1
00:00:00,000 --> 00:00:09,000
Hello, this is James Governor here at Redmug TV at the IBM Z-Summit for 2008.

2
00:00:09,000 --> 00:00:11,000
Would you like to introduce yourself, John?

3
00:00:11,000 --> 00:00:18,000
My name is John Shedletsky, I work for IBM in the Software Group, and I'm the Vice President of Competitive Technology.

4
00:00:18,000 --> 00:00:29,000
Historically, IBM didn't always do the best of jobs at helping its customers to make the economic case to their businesses in order to actually keep with the mainframe.

5
00:00:29,000 --> 00:00:31,000
I've noticed a bit of a change in that.

6
00:00:31,000 --> 00:00:38,000
Is this something that you're partly responsible for, this fact-based ability to help the customer make their case?

7
00:00:38,000 --> 00:00:44,000
Is that your group that does that? Is it a coherent strategy, or is it just something that I'm going to...

8
00:00:44,000 --> 00:00:58,000
Well, you know, for some time, the hardware organization in IBM, which is referred to as STG, which produces the main hardware product, NZOS,

9
00:00:58,000 --> 00:01:02,000
really drove these discussions about TCO.

10
00:01:02,000 --> 00:01:12,000
And in the software group, I think Steve Mills came to realize that you really can't talk about TCO in isolation from the software.

11
00:01:12,000 --> 00:01:14,000
It was really a combined story.

12
00:01:14,000 --> 00:01:21,000
And that was one of the assignments we got when he asked me to start getting involved in this subject.

13
00:01:21,000 --> 00:01:27,000
I will say that I think we've been a little more transparent with our data than has been the case in the past.

14
00:01:27,000 --> 00:01:33,000
I've had customers tell me, you know, IBM's pricing policies on the mainframe have been rather opaque to me.

15
00:01:33,000 --> 00:01:37,000
And I think this, in some sense, it hurt us rather than helped us.

16
00:01:37,000 --> 00:01:38,000
Absolutely.

17
00:01:38,000 --> 00:01:47,000
Because in the absence of information, competitors come in and say things that may not necessarily be true, and there's no one to contradict it.

18
00:01:47,000 --> 00:01:51,000
So we decided we needed to be a little more transparent.

19
00:01:51,000 --> 00:01:53,000
Well, frankly, exactly to your point.

20
00:01:53,000 --> 00:02:00,000
Whilst, yes, you may have been creating barriers to entry for your competitors, you were also creating barriers to participation from new customers.

21
00:02:00,000 --> 00:02:01,000
What have you found out?

22
00:02:01,000 --> 00:02:02,000
What's the story?

23
00:02:02,000 --> 00:02:03,000
What are the economics of this mainframe?

24
00:02:03,000 --> 00:02:11,000
Well, it boils down to one main idea, and that is the idea of consolidation.

25
00:02:11,000 --> 00:02:14,000
It's linked to this notion of economy of scale.

26
00:02:14,000 --> 00:02:17,000
It's a fundamental principle in economics.

27
00:02:17,000 --> 00:02:20,000
Even Henry Ford discovered this.

28
00:02:20,000 --> 00:02:28,000
Well, he didn't discover it, but he exploited this concept maybe a century ago when he created the automobile assembly line.

29
00:02:28,000 --> 00:02:38,000
The principle there was to get all the resources in one place and to be able to produce a unit of production at the lowest possible cost per unit.

30
00:02:38,000 --> 00:02:45,000
And the way he did that was by increasing the utilization of all the resources, namely the people who were working on the assembly line,

31
00:02:45,000 --> 00:02:51,000
and minimizing wasted effort to get all the energy focused on producing that production unit.

32
00:02:51,000 --> 00:02:53,000
The same is true with computing.

33
00:02:53,000 --> 00:03:04,000
In computing, a unit of work might be a transaction, and the objective here is to produce a transaction at the lowest possible cost per unit of work.

34
00:03:04,000 --> 00:03:08,000
And the way you do that is to get higher utilization out of the resources that are involved.

35
00:03:08,000 --> 00:03:16,000
And the way you do that is to run multiple workloads, because of the nature of how a computer works, CPU, having to wait for disk operations, and so forth.

36
00:03:16,000 --> 00:03:29,000
The way you actually do that is to run multiple workloads at the same time, multi-programming, and to apply some level of intelligent workload management to it so you meet service level agreement.

