1
00:00:00,160 --> 00:00:10,519
here it is my friends concrete proof that satire truly is dead the GPU beside

2
00:00:06,600 --> 00:00:12,880
me contains 36 NVIDIA Grace Blackwell

3
00:00:10,519 --> 00:00:18,680
Super Chips and is estimated to cost over $3

4
00:00:15,240 --> 00:00:21,279
million now obviously the big heat sink

5
00:00:18,680 --> 00:00:25,199
on the side is illustrative you won't be installing one of these in your gaming

6
00:00:22,880 --> 00:00:31,960
rig unless uh you happen to have a 100,000 watts of power on tap and a

7
00:00:28,400 --> 00:00:33,559
building scale liquid cooling system but

8
00:00:31,960 --> 00:00:38,360
many of the Technologies NVIDIA is introducing here will benefit Gamers the

9
00:00:36,640 --> 00:00:45,360
the biggest one isn't really obvious until you go under the hood in my hands

10
00:00:43,039 --> 00:00:52,199
is one gb200 super chip now some of this we've

11
00:00:48,600 --> 00:00:55,840
seen before like this 72 core NVIDIA

12
00:00:52,199 --> 00:00:59,239
Grace CPU but these puppies right here

13
00:00:55,840 --> 00:01:02,199
these are all new and very very exciting

14
00:00:59,239 --> 00:01:07,520
do you guys see this tiny tiny line here thinner than the width of a human hair

15
00:01:04,479 --> 00:01:10,840
that is the gap between the two black

16
00:01:07,520 --> 00:01:16,799
well dyes that make up a b200

17
00:01:10,840 --> 00:01:21,400
GPU wait a second GPU is that not two

18
00:01:16,799 --> 00:01:23,640
gpus yes but also no while SLI might be

19
00:01:21,400 --> 00:01:29,040
dead for consumers NVIDIA has been hard at work creating interconnects that run

20
00:01:25,640 --> 00:01:32,799
at absolutely dizzying speeds allowing

21
00:01:29,040 --> 00:01:37,399
multiple G GPU dies to now act as a

22
00:01:32,799 --> 00:01:41,280
single GPU that allow multiple gpus to

23
00:01:37,399 --> 00:01:45,439
act as a single super chip and that

24
00:01:41,280 --> 00:01:49,520
allow multiple Super Chips to act as a

25
00:01:45,439 --> 00:01:51,799
single oh no to act as a single cohesive

26
00:01:49,520 --> 00:01:57,360
processing unit and it is going to unlock gaming experiences and more that

27
00:01:54,520 --> 00:02:03,200
are going to blow your mind you speak English right yes I speak English

28
00:02:00,479 --> 00:02:03,200
how can I help

29
00:02:05,280 --> 00:02:11,680
you can you also speak segue to our

30
00:02:08,360 --> 00:02:13,840
sponsor no I am also skilled in survival

31
00:02:11,680 --> 00:02:18,480
and op yes you can yes you can it's fine Ridge ridge's got your last minute

32
00:02:16,040 --> 00:02:21,959
father's Day's gift covered with a big sale click on our Link in the

33
00:02:19,920 --> 00:02:26,400
description and get up to 40% off their Rings their wallets and more

34
00:02:33,319 --> 00:02:38,360
we'll get to the Demos in a bit but first let's take a closer look at the

35
00:02:36,920 --> 00:02:43,720
product that is turning Global Tech media into Jensen hang's swifties NVIDIA

36
00:02:41,720 --> 00:02:49,560
chose not to disclose the number of cacor tenores or even the size of the

37
00:02:46,280 --> 00:02:52,040
ony caches of their new b200 Blackwell

38
00:02:49,560 --> 00:02:58,360
GPU but they did give us some numbers to work with Apples to Apples they expected

39
00:02:54,560 --> 00:03:00,959
to hit around 10 petaflops at fp8 sparse

40
00:02:58,360 --> 00:03:07,560
which puts it roughly 2 and half times faster than last gen Hopper also each of

41
00:03:04,640 --> 00:03:13,319
these is expected to draw about 1,000 Watts hence the

42
00:03:09,400 --> 00:03:16,519
uh liquid cooling each of our gpus gets

43
00:03:13,319 --> 00:03:19,640
192 GB of hbm 3E high-speed memory

44
00:03:16,519 --> 00:03:22,440
running at a casual 8 terabytes a second

45
00:03:19,640 --> 00:03:27,360
and is equipped with 1.8 terabyte per second Envy link and these numbers get

