We are adding new benchmarks using popular / "de facto" algorithms used in their respective fields in order to give you a broader view of the tested device's performance. That does not mean we are abandoning the "synthetic" tests but giving you more choices.

The new benchmarks launched today are the first (we're not waiting for major new versions like other ISVs) not the last - watch for the next service pack(s)! more...

Download & Buy

Measures the transaction throughput of the memory sub-system using different locks and update algorithms. It shows the improvement the new transactional synchronisation extensions (TSX: HLE and RTM of Intel Haswell and future AMD CPUs) bring to locking mechanisms that are used in modern multithreaded operating systems and applications. more...

Download & Buy

While Sandra has been updated for the brand-new Windows 8 / Server 2012 operating systems, we have not forgotten Windows 7, Vista or XP users - all new features and enhancements are supported on all operating systems.

As SiSoftware operates a "just-in-time" release cycle, some features were introduced in Sandra 2012 service packs: in Sandra 2013 they have been updated and enhanced based on all the feedback received. more...

Download & Buy

Compute Shader/DirectCompute is a new programmable shader stage introduced with DirectX 11 that expands Direct3D beyond graphics programming. We believe Compute Shader/DirectCompute will become "the standard" for programming parallel workloads in Windows, thus we have ported all our GPGPUs benchmarks to DirectX 11 Compute Shader/DirectCompute. more...

OpenCL is an open standard for running parallel tasks on GPUs, CPUs and hardware accelerators using the same code - unlike proprietary solutions. We believe OpenCL will become "the standard" for programming parallel workloads in the future, thus we have ported all our GPGPUs benchmarks to OpenCL. more...