37
00:03:29,000 --> 00:03:43,000
The mainframe was designed to do this from the beginning, whereas some of the other platforms, most notably Windows, has really been regarded as a single application environment until very recently.

38
00:03:43,000 --> 00:03:54,000
And in the Unix world, while you could run multiple processes, in practice, even Unix servers were more or less dedicated to a particular application.

39
00:03:54,000 --> 00:04:08,000
It's really been the mainframe alone that really made it an operational principle that its job in life was to run multiple workloads simultaneously and to achieve very high levels of utilization of the process.

40
00:04:08,000 --> 00:04:16,000
Let me ask you about that, because that's a real challenge. One of the things is that most of the benchmarks are based on single proc, or at least single machine, single workload.

41
00:04:16,000 --> 00:04:20,000
How do you do that? Because there aren't really benchmarks for mixed workloads.

42
00:04:20,000 --> 00:04:32,000
Some people do benchmarks, but benchmarks are inherently interesting. They'll give you insight into processor speed, for example, but they don't necessarily tell you what you want to know.

43
00:04:32,000 --> 00:04:40,000
Because in a benchmark, what you do is set up some application program, and then you drive it to 100% utilization.

44
00:04:40,000 --> 00:04:40,000
Absolutely.

45
00:04:40,000 --> 00:04:47,000
But this is the point, that on these dedicated resources, typically they don't operate at 100% utilization.

46
00:04:47,000 --> 00:04:55,000
Whereas a mainframe can run multiple workloads, achieving 100% utilization of its processes.

47
00:04:55,000 --> 00:05:05,000
So, you can't just compare head to head, you know, let's just run this application just as hard as we can on both systems and see what throughput we get.

48
00:05:05,000 --> 00:05:10,000
You have to more step back and say, what's the workload in the data center?

49
00:05:10,000 --> 00:05:13,000
It becomes more of a data center issue than a platform issue.

50
00:05:13,000 --> 00:05:22,000
So, for example, that's why IBM is one reason why IBM has been focused on this so-called new enterprise data center that we've been talking about.

51
00:05:22,000 --> 00:05:31,000
Because we realize that the issue here is getting the lowest cost per unit of work out of the data center, all of the workload that the data center does.

52
00:05:31,000 --> 00:05:37,000
And what is the best way for a client to go about doing that in their data center?

53
00:05:37,000 --> 00:05:38,000
That's a possibility.

54
00:05:38,000 --> 00:05:44,000
I would say we could review where we are right now.

55
00:05:44,000 --> 00:05:52,000
Right now, I think primarily the role of the mainframe is to manage the core data of the business and the transactions that execute against that data.

56
00:05:52,000 --> 00:05:57,000
That's been the traditional role, the traditional strength.

57
00:05:57,000 --> 00:06:02,000
That's what the mainframe has been optimized to do for many years now.

58
00:06:02,000 --> 00:06:04,000
And we still see that.

59
00:06:04,000 --> 00:06:16,000
The mainframe is used by 66 out of the top 67 financial service companies in the world to manage their transactions against their core data.

60
00:06:16,000 --> 00:06:17,000
That's its strength.

61
00:06:17,000 --> 00:06:23,000
And it can do that in a way that other systems can only approximate.

62
00:06:23,000 --> 00:06:25,000
So, I see that role continuing.

63
00:06:25,000 --> 00:06:28,000
Do you have any messages for the London Stock Exchange?

64
00:06:28,000 --> 00:06:31,000
I saw something in the paper about a crash there.

65
00:06:31,000 --> 00:06:40,000
And it followed shortly after another article I saw about a crash at the Malaysian Stock Exchange going down for nine hours.

66
00:06:40,000 --> 00:06:41,000
Okay.

67
00:06:41,000 --> 00:06:43,000
They were running HP non-stop.

68
00:06:43,000 --> 00:06:44,000
Both of them, in fact.

69
00:06:44,000 --> 00:06:45,000
And it stopped.

70
00:06:45,000 --> 00:06:46,000
Yeah.

71
00:06:46,000 --> 00:06:47,000
Not so non-stop.

72
00:06:47,000 --> 00:06:48,000
Not so non-stop.

73
00:06:48,000 --> 00:06:49,000
Not so non-stop.

74
00:06:49,000 --> 00:06:50,000
So, yeah.

75
00:06:50,000 --> 00:06:53,000
So, I saw some back and forth about the London Stock Exchange.

