All around tool, benchmarking, system diagnostic and analyser.

SiSoftware Sandra (the System ANalyser, Diagnostic and Reporting Assistant) is an information & diagnostic utility. It should provide most of the information (including undocumented) you need to know about your hardware, software and other devices whether hardware or software. Sandra is a (girl) name of Greek origin that means "defender", "helper of mankind". We think that's quite fitting.

It works along the lines of other Windows utilities, however it tries to go beyond them and show you more of what's really going on. Giving the user the ability to draw comparisons at both a high and low-level. You can get information about the CPU, chipset, video adapter, ports, printers, sound card, memory, network, Windows internals, AGP, PCI, PCIe, ODBC Connections, USB2, 1394/Firewire, etc.

Native Unicode ports for 32-bit Windows (2000/XP/2003/Vista), 64-bit & x64 Windows (XP/2003/Vista) as well as Windows CE (Pocket PC 2002/2003/2003SE, Smart Phone 2002/2003/2003SE, CE .Net 4.20) are available.

General Sandra Information

Here are the version types, in line with industry standards:

• Sandra Lite (free for personal/educational use - no nag screens, time limit, etc.)
• Sandra Advanced (for OEMs)
• Sandra Professional (commercial)
• Sandra Engineer (commercially exploitabile)
• Sandra Enterprise (commercial)
• Sandra Legacy (home enthusiast)

List of SiSoftware Sandra Modules:

Here is a list of current modules:

• System Summary
• Mainboard/Chipset/System Monitors Info
• CPU/BIOS Info
• APM & ACPI (Advanced Power Management) Info
• PCI(e), AGP, CardBus, PCMCIA bus and devices Info
• Video Information (monitor, card, video bios, caps, etc.)
• OpenGL Information
• DirectX (DirectDraw, Direct3D, DirectSound (3D), DirectMusic, DirectPlay, DirectInput) Info
• Keyboard Info
• Mouse Info
• Sound Card (wave, midi, aux, mix) Info
• MCI Devices (mpeg, avi, seq, vcr, video-disc, wave) Info
• Joystick Info
• Printers Info
• Windows Memory Info
• Windows Info
• Font (Raster, Vector, TrueType, OpenType) Information
• Modem/ISDN TA Information
• Network Information*
• IP Network Information*
• WinSock & Internet Security Information
• Drives Information (Removable Hard Disks, CD-ROM/DVD, RamDrives, etc.)
• Ports (Serial/Parallel) Info
• Remote Access Service Connections (Dial-Up, Internet)*
• OLE objects/servers Info*
• Processes (Tasks) & Threads Info
• Modules (DLL, DRV) Info
• Services & Device Drivers (SYS) Info*
• SCSI Information*
• ATA/ATAPI Information
• Data Sources Information*
• CMOS/RTC Information*
• Smart Card & SIM Card Information*
• CPU Arithmetic Benchmark (MP/MT support)
• CPU Multi-Media Benchmark (including MMX, MMX Enh, 3DNow!, 3DNow! Enh, SSE(2)) (MP/MT support)
• File System (Removable, Hard Disks, Network, RamDrives) Benchmark
• Removable Storage/Flash Benchmark
• CD-ROM/DVD Benchmark
• Memory Bandwidth Benchmark (MP/MT support)
• Cache & Memory Bandwidth Benchmark (MP/MT support)
• Network/LAN Bandwidth Benchmark
• Internet/ISP Connection Benchmark
• Internet/ISP Peerage Benchmark
• Hardware Interrupts Usage*
• DMA Channel Usage*
• I/O Ports Usage*
• Memory Range Usage*
• Plug & Play Enumerator*
• Hardware registry settings
• Environment settings
• Registered File Types
• Key Applications(web-browser, e-mail, news, anti-virus, firewall, etc.)
• Installed Applications*
• Installed Programs*
• Start Menu Applications*
• On-disk Programs & Libraries*
• Installed Web Packages(ActiveX, Java classes)
• System Event Logs*
• Burn-in Wizard(test computer stability)
• Connect Wizard (connect to remote computers, PDAs, Smart Phones and other devices)
• Combined Performance Index Wizard (overall computer performance score)
• Create a Report Wizard (save, print, fax or e-mail in CIM (SMS/DMI), HTML, XML, RPT or TEXT format)
• Performance Tune-Up Wizard (tune-up computer)
• Environment Monitor Wizard (temperatures, voltages, fans, CPU power, cooling solution thermal resistance, etc.)
• WebUpdate Wizard for automatic version updating

What's New in version 2012:

Benchmark Results Certification

What is it? Certification uses the benchmark results submitted by users to work out whether your score (benchmark result) is valid (i.e. the device you tested is performing correctly) and how it compares to the scores obtained by other users when testing the same device.

By aggregating the scores submitted for each device and performing statistical analysis (e.g. computing mean/average, standard deviation, etc.) we can use statistical tools (e.g. normal distribution, Tdistribution, etc.) to work out whether the score is within the expected range (confidence intervals).

You can see whether the score is above/below average average, but also how significant the difference is. For some devices, +/10% is a lot; for others +/30% may be just fine. It depends.

