Thanks to all. From the responses so far and my experience I'm inclined to believe SRST is hardware and probably SRSTU is millicode (perhaps based on SRST for the first byte) and we must look for another technique.
My original thought was that we would use a serial search until the number of keys exceeded some threshold and then build and maintain the 2-byte hash table and switch to SRSTU, based on naively expecting its performance to be comparable to SRST up to some number of keys and significantly better than SRST when the number of entries exceeded some multiple of 256. We are experimenting with other techniques, but we can't change that the keys are added and deleted dynamically, are continually accessed, and the total number of entries varies significantly in different applications. I guess it's time to look at vector instructions and possibly B-trees. Gary Gary Weinhold Senior Application Architect DATAKINETICS | Data Performance & Optimization Phone:+1.613.523.5500 x216 Email: weinh...@dkl.com Visit us online at www.DKL.com E-mail Notification: The information contained in this email and any attachments is confidential and may be subject to copyright or other intellectual property protection. If you are not the intended recipient, you are not authorized to use or disclose this information, and we request that you notify us by reply mail or telephone and delete the original message from your mail system.