76
00:06:53,000 --> 00:06:58,000
I weren't sure what to blame for the outage, but they were running non-stop as well?

77
00:06:58,000 --> 00:06:59,000
Mm-hmm.

78
00:06:59,000 --> 00:07:02,000
Well, what they have, the core trading platform is still non-stop.

79
00:07:02,000 --> 00:07:05,000
They also have a messaging platform, which is Windows-based.

80
00:07:05,000 --> 00:07:10,000
I think what came back to hold Microsoft in that is they've done a brilliant job of PR-ing it that they run the exchange.

81
00:07:10,000 --> 00:07:13,000
So, of course, when the exchange goes down, everyone says it's Microsoft's fault.

82
00:07:13,000 --> 00:07:14,000
They were associated with it.

83
00:07:14,000 --> 00:07:15,000
Yeah.

84
00:07:15,000 --> 00:07:19,000
You rarely hear about events like that with businesses that are running a mainframe.

85
00:07:19,000 --> 00:07:25,000
We have examples of customers, I know, of a bank that has not had an unplanned outage in ten years.

86
00:07:25,000 --> 00:07:26,000
Ten years.

87
00:07:26,000 --> 00:07:28,000
It just runs.

88
00:07:28,000 --> 00:07:35,000
And the only way that you can achieve that kind of availability is a layered strategy that starts at the heart.

89
00:07:35,000 --> 00:07:37,000
You mean you don't have to reboot mainframes every day?

90
00:07:37,000 --> 00:07:38,000
No.

91
00:07:38,000 --> 00:07:40,000
It just runs.

92
00:07:40,000 --> 00:07:41,000
Just like it should.

93
00:07:41,000 --> 00:07:48,000
I mean, if you're running your core business and you have a global business, you need to be able to run that core business 24 hours a day.

94
00:07:48,000 --> 00:07:49,000
Mm-hmm.

95
00:07:49,000 --> 00:07:53,000
And this is one of the key values that the platform provides.

96
00:07:53,000 --> 00:07:58,000
Investment we make in availability would be hard for any other vendor to match.

97
00:07:58,000 --> 00:08:01,000
It starts at the design of the chip.

98
00:08:01,000 --> 00:08:06,000
There are things in the chip that are there to provide redundancy.

99
00:08:06,000 --> 00:08:15,000
What the earlier speaker today was talking about manage, what did you call it, oversight of the memory usage and oversight of the processor execution.

100
00:08:15,000 --> 00:08:20,000
These are error detection and error correction and access control mechanisms.

101
00:08:20,000 --> 00:08:22,000
And it goes from there.

102
00:08:22,000 --> 00:08:25,000
There's reliability and serviceability.

103
00:08:25,000 --> 00:08:33,000
If you do need a part anywhere around the world, most likely the system has already detected that and called IBM.

104
00:08:33,000 --> 00:08:39,000
And most likely that part is positioned somewhere close to the customer anywhere in the world.

105
00:08:39,000 --> 00:08:40,000
Mm-hmm.

106
00:08:40,000 --> 00:08:44,000
So we have global serviceability.

107
00:08:44,000 --> 00:08:56,000
And then going on from there, you look at things like the sysplex that enables clustering on a scale that no one else can really -- a scale and efficiency that no one else can match.

108
00:08:56,000 --> 00:09:01,000
So that even if you lose a system, if you do lose a system, the cluster continues to run.

109
00:09:01,000 --> 00:09:07,000
The software is designed within the cluster to be upgraded without bringing the cluster down.

110
00:09:07,000 --> 00:09:15,000
Many of the maintenance operations on things like DB2 can be done without bringing the database down.

111
00:09:15,000 --> 00:09:17,000
So you even eliminate planned out.

112
00:09:17,000 --> 00:09:23,000
There's a layered strategy that we've been working on for years with a lot of feedback from our customers.

113
00:09:23,000 --> 00:09:24,000
Mm-hmm.

114
00:09:24,000 --> 00:09:28,000
Just honing off that last little risk or that last little --

115
00:09:28,000 --> 00:09:29,000
Continual improvement, basically.

116
00:09:29,000 --> 00:09:33,000
Continual improvement, so that these platforms will run reliably.

117
00:09:33,000 --> 00:09:49,000
To bring it back to software a little bit, one of the things that I know that many organizations don't fully understand is the cost benefits, to your point about software, and if we think about mainframe licensing, which was sometimes opaque and occasionally a blunt instrument.