46
00:03:24,400 --> 00:03:34,959
even more ridiculous when we look at the super chip as a whole each super chip

47
00:03:31,120 --> 00:03:40,319
has two b200 gpus and a gray CPU for a

48
00:03:34,959 --> 00:03:44,439
total of 72 ARM CPU cores 864 GB of RAM

49
00:03:40,319 --> 00:03:48,040
and draws a total of 2700 Watts oh and

50
00:03:44,439 --> 00:03:50,519
by the way each of the 18 of these

51
00:03:48,040 --> 00:03:58,959
Blackwell compute nodes that make up an nvl 72 rack contains two Super Chips

52
00:03:55,720 --> 00:04:01,120
good Lord in California the rack that I

53
00:03:58,959 --> 00:04:08,079
was standing to in the intro would cost a whopping $30 an hour to run or about

54
00:04:05,599 --> 00:04:12,360
A4 million doar a year assuming you're paying residential energy rates speaking

55
00:04:10,280 --> 00:04:16,479
of running they literally need to take these demos to another room so I'm going

56
00:04:14,400 --> 00:04:21,040
to have to tell you about the spline on our way out of here we got our hands

57
00:04:18,759 --> 00:04:28,720
however temporarily on what NVIDIA is calling the spline of their nvl 72 rack

58
00:04:25,199 --> 00:04:31,520
this here contains 5,000 wires totaling

59
00:04:28,720 --> 00:04:36,919
over 2 miles mil and is cleverly laid out to optimize the latency and power

60
00:04:34,120 --> 00:04:41,039
efficiency see the networking all goes in the middle right here and the

61
00:04:39,240 --> 00:04:45,680
Blackwell compute nodes like the one they just took from us go at the top and

62
00:04:43,160 --> 00:04:51,160
the Bottom now they could have used fiber optics except that uh that would

63
00:04:48,800 --> 00:04:56,639
have cost them a casual 20,000 watts of additional power

64
00:04:53,479 --> 00:04:59,360
consumption so uh clever layout for the

65
00:04:56,639 --> 00:05:05,320
win put it all together and you've got a w

66
00:05:00,360 --> 00:05:09,360
72 Blackwell gpus 2600 gray CPU cores

67
00:05:05,320 --> 00:05:11,280
132 terab of hbm 3E memory with over

68
00:05:09,360 --> 00:05:16,840
half a pyte per second of aggregate bandwidth that's good for 720 pedop

69
00:05:14,560 --> 00:05:22,960
flops of fp8 training delivering results upwards of 30 times faster than a

70
00:05:19,400 --> 00:05:25,680
previous generation hgx h100 and if you

71
00:05:22,960 --> 00:05:30,560
didn't notice with perfect linear scaling something that is only possible

72
00:05:28,240 --> 00:05:34,840
when integrating your system this tightly even the placement of the

73
00:05:32,440 --> 00:05:39,600
individual blades matter on our super micro rack that we're looking at here

74
00:05:36,759 --> 00:05:43,800
you can see that they've got 10 up top and eight at the bottom with the nine

75
00:05:41,800 --> 00:05:48,720
nvlink switch units sandwiched in between that's because timing the

76
00:05:45,880 --> 00:05:52,560
electrical signals matters a lot and is easier on a more symmetrical setup now

77
00:05:51,080 --> 00:05:56,919
unfortunately NVIDIA didn't have a switch for us to show you they'll have

78
00:05:54,360 --> 00:06:03,520
to be represented by this piece of plastic but each of the nine units can

79
00:05:59,280 --> 00:06:06,560
handle 14.4 terabytes per second of NV

80
00:06:03,520 --> 00:06:10,199
link it is so integrated that NVIDIA

81
00:06:06,560 --> 00:06:14,840
says they think of this entire rack as

82
00:06:10,199 --> 00:06:17,160
one massive power hungry single GPU and

83
00:06:14,840 --> 00:06:20,560
it's kind of hard to argue otherwise other than that most of the time it's

84
00:06:18,759 --> 00:06:26,400
not doing graphics and I thought that's what the G was for and the craziest part

85
00:06:24,199 --> 00:06:33,400
is we haven't even looked at the craziest systems yet that was all mgx a

86
00:06:31,199 --> 00:06:41,240
standard set of reference designs that's intended to be compatible with multiple

