to a
(quote-resolved) expression such as:
expr ( $SPECCOPYNUM / 4 ) * 8 + ($SPECCOPYNUM % 4 ) )
would be to send the jobs to processors whose numbers are:
0,1,2,3, 8,9,10,11, 16,17,18,19 ...
- awk...print \$1: Pick out the line corresponding to this copy of the benchmark and use the CPU
number mentioned at the start of this line.
- sh dobmk actually runs the benchmark.
This result has been formatted using multiple flags files.
The "sw environment" from each of them appears next.
Sw environment from Oracle-Solaris-Studio12.5
Oracle Solaris SPEC CPU Flags
MTEXCLUSIVE
If set to "Y", additional memory allocation buckets will be created, so that threads will not need to share buckets
unless more than 2*NCPUS threads are created. This variable is used by mtmalloc.
SUNW_MP_PROCBIND
Binds threads in an OpenMP program to the virtual processors enumerated in the assignment. Can also be set to TRUE,
which casues threads to be bound in a round-robin fashion.
SUNW_MP_THR_IDLE
Specifies whether idle threads should SLEEP or SPIN.
STACKSIZE=<n>
Set the size of the stack (temporary storage area) for each slave thread of a multithreaded program.
ulimit -s <n>
Sets the stack size to n kbytes, or "unlimited" to allow the stack size to grow without limit.
Note that the "heap" and the "stack" share space; if your application allocates large amounts of memory on the heap,
then you may find that the stack limit should not be set to "unlimited". A commonly used setting for SPEC CPU2006 purposes
is a stack size of 128MB (131072K).
Sw environment from Oracle-SPARC
Oracle SPARC Series Platform File
LD_LIBRARY_PATH=<directories>
LD_LIBRARY_PATH controls the search order for both the compile-time and run-time linkers. Usually, it can be
defaulted; but testers may sometimes choose to explicitly set it (as documented in the notes in the submission), in order to
ensure that the correct versions of libraries are picked up.
MADV=access_lwp and LD_PRELOAD=madv.so.1
When the madv.so.1 shared object is present in the LD_PRELOAD list, it is possible to provide advice to the system
about how memory is likely to be accessed. The advice present in MADV applies to all processes and their descendants. A
commonly used value is access_lwp, which means that when memory is allocated, the next process to touch it will be
the primary user. Examples of other possible values include sequential, for memory that is used only once and
then no longer needed and acces_many when many processes will be sharing data.
MPSSHEAP=<size>, MPSSSTACK=<size>, and
LD_PRELOAD=mpss.so.1
When these variables are set, the mpss.so.1 shared object will set the preferred page size for new processes, and their
descendants, to the requested sizes for the heap and stack.
Platform settings
One or more of the following settings may have been applied to the testbed. 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.
autoup=<n> (Unix /etc/system)
When the file system flush daemon fsflush runs, it writes to disk all modified file buffers that are more
than n seconds old.
bufhwm=<n> (Unix /etc/system)
Sets the upper limit of the file system buffer cache. The units for bufhwm are in kilobytes.
cpu_bringup_set=<n> (Unix /etc/system)
Specifies which processors are enabled at boot time. <n> represents a bitmap of the
processors to be brought online.
poweradm set administrative-authority=none (Unix, superuser commands)
Solaris power management settings are determined by an 'administrative-authority'. When the authority is set to
'none', Solaris does not attempt to manage power.
psrset -c <n> (Unix, superuser commands)
Creates a new processor set and displays the new processor set ID.
psrset -e <n> (Unix, superuser commands)
Executes a command (with optional arguments) in the specified processor set.
The command process and any child processes are executed only by processors in the processor set.
segmap_percent=<n> (Unix /etc/system)
This value controls the size of the segmap cache as a percent of total memory. Set this value to help keep the file system cache from consuming memory unnecessarily.
STACKSIZE=<n> (Unix environment variable)
Set the size of the stack (temporary storage area) for each slave thread of a multithreaded program.
svcadm disable webconsole (Unix, superuser commands)
Turns off the Sun Web Console, a browser-based interface that performs systems management.
If it is enabled, system administrators can manage systems, devices and services from remote systems.
ts_dispatch_extended=<n> (Unix /etc/system)
Controls which dispatch table is loaded upon boot. A value of 1 loads the large system table, a value of 0 loads the regular system table.
tune_t_fsflushr=<n> (Unix /etc/system)
Controls the number of seconds between runs of the file system flush daemon, fsflush.
user_reserve_hint_pct=<n> (Unix /etc/system)
Informs the system about how much memory is expected
to be used by applications (as a percentage).