118
00:09:49,000 --> 00:09:50,000
Mm-hmm.

119
00:09:50,000 --> 00:09:59,000
That there are some advantages of running the application service, say, and the database on the same box.

120
00:09:59,000 --> 00:10:06,000
By collapsing the tiers, there are some clear and substantive benefits, and a lot of people have not realized that.

121
00:10:06,000 --> 00:10:08,000
I refer to that as co-location.

122
00:10:08,000 --> 00:10:10,000
So take a typical case.

123
00:10:10,000 --> 00:10:23,000
You may have your database running on a mainframe, and people will often think they want to extend that -- they want to extend the channel to the Internet for that data, maybe a customer service channel or something.

124
00:10:23,000 --> 00:10:30,000
And they will typically maybe use WebSphere and think about running WebSphere on Intel or Unix --

125
00:10:30,000 --> 00:10:31,000
Because it's cheaper.

126
00:10:31,000 --> 00:10:34,000
-- servers sitting in front of the mainframe.

127
00:10:34,000 --> 00:10:37,000
Well, we'll get back to the cheaper in a minute.

128
00:10:37,000 --> 00:10:50,000
But we've done some benchmarks on this, and we have seen that basically the closer you can run that channel extender, in this case a web application, to the source of the data, the better performance you're going to get.

129
00:10:50,000 --> 00:11:03,000
So you can move it from a separate platform onto the Z, you can run it in a separate LPAR on Z, separate partition, or you can run it even in the same partition.

130
00:11:03,000 --> 00:11:08,000
And the closer you can get, the better your performance will be, and we refer to that as the co-location.

131
00:11:08,000 --> 00:11:11,000
And it can be a dramatic improvement, one and a half, two times.

132
00:11:11,000 --> 00:11:14,000
But also, of course, in licensing, there is an advantage as well.

133
00:11:14,000 --> 00:11:29,000
Well, in licensing, that's a little different story because, for example, you have to consider what would I pay to run this on Z Linux, where I'm taking advantage of the IFL, running 100% on an IFL.

134
00:11:29,000 --> 00:11:41,000
And I'm only paying for the software on a per core basis, a per IFL processor basis, which is just almost the same as what you would pay to run it on an Intel dual core.

135
00:11:41,000 --> 00:11:45,000
So that's a very low price there on Z Linux.

136
00:11:45,000 --> 00:11:49,000
You can run it on ZOS in the same partition as DB2.

137
00:11:49,000 --> 00:11:50,000
Right.

138
00:11:50,000 --> 00:12:01,000
But then you would have to take advantage of a ZAP processor, and while you may get 85% offload to a ZAP processor, there's still that 15% that's going to generate NLC.

139
00:12:01,000 --> 00:12:09,000
So the cost equation is a little bit different, and customers that are motivated by one or the other will make different decisions.

140
00:12:09,000 --> 00:12:19,000
It's still kind of difficult to compete on the understanding of TCO against a Microsoft or a Solaris platform.

141
00:12:19,000 --> 00:12:23,000
So how can you get better at that, especially in terms of the language that you use?

142
00:12:23,000 --> 00:12:24,000
That opacity remains.

143
00:12:24,000 --> 00:12:31,000
IBM has this language, a self-contained sort of church language.

144
00:12:31,000 --> 00:12:37,000
Other people don't understand, and that is a barrier to entry and participation in customers.

145
00:12:37,000 --> 00:12:40,000
So you say we say the liturgy of LPARs and MIPS.

146
00:12:40,000 --> 00:12:41,000
That is correct.

147
00:12:41,000 --> 00:12:42,000
Yeah.

148
00:12:42,000 --> 00:12:44,000
We do do that.

149
00:12:44,000 --> 00:12:51,000
I've struggled with this question because I think there are fundamental differences.

150
00:12:51,000 --> 00:12:57,000
When we talk about the new enterprise data center, that's all, well, it's about a number of things, but cost is at the center of it.

151
00:12:57,000 --> 00:13:00,000
You could look at what Microsoft is doing.

152
00:13:00,000 --> 00:13:04,000
Microsoft has 15 data centers today around the world.

153
00:13:04,000 --> 00:13:05,000
So obviously they're running Wintel.

154
00:13:05,000 --> 00:13:09,000
They don't run on anything else but Windows on Intel.