87
00:06:35,720 --> 00:06:47,919
Generations hence the mg hgx is a whole

88
00:06:41,240 --> 00:06:51,080
different beast in this or on it it is

89
00:06:47,919 --> 00:06:52,560
eight Blackwell b200 gpus with a

90
00:06:51,080 --> 00:06:59,720
combined 1.44 terabytes of GPU memory absolutely

91
00:06:57,360 --> 00:07:03,960
ridiculous but the difference between this and what I just showed you is

92
00:07:01,280 --> 00:07:10,080
completely gone is any trace of Grace CPUs this is purely a GPU board because

93
00:07:07,879 --> 00:07:15,599
this insanity is meant to be integrated into a partner system like say from

94
00:07:12,400 --> 00:07:18,759
Super Micro now NVIDIA does sell their

95
00:07:15,599 --> 00:07:20,160
own dgx unit with this board and the

96
00:07:18,759 --> 00:07:25,360
rest of the components that make up a complete system but that's mostly

97
00:07:22,360 --> 00:07:29,160
intended to be a reference system these

98
00:07:25,360 --> 00:07:32,280
8 gpus get combined with Envy link just

99
00:07:29,160 --> 00:07:35,680
like the the rack setup for a whopping

100
00:07:32,280 --> 00:07:38,240
72 peda flops of FPA training while

101
00:07:35,680 --> 00:07:45,560
drawing nearly really 10,000 Watts now

102
00:07:42,400 --> 00:07:47,639
naturally this much power is a little

103
00:07:45,560 --> 00:07:51,960
hard to cool which is why it's so massive but the good thing about it is

104
00:07:50,080 --> 00:07:58,039
it doesn't require messing around with water or racks with 120,000 watts of

105
00:07:56,080 --> 00:08:02,800
power if you're installing these into an existing data center since

106
00:08:00,080 --> 00:08:05,840
those practically don't exist so you've got to spread them out a little bit

107
00:08:04,319 --> 00:08:11,159
according to your power budget which means you need networking and that is

108
00:08:09,120 --> 00:08:15,000
where NVIDIA's new hardware networking products come in this Ethernet switch

109
00:08:13,479 --> 00:08:20,319
will do something in the neighborhood if I think it's like 50 terabits per second

110
00:08:17,919 --> 00:08:24,720
of switching which is all really cool but what are we doing with this exactly

111
00:08:22,720 --> 00:08:28,319
I don't know how about Healthcare the tools I'm looking at right here use

112
00:08:26,360 --> 00:08:33,479
machine learning to approximate viral protein folding generate potential drug

113
00:08:30,840 --> 00:08:38,599
molecules to disable them and then test rapidly accelerating drug development oh

114
00:08:36,039 --> 00:08:41,680
and this is cool finding exactly what it is you're supposed to be taking a

115
00:08:39,839 --> 00:08:45,480
picture of with the ultrasound wand can take a bit of time why not let the

116
00:08:43,519 --> 00:08:51,680
machine identify it for you that's a left ventricle right cool know what else

117
00:08:48,680 --> 00:08:54,800
is cool simulations like the one we're

118
00:08:51,680 --> 00:08:56,640
living in behind me is Earth 2 a climate

119
00:08:54,800 --> 00:09:00,480
and weather simulation program that can run at such a high resolution that you

120
00:08:58,640 --> 00:09:06,000
can determine what's going to happen on a 1 km x 1 km basis is which is pretty

121
00:09:04,440 --> 00:09:11,760
cool but what if you need to simulate the movement of hot and cold air on a

122
00:09:07,959 --> 00:09:14,800
molecular level well you can do that too

123
00:09:11,760 --> 00:09:18,040
that is nuts which is all cool but what

124
00:09:14,800 --> 00:09:21,320
if I can't afford a dgx or an mgx to

125
00:09:18,040 --> 00:09:24,839
train those data sets well you can still

126
00:09:21,320 --> 00:09:28,360
use or experience NVIDIA's new Nims or

127
00:09:24,839 --> 00:09:30,440
NVIDIA inference microservices Nims are

128
00:09:28,360 --> 00:09:34,320
pre-trained and pre-optimized containerized AI models that you can

129
00:09:32,399 --> 00:09:39,079
download and deploy for any number of use cases and if that all sounded like

130
00:09:36,680 --> 00:09:43,560
gobleg um let's go back to that bilingual demo for a second facial

131
00:09:41,480 --> 00:09:47,600
animations can be an extremely timec consuming component of game development

132
00:09:45,680 --> 00:09:54,000
and are one of the big reasons that localization can be such a challenge the

