1
00:00:00,080 --> 00:00:05,359
although transistors still keep on shrinking it's getting more and more

2
00:00:03,520 --> 00:00:09,760
difficult to pack as many of them on a chip as we'd like partial solutions to

3
00:00:07,680 --> 00:00:13,599
this such as using chiplets to reduce the rate of manufacturing defects and

4
00:00:11,759 --> 00:00:17,440
stacking transistors on top of each other have been in vogue for a while now

5
00:00:15,759 --> 00:00:22,320
but it might not be too surprising that some manufacturers have decided to

6
00:00:19,439 --> 00:00:26,640
simply make the chips themselves bigger when in doubt supersize

7
00:00:24,800 --> 00:00:30,320
now i'm not saying that your next computer might have a CPU that's so big

8
00:00:28,480 --> 00:00:33,280
it'll take up half the motherboard but when you get away from personal

9
00:00:31,599 --> 00:00:37,120
computers and start looking at chips that we might see in data centers in the

10
00:00:34,960 --> 00:00:40,399
near future you start seeing some pretty eye-watering stuff

11
00:00:38,960 --> 00:00:45,440
we're talking about designs like the wafer scale engine 2 from cerebros

12
00:00:42,960 --> 00:00:50,239
currently the largest chip in the world built on a seven nanometer process and

13
00:00:47,360 --> 00:00:57,039
contains 850 000 cores and is a whopping 21.5

14
00:00:54,000 --> 00:00:59,920
centimeters or 8.5 inches long that's

15
00:00:57,039 --> 00:01:05,840
more total area than 25 ryzen desktop cpus perhaps unsurprisingly a chip this

16
00:01:02,640 --> 00:01:08,720
big and with this many transistors 2.6

17
00:01:05,840 --> 00:01:14,320
trillion to be exact requires a lot of power the wafer scale engine 2 sucks

18
00:01:10,880 --> 00:01:16,960
down 15 kilowatts so if you were somehow

19
00:01:14,320 --> 00:01:22,320
able to drop this into your pc you'd need 15 1000 watt power supplies just to

20
00:01:20,320 --> 00:01:26,880
keep it fit that's not even counting the rest of the system but despite this the

21
00:01:24,880 --> 00:01:31,360
new design should actually result in power savings you see data centers and

22
00:01:29,680 --> 00:01:36,159
supercomputers that do artificial intelligence processing often have to

23
00:01:33,439 --> 00:01:40,320
use lots of separate chips such as gpus spread across a large facility having

24
00:01:38,640 --> 00:01:44,960
the same amount of computing power on just one physical chip is far more power

25
00:01:43,200 --> 00:01:49,840
efficient even if the power consumption rating of that chip is a lot higher than

26
00:01:47,360 --> 00:01:53,759
a typical GPU but there are other advantages to this approach besides just

27
00:01:51,840 --> 00:01:57,840
saving energy you might be wondering why we aren't simply just sticking a bunch

28
00:01:55,600 --> 00:02:02,399
of chiplets onto one package instead to make something like a really big version

29
00:02:00,000 --> 00:02:06,960
of an AMD epic processor and we'll tell you why right after we think ifixit for

30
00:02:04,880 --> 00:02:10,399
sponsoring this video ifixit wants to help you fix all of your devices so you

31
00:02:09,039 --> 00:02:14,879
never have to pay for a costly replacement again from your xbox to your

32
00:02:12,800 --> 00:02:19,200
toothbrush i fix it as parts and guides for almost any device you can think of

33
00:02:16,720 --> 00:02:24,239
they have over 70 000 step-by-step guides with photos to make it easy check

34
00:02:21,680 --> 00:02:27,599
out ifixit.com techwiki to pick up a repair kit and join the right to repair

35
00:02:26,160 --> 00:02:31,840
movement today so as versatile as chiplets have been

36
00:02:30,080 --> 00:02:36,319
they still suffer from having more latency than one big monolithic

37
00:02:34,319 --> 00:02:40,879
processor the little interconnects that move data between chiplets as quick as

38
00:02:38,160 --> 00:02:44,879
they may be and they are fast are still slower than if you physically

39
00:02:42,720 --> 00:02:48,879
put computing units directly adjacent to each other to form one big chip

40
00:02:47,200 --> 00:02:53,120
ultimately this means that huge monolithic chips can process more data

41
00:02:51,519 --> 00:02:57,440
than a system with the same number of transistors spread out among multiple

42
00:02:55,360 --> 00:03:01,920
chips and when you consider just how much data has to be processed for ai

43
00:02:59,680 --> 00:03:06,159
applications and scientific research it makes a difference wafer scale

44
00:03:04,560 --> 00:03:09,920
technology has already drawn interest from diverse industries including

45
00:03:07,840 --> 00:03:13,760
national intelligence and healthcare but though it has some obvious advantages

46
00:03:11,920 --> 00:03:18,480
that doesn't necessarily mean that it's the silver bullet to large-scale compute

47
00:03:15,920 --> 00:03:21,360
challenges for instance one big issue is the fact that these processors are

48
00:03:19,920 --> 00:03:26,080
designed to handle lots of data so they also need access to

49
00:03:24,000 --> 00:03:29,680
a lot of memory and designs with chiplets and larger amounts of memory

50
00:03:27,760 --> 00:03:33,599
built on the same package may end up being more popular this is similar to

51
00:03:31,760 --> 00:03:37,519
what tesla has done with their new d1 chip which was developed in part to help

52
00:03:35,599 --> 00:03:42,720
propel tesla's self-driving ai technology the d1 chip itself is much

53
00:03:40,640 --> 00:03:48,480
smaller than the wafer scale engine but tesla has included over 11 gigabytes of

54
00:03:45,519 --> 00:03:53,200
high speed sram in an arrangement of 25 d1 chips connected together to make a

55
00:03:50,879 --> 00:03:57,519
training tile that's bigger than your head and of course making smaller chips

56
00:03:55,920 --> 00:04:01,920
reduces the amount of silicon you'll waste due to manufacturing errors as we

57
00:03:59,680 --> 00:04:05,519
mentioned earlier but regardless of whether a particular company is using

58
00:04:03,599 --> 00:04:09,599
wafer scale or an arrangement more like teslas putting a large amount of silicon

59
00:04:07,760 --> 00:04:13,360
on one plane may end up becoming an industry trend because if america has

60
00:04:11,599 --> 00:04:18,799
taught us anything it's that there's a deep human need to supersize

61
00:04:16,320 --> 00:04:22,479
and if you feel the need like the video or dislike the video check out our other

62
00:04:20,720 --> 00:04:26,720
videos and comment below with video suggestions we make videos here get your

63
00:04:24,960 --> 00:04:29,840
videos here at Techquickie don't forget to subscribe and follow

64
00:04:30,000 --> 00:04:33,320
see you later