Virtualization in SPARC systems
SPARC systems provide virtualization capabilities at several levels:
- Zones, created by Solaris
- Logical domains (LDoms), created by Oracle VM Server for SPARC
- Physical domains (PDoms), created by the Service Processor
At the time of release of SPEC CPU2017, Oracle submitted results to SPEC for a
1-Chip VM with SPARC M7
which used 2 of the above technologies, namely LDoms and PDoms. The example shown here is that system.
From the point of view of the VM
A SUT (System Under Test) using Oracle VM Server for SPARC is able to accurately inventory cores and virtual processors using
ordinary Solaris commands.
In this example system, there are 256 cpus, 32 cores, 1 chip:
$ hostname
m7-16-002c-ld3
$
$ pkg info entire | grep Version
Version: 0.5.11 (Oracle Solaris 11.3.10.5.0)
$
$ psrinfo -pv
The physical processor has 32 cores and 256 virtual processors (0-255)
The core has 8 virtual processors (0-7)
The core has 8 virtual processors (8-15)
The core has 8 virtual processors (16-23)
The core has 8 virtual processors (24-31)
The core has 8 virtual processors (32-39)
The core has 8 virtual processors (40-47)
The core has 8 virtual processors (48-55)
The core has 8 virtual processors (56-63)
The core has 8 virtual processors (64-71)
The core has 8 virtual processors (72-79)
The core has 8 virtual processors (80-87)
The core has 8 virtual processors (88-95)
The core has 8 virtual processors (96-103)
The core has 8 virtual processors (104-111)
The core has 8 virtual processors (112-119)
The core has 8 virtual processors (120-127)
The core has 8 virtual processors (128-135)
The core has 8 virtual processors (136-143)
The core has 8 virtual processors (144-151)
The core has 8 virtual processors (152-159)
The core has 8 virtual processors (160-167)
The core has 8 virtual processors (168-175)
The core has 8 virtual processors (176-183)
The core has 8 virtual processors (184-191)
The core has 8 virtual processors (192-199)
The core has 8 virtual processors (200-207)
The core has 8 virtual processors (208-215)
The core has 8 virtual processors (216-223)
The core has 8 virtual processors (224-231)
The core has 8 virtual processors (232-239)
The core has 8 virtual processors (240-247)
The core has 8 virtual processors (248-255)
SPARC-M7 (chipid 3, clock 4133 MHz)
$
From the point of view of the Host
Oracle VM Server for SPARC manages Logical Domains using the ldm command.
From its point of view, the example SUT just above is ld3, which uses CMIOU11 (Chip/Memory/IO Unit #11).
# hostname
m7-16-002c
# pkg info entire | grep Version:
Version: 0.5.11 (Oracle Solaris 11.3.5.1.0)
# ldm --version
Logical Domains Manager (v 3.3.0.1.4)
Hypervisor control protocol v 1.12
Using Hypervisor MD v 1.4
System PROM:
Hostconfig v. 1.6.2.b @(#)Hostconfig 1.6.2.b 2015/12/07 09:05
Hypervisor v. 1.15.2.a @(#)Hypervisor 1.15.2.a 2015/11/20 04:45
OpenBoot v. 4.38.2 @(#)OpenBoot 4.38.2 2015/10/30 13:09
# ldm list
NAME STATE FLAGS CONS VCPU MEMORY UTIL NORM UPTIME
primary active -n-cv- UART 256 489984M 0.1% 0.1% 7d 2h 38m
ld1 active -n---- 5001 256 489984M 0.1% 0.1% 7d 2h 38m
ld2 active -n---- 5002 256 489984M 0.0% 0.0% 7d 2h 38m
ld3 active -n---- 5003 256 489984M 0.0% 0.0% 3d 8h 45m
# ldm list-rsrc-group -l -o mem,core /SYS/CMIOU11
NAME
/SYS/CMIOU11
CORE
CID BOUND
704, 705, 706, 707, 712, 713, 714, 715 ld3
720, 721, 722, 723, 728, 729, 730, 731 ld3
736, 737, 738, 739, 744, 745, 746, 747 ld3
752, 753, 754, 755, 760, 761, 762, 763 ld3
MEMORY
PA SIZE BOUND
0x580050000000 489984M ld3
0x5877f0000000 64M _sys_
0x5877f4000000 192M _sys_
#
From the point of view of the Service Processor
Using the Service Processor, a system administrator defines Physical Domains (PDoms).