133
00:09:50,800 --> 00:09:56,800
Nim in use here allows automatic mapping

134
00:09:54,000 --> 00:10:00,959
of speech to mouth animations and facial expressions meanwhile this guy takes

135
00:09:58,800 --> 00:10:05,560
things to two steps further using Nims for automatic speech recognition and

136
00:10:03,399 --> 00:10:09,839
facial animations but also a third one that I think is perhaps the most

137
00:10:07,720 --> 00:10:13,839
interesting to me there's a major concern right now in the games industry

138
00:10:11,920 --> 00:10:20,000
that AI is going to take jobs away from writers but this guy uses a n for data

139
00:10:16,800 --> 00:10:22,800
retrieval that is part of inworld ai's

140
00:10:20,000 --> 00:10:27,680
platform and this is really cool instead of him just crapping out whatever

141
00:10:24,880 --> 00:10:33,240
response chat GPT might throw at you he's actually got an extensive backstory

142
00:10:31,040 --> 00:10:38,720
that does need to be written by a human writer in order to give you a

143
00:10:35,399 --> 00:10:40,720
personality and context specific

144
00:10:38,720 --> 00:10:45,950
information that will help you advance the story have you ever tried any of the

145
00:10:42,800 --> 00:10:47,839
fine merchandise from LTT

146
00:10:47,839 --> 00:10:52,480
store.com now that is really cool and

147
00:10:50,880 --> 00:10:56,040
we're just scratching the surface right now over time NVIDIA is going to be

148
00:10:54,360 --> 00:11:00,880
looking to The Gaming Community both developers and Gamers for inspiration

149
00:10:58,560 --> 00:11:04,880
for what to do with these and oh I've got one more really cool demo G assist

150
00:11:03,120 --> 00:11:11,680
here might just be a tech demo at the moment but it's a pretty darn compelling

151
00:11:07,480 --> 00:11:16,200
one how do I craft a stone

152
00:11:11,680 --> 00:11:19,120
axe okay that is cool but what dinosaur

153
00:11:16,200 --> 00:11:19,120
am I looking at right

154
00:11:20,320 --> 00:11:27,079
now okay that's kind of sick and what's

155
00:11:24,240 --> 00:11:33,360
cool is the image recognition and I believe the voice to text are both

156
00:11:29,480 --> 00:11:34,760
running locally on this RTX series GPU I

157
00:11:33,360 --> 00:11:41,800
don't know about you guys but I think this is so cool that I don't know what to say way to our sponsor back Blaze

158
00:11:39,440 --> 00:11:45,920
losing your data is never fun so having solid backups of everything is super

159
00:11:44,120 --> 00:11:49,720
important and back Blaze is an affordable easyto ouse cloud backup

160
00:11:47,880 --> 00:11:54,720
solution with plans that start at just $9 a month you can backup almost

161
00:11:52,519 --> 00:11:58,279
anything from your Mac or PC and access it anywhere in the world with their web

162
00:11:56,399 --> 00:12:02,320
and mobile apps and they've restored over 55

163
00:11:59,760 --> 00:12:06,040
billion files with multiple options for how you can retrieve your data including

164
00:12:04,079 --> 00:12:09,399
having them send a physical hard drive straight to your door and if you're

165
00:12:07,800 --> 00:12:14,560
worried about accidentally deleting files you can increase your retention

166
00:12:11,279 --> 00:12:16,440
history to one year for free plus for

167
00:12:14,560 --> 00:12:20,279
organizational and business purposes their Advanced admin controls are

168
00:12:17,880 --> 00:12:24,279
designed for security scalability and ransomware resilience back blazs has

169
00:12:22,360 --> 00:12:29,320
over three exabytes of data under their management and has the trust of over

170
00:12:26,399 --> 00:12:33,160
half a million customers including us that's right we not only work with them

171
00:12:31,040 --> 00:12:38,000
on a sponsored basis we actually back up our servers nightly to back Blaze so

172
00:12:35,760 --> 00:12:42,079
starting at $9 a month it is hard to find a better investment than your peace

173
00:12:39,639 --> 00:12:47,680
of mind so sign up today and get a free 15-day trial at back blaze.com

174
00:12:44,880 --> 00:12:51,959
if you guys enjoyed this video uh why not check out our video from last

175
00:12:49,279 --> 00:12:55,680
computex showing off the grace CPUs and their last gen Super Chips we got a

176
00:12:53,880 --> 00:12:59,040
little bit more into the weeds and it was very very cool