1 00:00:00,000 --> 00:00:04,400 Although transistors still keep on shrinking, it's getting more and more difficult to pack 2 00:00:04,400 --> 00:00:09,200 as many of them on a chip as we'd like. Partial solutions to this, such as using chiplets 3 00:00:09,200 --> 00:00:13,840 to reduce the rate of manufacturing defects and stacking transistors on top of each other 4 00:00:13,840 --> 00:00:17,360 have been in vogue for a while now, but it might not be too surprising 5 00:00:17,360 --> 00:00:22,400 that some manufacturers have decided to simply make the chip themselves bigger, 6 00:00:22,400 --> 00:00:27,120 when in doubt, supersize. Now, I'm not saying that your next computer 7 00:00:27,120 --> 00:00:30,160 might have a CPU that's so big it'll take up half the motherboard, 8 00:00:30,160 --> 00:00:33,360 but when you get away from personal computers and start looking at chips 9 00:00:33,360 --> 00:00:39,040 that we might see in data centers in the near future, you start seeing some pretty eye-watering stuff. 10 00:00:39,040 --> 00:00:43,040 We're talking about designs like the Wafer Scale Engine 2 from Cerebrus, 11 00:00:43,040 --> 00:00:47,280 currently the largest chip in the world. Built on a seven nanometer process, 12 00:00:47,280 --> 00:00:51,840 it contains 850,000 cores 13 00:00:51,840 --> 00:00:56,800 and is a whopping 21.5 centimeters or 8.5 inches long. 14 00:00:56,800 --> 00:01:00,640 That's more total area than 25 Ryzen desktop CPUs. 15 00:01:00,640 --> 00:01:04,880 Perhaps unsurprisingly, a chip this big and with this many transistors, 16 00:01:04,880 --> 00:01:09,280 2.6 trillion, to be exact, requires a lot of power. 17 00:01:09,280 --> 00:01:12,800 The Wafer Scale Engine 2 sucks down 15 kilowatts, 18 00:01:12,800 --> 00:01:16,800 so if you were somehow able to drop this into your PC, 19 00:01:16,800 --> 00:01:20,000 you'd need 15 1000 watt power supplies 20 00:01:20,000 --> 00:01:23,440 just to keep it fit. And that's not even counting the rest of the system. 21 00:01:23,440 --> 00:01:28,480 But despite this, the new design should actually result in power savings. 22 00:01:28,480 --> 00:01:32,800 You see, data centers and supercomputers that do artificial intelligence processing 23 00:01:32,800 --> 00:01:38,400 often have to use lots of separate chips, such as GPUs, spread across a large facility. 24 00:01:38,400 --> 00:01:43,760 Having the same amount of computing power on just one physical chip is far more power efficient, 25 00:01:43,760 --> 00:01:48,800 even if the power consumption rating of that chip is a lot higher than a typical GPU. 26 00:01:48,800 --> 00:01:52,880 But there are other advantages to this approach, besides just saving energy. 27 00:01:52,960 --> 00:01:57,760 You might be wondering why we aren't simply just sticking a bunch of chiplets onto one package instead 28 00:01:57,760 --> 00:02:02,000 to make something like a really big version of an AMD Epic processor. 29 00:02:02,000 --> 00:02:06,880 So as versatile as chiplets have been, they still suffer from having more latency 30 00:02:06,880 --> 00:02:11,200 than one big monolithic processor. The little interconnects that move data 31 00:02:11,200 --> 00:02:16,160 between chiplets as quick as they may be, and they are fast, are still slower 32 00:02:16,160 --> 00:02:21,600 than if you physically put computing units directly adjacent to each other to form one big chip. 33 00:02:21,600 --> 00:02:26,560 Ultimately, this means that huge monolithic chips can process more data than a system 34 00:02:26,560 --> 00:02:30,400 with the same number of transistors spread out among multiple chips. 35 00:02:30,400 --> 00:02:34,720 And when you consider just how much data has to be processed for AI applications 36 00:02:34,720 --> 00:02:38,400 and scientific research, it makes a difference. 37 00:02:38,400 --> 00:02:41,760 Wave for scale technology has already drawn interest from diverse industries, 38 00:02:41,760 --> 00:02:46,320 including national intelligence and healthcare, but though it has some obvious advantages, 39 00:02:46,320 --> 00:02:51,200 that doesn't necessarily mean that it's the silver bullet to large-scale compute challenges. 40 00:02:51,200 --> 00:02:56,720 For instance, one big issue is the fact that these processors are designed to handle lots of data, 41 00:02:56,720 --> 00:03:02,160 so they also need access to a lot of memory, and designs with chiplets and larger amounts of memory 42 00:03:02,160 --> 00:03:05,360 built onto the same package may end up being more popular. 43 00:03:05,360 --> 00:03:09,600 This is similar to what Tesla has done with their new D1 chip, which was developed in part 44 00:03:09,600 --> 00:03:12,960 to help propel Tesla's self-driving AI technology. 45 00:03:12,960 --> 00:03:16,800 The D1 chip itself is much smaller than the Wave for Scale engine, 46 00:03:16,800 --> 00:03:23,680 but Tesla has included over 11 gigabytes of high-speed SRAM in an arrangement of 25 D1 chips 47 00:03:23,680 --> 00:03:28,400 connected together to make a training tile that's bigger than your head. 48 00:03:28,400 --> 00:03:33,760 And of course, making smaller chips reduces the amount of silicon you'll waste due to manufacturing errors, 49 00:03:33,760 --> 00:03:37,600 as we mentioned earlier. But regardless of whether a particular company 50 00:03:37,600 --> 00:03:40,640 is using Wave for Scale or an arrangement more like Tesla's, 51 00:03:40,640 --> 00:03:45,200 putting a large amount of silicon on one plane may end up becoming an industry trend. 52 00:03:45,200 --> 00:03:50,720 Because if America has taught us anything, it's that there's a deep human need to supersize. 53 00:03:50,720 --> 00:03:54,320 And if you feel the need, like the video or dislike the video, 54 00:03:54,320 --> 00:03:57,440 check out our other videos and comment below with video suggestions. 55 00:03:57,440 --> 00:04:00,640 We make videos here. Get your videos here at TechQuickie. 56 00:04:00,640 --> 00:04:02,320 Don't forget to subscribe and follow. 57 00:04:04,320 --> 00:04:05,040 See you later.