This document provides some frequently asked questions about SiSoft Sandra. Please read the Help File as well!
Q: What is the Dhrystone benchmark?
A: The original Dhrystone benchmark is still widely used to measure CPU performance in industry under various versions/variants. The benchmark is designed to contain a representative sample of types of operations, mostly numerical, used by applications. Unfortunately this does not always represent a true real-life performance, but is useful to compare the speed of various CPUs.
The Dhrystone benchmark used here is a 32-bit variant of the original one which runs under UNIX. The result is determined by measuring the time it takes to perform some sequences of instructions. Due to various changes, the result is not directly comparable with other Dhrystone benchmarks. However the MIPS (Million Instructions Per Second) should be the same for the same system (+5-10% variation) between benchmarks.
While the original benchmark does not compute anything, this version does check the results with the expected ones just in case there are problems with the CPU/memory.
Q: What is the Whetstone benchmark?
A: The Whetstone benchmark is widely used in the computer industry as a measure of FPU or Co-Processor performance. Floating-point arithmetic is most significant in programs that require a Co-Processor. These are mostly scientific, engineering, statistical and computer-aided design programs.
The Whetstone benchmark used here is a 32-bit variant of the original one which runs under UNIX. The result is determined by measuring the time it takes to perform some sequences of floating-point instructions. Due to various changes, the result is not directly comparable with other Whetstone benchmarks. However the MFLOPS (Million FLoating OPerations per Second) should be the same for the same system (+5-10% variation) between benchmarks.
Q: Why does the rating vary between sequential runs?
A: On most systems, the value of the rating shouldn't change by more than about +5 percent from run to run. On systems with limited memory it may vary by +10 percent due to memory swapping. If you're seeing variations higher than this, some hardware or software is probably to blame. Do note that "limited memory" depends on operating system, installed drivers, running programs, etc. A badly configured system with 32MB may be worse memory-wise than an 8MB system...
Software Causes:
Hardware Causes:
Q: Why does the rating vary between random runs?
A: You may find that running the program straight after Windows loads you get a higher benchmark rating than after running and closing programs. This should not happen in practice very often, but it does sometimes.
Software Causes:
Hardware Causes:
Q: The CPU benchmark scores in Sandra version 4.20 and later are higher than in the older versions!
A: All scores were calibrated in later releases to make them "compatible" with Wintune 98.
Q: Are the tests in the CPU Multi-Media Benchmark optimised for a specific CPU?
A: Yes, the tests are optimised as far as possible but without introducing instructions that would generate large penalties on other processors. Here is the breakdown:
Q: My AMD K6-2 with 3DNow! barely beats a P6's FPU! Is the test flawed?
Q: My Pentium III with SSE barely beats a P6's FPU! Is the test flawed?
A: No. While 3DNow!/SSE can execute a maximum 4 operations per clock, a P6's super-pipelined FPU can reach 2. Most programs cannot be written to run 4x using 3DNow!/SSE since other operations must also be executed. A K6-2 using 3DNow! beats a PII by 40% in our test at the same clock speed. This is a 210% (3.2x times) improvement over the K6-2's FPU score. A Pentium III beats a PII by 50% in our test at the same clock speed.
Q: Why does the MMX test run faster than the 3DNow! or SSE tests?
A: MMX uses integer data and can execute the same number of operations per clock as SSE or 3DNow! Since it is much faster to work with integer numbers, the test yields higher scores. Generally MMX is 60% faster than SSE or 3DNow!
Q: How much faster is MMX on a P5 class CPU in the CPU Multi-Media Benchmark?
A: The MMX test runs about 180% (i.e. more than 2.8x) faster than the ALU test. It is 193% (i.e. 3x) faster than the FPU test.
Q: How much faster is 3DNow! on a K6 class CPU in the CPU Multi-Media Benchmark?
A: The 3DNow! test runs about 210% (i.e. more than 3.2x) faster than the FPU test.
Q: My Cyrix 6x86, 6x86MX or AMD K5, K6 get very low FPU scores!
A: The built-in FPU in these processors is not pipelined like those in Intel CPUs (e.g. Pentium, Pentium Pro, PII). The actual FPU performance is roughly on a par with a Pentium running at the same clock rate and therefore are lower than the performance rating. This is a non-issue unless you run heavily dependent FPU programs like ray-tracing or games like Quake, Quake II, Half-Life, Heretic II, etc.