Based on the variability of scores you can determine whether the performance of your device is consistent or varies significantly from test to test. A large variability would indicate a problem either with the device or your environment (e.g. OS device drivers, virus checkers, etc.) that should be addressed.

Ranker functionality must be enabled: the results get downloaded from the Ranker so if it is disabled, it cannot get the reference results for the device tested.

GeneralPurpose (GP) Computing benchmarks CPU vs. GP(GPU) vs. (GP)APU

Sandra's GP (former GPGPU) benchmarks may still be the only ones that allow full APU performance measurement against CPUs or even GP(GPU)s (through OpenCL) as they use the *same workloadas the native as well as the software VM (.Net/Java) counterparts allowing applestoapples comparisons:

• GP Performance (OpenCL / DX CS / CUDA) = CPU MultiMedia / .Net MultiMedia / Java MultiMedia / Video Shading
• GP Cryptography (OpenCL / DX CS / CUDA) = CPU Cryptography / .Net Cryptography / Java Cryptography
• GP Bandwidth (OpenCL / DX CS / CUDA) = Memory Bandwidth / Video Bandwidth

As a user, you would not care if a program uses native CPU instructions, the GP(GPU) or even your APU (CPU+GPU) to get your work done faster.

The point is you are benchmarking CPU+GPU together and not just CPU or GPU individually; both resources (thus the whole APU) is used to perform computations better which is the whole point.

As we support OpenCL, DirectX ComputeShader and CUDA just about all (GP)GPUs are supported.

System Overall benchmark Reloaded

What is it? The updated version generates an overall system performance score (geometric mean) based on the individual benchmarks that allows system2system comparisons:

• Native CPU performance: CPU Arithmetic, Multimedia
• Software VM performance: .NetArithmetic, .Net Multimedia
• Native Memory & Cache performance
• Storage performance
• GP(GPU/APU)*(General Purpose) performance: Arithmetic, Memory

Why .Net? While applications have already been ported to .Net and WPF (Windows Presentation Foundation) the trend is accelerating with the launch of Windows 8/Server 2012 where new applications will need to use the METRO environment.

*Why GP(GPU/APU)? With the recent introduction of APUs (CPU with builtin (GP)GPU) we believe most future applications will use both (CPU+GPU aka APU) simultaneously for best performance.

New Memory Latency Test: InPage Random Access Pattern

What is it? It is a new pattern that ensures the memory accesses stay "inpage" and thus we do not incur "outofpage" lantencies as we move beyond L1D and L2 caches. The latencies reported are thus "best case" rather than "worst case" and match the latencies reported by vendors (which are always "inpage"/"best case").

Our view is that if you are unlucky enough to miss both L1D/L2 you are unlikely to be "inpage" considering the native page size is just 4kB thus you are very much likely to be "outofpage". Even if using large pages (2MB but cannot easily be used in Windows, thus very few applications usually servers support them) considering most L2 caches are around this size you are still likely to be "outofpage" if you missed L2.

We believe in giving you a choice thus you can select either "inpage random access", "full random access" and "sequential access".

Thanks go to Michael Schuette (Lost Circuits) and Joel Hruska for their testing, advice and support.

Transcoding benchmark CPU vs. GP(GPU) vs. (GP)APU

The key advantage of Sandra's benchmark is WMF (Windows Media Foundation): it can use either software (CPU) transcoding, GP(GPU) (Intel/nVidia) or APU (AMD) transcoding depending on the encoders/decoders installed. So you can benchmark CPU vs. GP(GPU) or APU using the *same workload*.

Other benchmarks may use only software decoders/encoders which means you only test CPU performance and ignore GP(GPU) or APU performance entirely. Only by using the hardware accelerated decoders/encoders you can harness the power of GP(GPU) and APU.

Largepage support for all memory tests

Using largepages (2MB on x86/x64 Windows) instead of native pages (4kB) results in less outofpage hits and thus lower latencies. Unfortunately hugepages (1GB) are not currently supported by Windows and we do not know whether the Windows 8/Server 2012 will enable them.

FMA3 & FMA4 instruction set support for just released & future CPUs

Using 256bit register width (instead of 128bit of SSE/2/3/4) yields further performance gains through greater parallelism in most algorithms. Combined with the increase in processor cores and threads we will soon have CPUs rivaling GPGPUs in performance.

What's New in 18.30:

• GP (GPU/APU) Benchmarks: optimisations for APUs, both current AMD and future Intel when using complex kernels that overwhelm them. APU mode can run different kernels on CPU & GPU part, selecting the best for each device.
• Dedicated high-performance GPUs will still execute the "heavier" kernels which allow better compute core utilisation but are too large for APUs.
• File System Benchmark: reduced run-time and test file size while maintaining score quality (i.e. similar margin of error). You can test slow drives even on systems with large disk caches (i.e. large memory).
• Ranker: is finally operational after over 1 month outage due to server transfer gone wrong; most benchmark results have been restored. With 41 benchmarks and over 200,000 scores in popular benchmarks the total number or scores is somewhat large.
• Cache/Memory Latencies Benchmark: here is a public article detailing our methodology on measuring cache/memory latencies, why, what and how is measured, and how our results relate to manufacturer results.