Follow Slashdot blog updates by subscribing to our blog RSS feed

 



Forgot your password?
typodupeerror

Comment: Re:Access time latency (Score 1) 159

by adisakp (#49520489) Attached to: New PCIe SSDs Load Games, Apps As Fast As Old SATA Drives
Until the engine decides to redundantly load the same package again, it won't be cached (ie first time is off disk and latter times off RAM). A good engine limits the number of times redundant loads occur. And unless you have an abundance of RAM, it's typically pointless to cache a very large file that is read at a slower speed than what the disk will actively serve as well.

Comment: Re:Why not? (Score 1) 670

by adisakp (#49520417) Attached to: William Shatner Proposes $30 Billion Water Pipeline To California
Ah, the Australian plant has 3X the output. I'm not sure if there is higher efficiency (operation cost) for larger plants, but typically, desalinization is a process which has some efficiency scaling. Anyhow, 7-8% of one very metropolitan/urban county isn't going to put a dent in overall CA water consumption when the vast majority of it is going to agricultural uses.

Comment: Re:Opinion from a game developer (Score 1) 159

by adisakp (#49520185) Attached to: New PCIe SSDs Load Games, Apps As Fast As Old SATA Drives
Game engines are constantly improving on this too... with file read ahead, and multithreading decompression of chunks, as well as other optimizations. Over time, this process has been gradually getting faster and at some point, SSD's will come out ahead. It's just that the current bottleneck is quite often CPU and memory bandwidth, not HD linear read speed.

Comment: Opinion from a game developer (Score 1) 159

by adisakp (#49520155) Attached to: New PCIe SSDs Load Games, Apps As Fast As Old SATA Drives
NOTE: I'm speaking for myself here, and not for my company, but I have been working full time in the games industry for 23 years.

Most games use pack-files (sometimes called packages) that are large binary blobs on disk that are loaded contiguously in a seek-free manner. Additionally, these blobs may have ZIP or other compression applied to them (often in an incremental chunked way). The CPU's can only process the serialization of assets (loading) at a certain speed due to things like allocation of memory from the kernel and graphics drivers (which on secure OS's typically involves remapping and clearing pages). There are additional CPU constraints for the decompression, and for the serialization "linker" phase to associate assets in a package and present them to the game engine.

All this stuff takes time, and in a game with streaming (loading while game-play is going on), there are a limited number of CPU cycles as well as memory bandwidth to process the serialization after running the game engine.

These processing constraints impose a limit on the speed at which data can be loaded and consumed by the engine. And in many game engines on a typically powered PC, that number may be anywhere from 50-200MB/s but probably averaging closer to 100-150MB/s. Since this is in the linear contiguous read speed of many hard drives, as long as the package file is not fragmented on the disk, using an SSD will result in minimal speedup during this type of loading process.

Comment: Re:Why not? (Score 1) 670

by adisakp (#49511929) Attached to: William Shatner Proposes $30 Billion Water Pipeline To California

For $30B, you can build a LOT of desalination plants.

Define "a LOT"??? My calculations are that you could build maybe 4-5 plants or actually build and operate 2 plants going on costs from other similar plants in the world.

Australia built a desalination plant with an intial estimated construction cost of $3-4B AUS. Final construction was $6-7B AUS -- however, the total costs including operation of the plant at $1.8M a day over the 27yr contract will be around $19B Australian or roughly $15B US.

Assuming the US could operate as efficiently cost-wise (and we rarely do on large public works projects), we could afford to build and run 2 Desalination plants for $30B US.

Comment: Not easy to fix and we need fewer killings (Score 1) 173

by jbn-o (#49504415) Attached to: FBI Overstated Forensic Hair Matches In Nearly All Trials Before 2000

I disagree; knowing that bad evidence was presented (particularly in life imprisonment and death penalty cases where there is no chance to make amends with those falsely convicted) shows more evidence of why the death penalty was never a good idea. Therefore we don't need more death penalty conclusions such as "Willfully hide exculpatory evidence in a capital murder trial? Death penalty.".

All syllogisms have three parts, therefore this is not a syllogism.

Working...