In the example system, there is one Physical Domain per DCU (Domain Configurable Unit).
CMIOU11 is part of DCU2, which is assigned to HOST2.
-> show /SP system_description
/SP
Properties:
system_description = SPARC M7-16, ILOM v3.2.5.8.g, r105871
-> show /System system_fw_version
/System
Properties:
system_fw_version = Sun System Firmware 9.5.2.g 2015/12/07 11:57
-> show HOST2 dcus_assigned
/HOST2
Properties:
dcus_assigned = /SYS/DCU2
-> show /SYS/DCU2 members
/SYS/DCU2
Properties:
members = /SYS/CMIOU8/CM/CMP /SYS/CMIOU9/CM/CMP /SYS/CMIOU10/CM/CMP
/SYS/CMIOU11/CM/CMP
->
The service processor is able to show many details about the hardware
For the system discussed in this example, CMIOU11
has 16 memory DIMMs, each of which has 32 GB.
[Output was edited to reduce white space]
-> show /SYS/CMIOU11/CM/CMP fru_name -t -format nowrap
Target | Property | Value
-----------------------------------+------------------+--------------------------
/SYS/CMIOU11/CM/CMP | fru_name | Oracle SPARC M7
/SYS/CMIOU11/CM/CMP/BOB00/CH0/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB00/CH1/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB01/CH0/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB01/CH1/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB10/CH0/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB10/CH1/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB11/CH0/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB11/CH1/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB20/CH0/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB20/CH1/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB21/CH0/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB21/CH1/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB30/CH0/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB30/CH1/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB31/CH0/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
/SYS/CMIOU11/CM/CMP/BOB31/CH1/DIMM | fru_name | 32768MB DDR4 SDRAM DIMM
-> show /SYS/CMIOU11/CM/CMP fru_manufacturer -t -format nowrap
Target | Property | Value
-----------------------------------+------------------+--------------------------
/SYS/CMIOU11/CM/CMP | fru_manufacturer | Oracle Corporation
/SYS/CMIOU11/CM/CMP/BOB00/CH0/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB00/CH1/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB01/CH0/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB01/CH1/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB10/CH0/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB10/CH1/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB11/CH0/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB11/CH1/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB20/CH0/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB20/CH1/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB21/CH0/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB21/CH1/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB30/CH0/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB30/CH1/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB31/CH0/DIMM | fru_manufacturer | Samsung
/SYS/CMIOU11/CM/CMP/BOB31/CH1/DIMM | fru_manufacturer | Samsung
-> show /SYS/CMIOU11/CM/CMP fru_part_number -t -format nowrap
Target | Property | Value
-----------------------------------+------------------+--------------------------
/SYS/CMIOU11/CM/CMP/BOB00/CH0/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB00/CH1/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB01/CH0/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB01/CH1/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB10/CH0/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB10/CH1/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB11/CH0/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB11/CH1/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB20/CH0/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB20/CH1/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB21/CH0/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB21/CH1/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB30/CH0/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB30/CH1/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB31/CH0/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
/SYS/CMIOU11/CM/CMP/BOB31/CH1/DIMM | fru_part_number | 07075400,M393A4K40BB1-CRC
->
For more information
See:
www.oracle.com/technetwork/server-storage/sun-sparc-enterprise/documentation/sparc-t7-m7-server-architecture-2702877.pdf
Power management policy (Integrated Lights Out Manager, ILOM)
The power management settings available from the ILOM menus, and their meanings, are:
- Disabled - All components run at full speed/capacity.
- Performance - Components may be put to sleep when system usage allows it. Power management
assumes that the system usage may change quickly, and that components may need to be quickly re-enabled.
- Elastic - As with the previous option, components may be put to sleep. Power management is
allowed to assume that system usage will change in a more gradual manner, thus allowing deeper sleep states across
more components.
For questions about the meanings of these flags, please contact the tester.
For other inquiries, please contact info@spec.org
Copyright 2017-2020 Standard Performance Evaluation Corporation
Tested with SPEC CPU2017 v0.903.0.
Report generated on 2020-01-15 19:45:01 by SPEC CPU2017 flags formatter v5178.
![[benchmark]](https://www.spec.org/auto/cpu2017/images/benchmark.png)
![[suite]](https://www.spec.org/auto/cpu2017/images/suite.png)