New More Effective Tuning Methodology Supported
Pipeline stall accounting radically improves tuning by focusing the user on the instances of possible issues (like cache misses) which actually end up mattering. Core2 Duo and Core2 Quad processors have greatly enhanced performance analysis capabilities. These processors support more events, higher precision in event location correlation, and a new and wonderful pipeline stall accounting.
New Events for Tuning Multi-Core Intel Processors
New events measure parallelism, core sharing of the bus and cache, and modified data sharing by threads. These identify opportunities to improve threading, tune multi-core sharing of the bus and cache, and optimize cache-line usage.
Faster Call Graph
Selective Instrumentation for Java and Native Code Now you can selectively instrument Java or native code to improve runtime performance. By gathering data only on the modules being tuned, overhead is reduced and runtime is improved.
Supports the Latest Intel Processors
Supports the latest Intel quad-core processors
All Architectures:
Low Overhead
Accurately identify where the program spends time. Sampling is system wide with negligible overhead (typically less than 5 percent).
Find the Critical Path
Determine function calling sequences and find the critical path using Call Graph.
No Recompile Required
Unlike traditional instrumented profilers that make you recompile or modify your build script, just use your production executables.
Compatibility
VTune Performance Analyzer supports the latest Intel processors (Intel 64 architecture-based processors, Intel Itanium processors, multi-core processors...) and a wide variety of Linux* distributions.
Programming Language and Compiler Independent
VTune analyzer supports all compilers that follow industry standards (ELF, STABS, DWARF).
Mixed Java and Native Code
Unlike Java*-only analyzers, VTune analyzer tunes mixed Java and native code1.
Minimal Memory Footprint
Remote profiling minimizes the performance impact on the target system by running the user interface on a separate system.
Command Line Capability
Automate batch operations.
Large Applications Welcome
VTune analyzer is a robust solution even with large executables2. If you have a large application with hundreds of thousands of functions, bring it to VTune analyzer.
Listen to the Compiler's Advice
An optimizing compiler can do a lot better with just a few tips from you. We've integrated the Intel Compilers with VTune analyzer to make this easy and very effective.
Large Enterprise and HPC Systems:
Minimize Traffic in Non-uniform Memory Architecture (NuMA) Systems
By storing sampling data in local CPU memory. This is critical to avoid saturating the interconnect fabric and slowing the system under test.
Designed for High Performance Computing
Large High Performance Computing (HPC) systems have unique requirements supported by VTune analyzer.
- Multiple users can share a large system for simultaneous Call Graph performance analyses.
- Sampling is supported on systems with 128 or more3 processors using local buffering per CPU for minimum inter-node contention. To limit the amount of data collected we recommend selecting a maximum of 64 CPUs for simultaneous data collection.
Hardware Requirements
Memory
- Integrated Eclipse* Environment, Single System or Host Only:
512 MB of RAM
- Command Line or Target Only:
256 MB of RAM
When running your application with the Call Graph collector, it will require more memory than usual.
Disk Space
- Integrated Eclipse Environment, Single System or Host Only:
1 GB during installation
500 MB after installation
- Command Line or Target Only:
600 MB during installation
100 MB after installation
This varies greatly, but for a single or dual processor system, an additional 1 GB on the target system is a good starting point.
At least double the minimum RAM requirements.
Supported Processors
- Processor Requirements for Host (Eclipse* or command line interface)
IA-32 architecture-based processor - Intel Pentium 4 performance level or better
Intel 64 architecture-based processor or equivalent
Intel Itanium 2 processor
AMD Athlon* or Opteron* processor
- Processors Supported by Data Collector (Single and Remote Target Systems)
(Note: We are constantly adding new processors. Be sure you have the latest software - check for updates).