155
00:13:09,000 --> 00:13:13,000
And I believe they have a hundred and --

156
00:13:13,000 --> 00:13:15,000
Actually, you can run Windows on Solaris now, but --

157
00:13:15,000 --> 00:13:17,000
Well, you could, but they don't.

158
00:13:17,000 --> 00:13:24,000
And I think they have a total of 150,000 servers right now supporting their operations.

159
00:13:24,000 --> 00:13:30,000
And they're trying to move into this software as a service business model to compete more with Google.

160
00:13:30,000 --> 00:13:37,000
And they're planning to build 24 more data centers, 500,000 square feet each.

161
00:13:37,000 --> 00:13:40,000
And they recently had a conference where they talked about the plans.

162
00:13:40,000 --> 00:13:48,000
Now, the thing that I find amazing about this is that in order --

163
00:13:48,000 --> 00:13:56,000
They understand these issues of electrical consumption, cooling, floor space, and cost.

164
00:13:56,000 --> 00:13:59,000
Because their data centers are getting so massive.

165
00:13:59,000 --> 00:14:02,000
Even for Microsoft, the cost is massive.

166
00:14:02,000 --> 00:14:05,000
So they're trying to do something about it.

167
00:14:05,000 --> 00:14:11,000
And what they're doing is they're abandoning the HP Intel servers, which is what they run now.

168
00:14:11,000 --> 00:14:13,000
I believe it's ProLiance.

169
00:14:13,000 --> 00:14:16,000
And designing their own custom servers.

170
00:14:16,000 --> 00:14:21,000
And they're packing them in blade-type configurations into racks.

171
00:14:21,000 --> 00:14:26,000
And stuffing these racks into what effectively are shipping containers.

172
00:14:26,000 --> 00:14:28,000
I sit back and I think about that.

173
00:14:28,000 --> 00:14:39,000
So here's a company that predicated on the idea that the Wintel platform is the cheapest platform you can run on because it's commodity servers.

174
00:14:39,000 --> 00:14:47,000
And now they've gone down this road, like Steve was talking about this morning, where some of the other accruing costs start to accrue.

175
00:14:47,000 --> 00:14:51,000
And they've realized that they can't do that anymore.

176
00:14:51,000 --> 00:14:57,000
They have to build custom servers, just like Google has built custom servers.

177
00:14:57,000 --> 00:15:04,000
So this is where the Microsoft endgame takes you, to custom servers and blades packed in containers.

178
00:15:04,000 --> 00:15:09,000
The points I'll make about that: that nibbles at the edges of the cost equation.

179
00:15:09,000 --> 00:15:14,000
It doesn't address the most important elements of cost, which is labor and software.

180
00:15:14,000 --> 00:15:20,000
Now the ironic thing is, if all their software ran on Linux, let me talk about the alternative.

181
00:15:20,000 --> 00:15:23,000
The alternative is to consolidate.

182
00:15:23,000 --> 00:15:28,000
So where Microsoft sees their consolidation container being a shipping container,

183
00:15:28,000 --> 00:15:33,000
where you have to leave a little space in there for a person to walk in and deal with all those blades,

184
00:15:33,000 --> 00:15:38,000
our consolidation container is a ceramic module in a mainframe.

185
00:15:38,000 --> 00:15:42,000
With layers and layers of wiring, where the chips are really close to each other,

186
00:15:42,000 --> 00:15:46,000
and where we can power them and cool them in a very efficient way.

187
00:15:46,000 --> 00:15:52,000
It's back to this idea of consolidation as a far more effective vehicle for reducing cost,

188
00:15:52,000 --> 00:15:55,000
and all these other side benefits, like energy consumption,

189
00:15:55,000 --> 00:15:59,000
than simply just packing more blades into a tighter and tighter space.

190
00:15:59,000 --> 00:16:04,000
The second point I wanted to make: you could have a thousand blades in a shipping container,

191
00:16:04,000 --> 00:16:10,000
and you still couldn't do transaction processing against a single large database image.

192
00:16:10,000 --> 00:16:14,000
There is no technology in the world today that will let you do that.

193
00:16:14,000 --> 00:16:22,000
So you could say that Microsoft's solution for their data centers are really customized solutions

194
00:16:22,000 --> 00:16:24,000
for the kind of services they're contemplating providing.

195
00:16:24,000 --> 00:16:26,000
Maybe it's a different kind of workload to be fair.

