|↓||Skip to table of contents||↓|
|This is the talk page for discussing improvements to the AMD K5 article.|
|WikiProject Computing||(Rated C-class, Mid-importance)|
I don't think it is fair to call K5's implementation of branch prediction inferior. It's actually a very innovative design.
The prediction information is stored together with each cache line of the L1 cache. There're 2 perdictions per cache line, each as an offset to the jump address in the cache line (so it only takes a few bits instead of the whole 32-bit).
This makes look up exceptionally fast and space effecient. Although the number of entries in total is 4 times that of the P5, it occupies less space and lookup consist of only 2 searches without having to go through the whole branch prediction table.
The con is that it's limited to 2 branches per cache line, so codes exceeding that will cause trashing. The predcition counter is also less sophiciated than the P5 (a design choice, not an inherit problem). When a cache line is replaced, the counter would obviously have to reset, so branch information could not survive very long. All in all, it allows a fast and huge branch prediction table that is less accurate. I believe they supplement the K6 with an additional table to provide very good prediction rate.
Interestingly when they removed the thing from the K7, they said that it is an overkill for the generation of the CPU. So I guess the bottom line is does it really improve performance if they have to put in a secound "normal" branch prediction table anyway. unsigned
The text of this article appears to have been pulled from here, or vice versa: http://www.cpu-collection.de/?tn=0&l0=co&l1=AMD&l2=K5
Aluvus 04:52, 11 March 2006 (UTC) ---
This whole article relies solely on one source and that source seems to be a personal website rather then any news articles or anything. Please cite additional sources and check article for accuracy. -Tracer9999 (talk) 09:02, 30 October 2009 (UTC)
Floating Point Performance
From the benchmarks I've been able to find online (particularly those at cpu-world.com), the K5 FPU appears to be significantly slower than that of the Cyrix 6x86 (by approximately a 2:3 ratio comparing parts of equal clock speeds), which contradicts claims made in this article and the cited sources (which include no benchmarks or other performance data to support their claims). — Preceding unsigned comment added by 18.104.22.168 (talk) 23:23, 15 March 2012 (UTC)