Intel Core 2 Quad processor
Intel Core 2 Duo processor
Intel Core 2 Extreme processor
Intel Core Duo processor
Intel Core Solo processor
Intel Pentium 4 processor
Intel Pentium 4 processor Extreme Edition
Intel Pentium 4 processor supporting Hyperthreading Technology
Intel Pentium 4 processor with Streaming SIMD Extensions 3 (SSE3)
Mobile Intel Pentium 4 processor - M
Intel Pentium D processor
Intel Pentium processor Extreme Edition
Intel Pentium M processor
Intel Celeron processor
Mobile Intel Celeron processor
Intel Celeron M processor
Intel Celeron D processor
Quad-Core Intel Xeon processor 5300 series
Quad-Core Intel Xeon processor 32xx series
Dual-Core Intel Xeon processor 5100 series
Dual-Core Intel Xeon processor 5300 series
Dual-Core Intel Xeon processor 30xx series
Intel Xeon processor MP
Dual-Core Intel Xeon processor 7100 series
64-bit Intel Xeon processor
Intel Xeon processor
Dual-Core Intel Itanium 2 processor 9000 sequence
Intel Itanium 2 processor
Low Voltage Intel Itanium 2 processor
Supported Linux Distributions (Host and Target)
Operating System
- Red Hat Enterprise Linux* 3.0 Update 8 (Kernel Version 2.4.21-47.EL) (IA-32 architecture, Intel 64 architecture, IA-64 architecture)
- Red Hat Enterprise Linux 4.0 Update 4 (Kernel Version 2.6.9-42.EL) (IA-32 architecture, Intel 64 architecture, IA-64 architecture)
- Red Hat Enterprise Linux 5 (Kernel Version2.6.9-42.EL) (IA-32 architecture, Intel 64 architecture, IA-64 architecture)
- Red Hat Fedora* Core 5 (Kernel Version 2.6.15-1.2054_FC5) (IA-32 architecture, Intel 64 architecture,)
- Red Hat Fedora* Core 6 (Kernel Version 2.6.18-1.2798.fc6) (IA-32 architecture, Intel 64 architecture,)
- SuSE Linux Enterprise Server* (SLES) 9.0 Service Pack 3 (Kernel Version 2.6.5-7.244) (IA-32 architecture, Intel 64 architecture, IA-64 architecture)
- SuSE Linux Enterprise Server (SLES) 10.0 (Kernel Version 2.6.16.21-0.8) (IA-32 architecture, Intel 64 architecture, IA-64 architecture)
- SuSE Linux 10 (Kernel Version2.6.13-15) (IA-32 architecture, Intel 64 architecture,)
- SGI Pro Pack* 4.0, Service Pack 3 (Kernel Version 2.6.5-7.244-sn2) (IA-64 architecture)
- SGI Pro Pack 5.0 (Kernel Version2.6.16.21-08) (IA-64 architecture)
- Red Flag Linux 5.0 (DataCenter) (Kernel Version 2.6.9-11.19AX) (IA-32 architecture, Intel 64 architecture, IA-64 architecture)
- Miracle Linux 4 (Kernel Version 2.6.9-11.19AX) (IA-32 architecture, Intel 64 architecture, IA-64 architecture)
- Haansoft Linux 2006 Server (Kernel Version 2.6.9-11.19AX) (IA-32 architecture, Intel 64 architecture, IA-64 architecture)
- Turbo Linux 10 (Kernel Version2.6.9-5.13) (IA-32 architecture, Intel 64 architecture, IA-64 architecture)
- Mandriva / Mandrake Linux 10.2 (Kernel Version 2.6.11-6mdk) (IA-32 architecture, Intel 64 architecture,)
- MontaVista Linux Carrier Grade Edition 4 (Kernel Version 2.6.10) (IA-32 archtecture - via Remote data collection only)
Software Requirements
Host Software Requirements for Graphical User Interface Integrated with Eclipse
- Eclipse Development Environment
Eclipse 3.2.1
- Supported Java* Development Kit (JDK)
BEA JRockit* 5.0
VTune Analyzer Has Been Tested for Profiling Under the Following JDKs
BEA JRockit* 1.4.2 and 5.0
Sun J2SE* 5.0
IBM JDK 1.4.2 and 1.5
BEA JRockit 5.0
Sun J2SE 5.0
BEA JRockit 1.4.2 and 5.0
IBM JDK 1.42
Java Tuning Support
VTune™ Performance Analyzer for Linux supports tuning Java 1.5 and JVMTI.
Web Browser Requirements
A modern 4.0 HTML-compliant web browser is required for reading documentation.