196
00:16:26,000 --> 00:16:27,000
Different kind of workload.

197
00:16:27,000 --> 00:16:31,000
A final question would be, where do you see the mainframe in 10 years?

198
00:16:31,000 --> 00:16:39,000
I was having a discussion with someone about where do we see this idea of data centers in 10 years?

199
00:16:39,000 --> 00:16:40,000
The logical ultimate...

200
00:16:40,000 --> 00:16:43,000
Are you going to tell me there will be five? We're back to Thomas Watson.

201
00:16:43,000 --> 00:16:44,000
Two.

202
00:16:44,000 --> 00:16:45,000
Two.

203
00:16:45,000 --> 00:16:47,000
Two in the world.

204
00:16:47,000 --> 00:16:53,000
Just this so-called, this concept of cloud computing where you basically rent a server,

205
00:16:53,000 --> 00:16:56,000
is very popular in the Bay Area.

206
00:16:56,000 --> 00:16:59,000
My son works for a startup and they rent their servers.

207
00:16:59,000 --> 00:17:00,000
You don't even know where they are.

208
00:17:00,000 --> 00:17:01,000
Right.

209
00:17:01,000 --> 00:17:03,000
He just rents them out of the cloud.

210
00:17:03,000 --> 00:17:09,000
And, you know, the logical progression here is to consolidate everything,

211
00:17:09,000 --> 00:17:12,000
as long as you have security for isolation and so forth,

212
00:17:12,000 --> 00:17:18,000
into a few mega cloud centers around the world.

213
00:17:18,000 --> 00:17:20,000
Look at it from the customer's point of view.

214
00:17:20,000 --> 00:17:21,000
This is great.

215
00:17:21,000 --> 00:17:24,000
They don't have to worry about getting power delivered to their data centers.

216
00:17:24,000 --> 00:17:27,000
They don't have to worry about having to build a new data center.

217
00:17:27,000 --> 00:17:32,000
They don't have to worry about financing to finance all the equipment that they need.

218
00:17:32,000 --> 00:17:35,000
Well, as Nicholas Carr points out in the big switch,

219
00:17:35,000 --> 00:17:39,000
and, in fact, Jonathan Schwartz from Sun has made the point many times,

220
00:17:39,000 --> 00:17:42,000
you know, we used to have chief electricity officers.

221
00:17:42,000 --> 00:17:47,000
And manufacturing organizations would have their own electricity plants.

222
00:17:47,000 --> 00:17:49,000
That's not necessarily an ideal model.

223
00:17:49,000 --> 00:17:53,000
The flip side is, increasingly these days, we're seeing companies, you know,

224
00:17:53,000 --> 00:17:56,000
BT investing in wind farms, Google investing in renewables.

225
00:17:56,000 --> 00:17:59,000
Perhaps the chief electricity officer will come back.

226
00:17:59,000 --> 00:18:02,000
So, I'm not so sure we're going to see these five data centers,

227
00:18:02,000 --> 00:18:06,000
but it's an interesting vision, and it could be that, yes,

228
00:18:06,000 --> 00:18:09,000
that Thomas Watson was correct on that famous quote,

229
00:18:09,000 --> 00:18:11,000
you know, the world doesn't need more than five computers.

230
00:18:11,000 --> 00:18:13,000
If that's the vision of the future,

231
00:18:13,000 --> 00:18:16,000
a lot of consolidation across enterprise boundaries,

232
00:18:16,000 --> 00:18:20,000
because of the economics that that provides,

233
00:18:20,000 --> 00:18:26,000
then I see System Z being at the heart of those consolidated centers.

234
00:18:26,000 --> 00:18:32,000
Now, that means it'll have to be able to run more different kinds of workloads,

235
00:18:32,000 --> 00:18:34,000
probably different architectures.

236
00:18:34,000 --> 00:18:36,000
You could be running windows.

237
00:18:36,000 --> 00:18:40,000
That are tightly integrated the way that the processors are today,

238
00:18:40,000 --> 00:18:47,000
sharing at the ceramic level, not at the container level or at the network level.

239
00:18:47,000 --> 00:18:51,000
So, that was Red Bug TV and John Chemniewski.

240
00:18:51,000 --> 00:18:53,000
Thank you very, very much.

241
00:18:53,000 --> 00:18:53,000
You did.

242
00:18:56,000 --> 00:19:25,980
Thank you.