Okay Guyo, welcome to another video. So, I've got some exciting news. We have reached seven thousand subscribers on this channel. That's just brilliant! Thank you very much for subscribing. In celebration of reaching seven thousand subscribers, I have decided to upload a mathematics competition containing unusually difficult questions. The first person to decipher a hidden message by answering 10 riddles within seven days of the upload will win a hundred dollars. So, that should be pretty good fun. That's coming up shortly, so keep your eye on this channel. Now, onto the topic for today. Today's topic is the min and Max instructions in SSEs. Sorry, something stuck in my head. It's been a really long time since I did a video dedicated to instructions in x86. I think we have covered about half of them. Maybe this video today is going to be a bit of a return to form. The min and Max instructions in SSE can be thought of as a conditional move. They compare corresponding elements from two registers in SIMD (MMX registers or SSE registers or AVX if you have it) and store either the minimum or the maximum of each pair. The first ones we will look at briefly are the SSE floating-point versions: max SS, max PS, max SD, and max PD. The minimum versions are the same thing. These are used for discovering the minimum and maximum of each pair of singles or doubles. For all of the instructions we are looking at today, the parameters are an SSE register as the first source and destination, and the second source is either an SSE register or a memory operand. So, what do these instructions do? Let me illustrate it below. For example, if the CPU reads the instruction "min PS XMM0, XMM1" and the numbers in...
Award-winning PDF software
Video instructions and help with filling out and completing Can Form 1094 B Tracker
