←back to thread

Building the System/360 Mainframe Nearly Destroyed IBM

(spectrum.ieee.org)
169 points rbanffy | 9 comments | 08 Apr 25 07:30 UTC | HN request time: 0.204s | source | bottom
Show context
talkingtab ◴[08 Apr 25 15:11 UTC] No.43622725[source]▶
This whole thing is very cool and worth reading.

BUT. I worked at a place that used IBM 360s. We ran stuff for engineers, a lot of Fortran along with assembly code. We had so much stuff going on we could not code up and run things fast enough. The engineer/scientist got frustrated.

Then one day an engineer brought in an Apple II from home and ran the programs on that.

The earth shook. The very ground beneath us moved. Tectonic plates shifted. The world was never the same again! I think it was Visicalc.

Later there were other things. Soul Of A New Machine. The Mac.

I wonder how the compute power of a current high end smart phone compares with and IBM 360? I know the graphics chip is better.

replies(9): >>43623121 #>>43623556 #>>43623991 #>>43624225 #>>43624864 #>>43625147 #>>43627382 #>>43627847 #>>43631309 #
1. btilly ◴[08 Apr 25 17:23 UTC] No.43624225[source]▶
I wonder how the compute power of a current high end smart phone compares with and IBM 360? I know the graphics chip is better.

A current high end smartphone has around 10 billion transistors.

From https://gunkies.org/wiki/IBM_System/360, IBM made 11-12 million SLT modules per year in the late 1960s, with less before that. Each individual SLT module contained a handful of transistors. Therefore, in transistor count alone, a single smartphone has more transistors than IBM produced through the 1960s. And this is before we consider the fact that clock speeds today are much higher than they were in the 1960s.

Your smartphone literally has enough hardware to outcompute the entire world circa 1970.

Isn't it amazing what over 50 years of Moore's Law can do?

replies(4): >>43624673 #>>43624770 #>>43625609 #>>43630578 #
2. btilly ◴[08 Apr 25 18:01 UTC] No.43624673[source]▶
Huh. The article claims at least an order of magnitude more SLT modules than the reference I found. I think it is still quite a bit less than the smartphone, but that makes global compute at least closer.

Still, 55 years of doubling transistors at a given cost every 2 years is about a 190 million fold transistor difference for a given cost. Clock speeds have improved by a factor of 1000 on top of that. Even with performance tradeoffs for battery life in a smartphone, there is no surprise that the phone should have more compute power than the world did in 1970.

3. twoodfin ◴[08 Apr 25 18:09 UTC] No.43624770[source]▶
Indeed. I find it interesting to look at the generational outliers on that curve: The Cray-1 wasn’t eclipsed in raw FP compute by a consumer system until the Pentium more than 15 years later.

http://www.roylongbottom.org.uk/Cray%201%20Supercomputer%20P...

replies(1): >>43624965 #
4. btilly ◴[08 Apr 25 18:27 UTC] No.43624965[source]▶
Most of the outliers look like, "Someone was willing to spend large amounts of money."

Another outlier was Deep Blue. Estimated cost of about $10 million. Its estimated strength was matched by top end PCs about 9 years later. Your phone today is better than those PCs.

Progress is relentless.

5. kstrauser ◴[08 Apr 25 19:29 UTC] No.43625609[source]▶
My home NAS in the other room could hold about 350 million C64 floppies. I've sometimes wondered how that compares to the world's floppy disk manufacturing capacity in 1982.

I also appreciate that my Internet connection is about 33 million times faster than my first modem. It'd take me over a year to download what I can slurp in about 1 second now, even if I could afford the 7 thousand floppies it'd take to store it.

Progress, yo.

replies(1): >>43627755 #
6. ◴[09 Apr 25 00:18 UTC] No.43627755[source]▶
7. graycat ◴[09 Apr 25 10:16 UTC] No.43630578[source]▶
> the entire world circa 1970.

About then was the IBM 360/91 with a 60 nanosecond cycle time. So, that would be a clock speed of

     1/ ( (60)/(10^9) ) 

     = (10^9) / 60

     = 10^7 (100 / 60 )

     = 10^7 (10 / 6 )

     = 10^7 (1.66)

     1.66 (10,000,000)

     16.66 (1,000,000)

     = 17 Mhz
Now we can have clock frequencies of 4 GHz, that is

     4000/17 = 235
times faster. And we can have 16 cores instead of 1 for

     (16)(4000) / 17 = ~4000
times faster. "entire world"?
replies(1): >>43641437 #
8. photon_rancher ◴[10 Apr 25 07:05 UTC] No.43641437[source]▶
What’s the average IPC of these chips for a reasonable workload?

Early processors were typically 1 or lower. Modern stuff is all superscalar piplined and out of order and can do way more than you’d expect. Not to mention SIMD operations and other technologies. Branch prediction is probably better on the new chips too.

And with more RAM and cache algorithms can be chosen with different tradeoffs for less instructions.

16 cores at 4ghz was a thing like a decade ago - chips today might have the same specs but are definitely far faster.

replies(1): >>43649664 #
9. graycat ◴[11 Apr 25 01:42 UTC] No.43649664{3}[source]▶
WOW! IPC, instructions per cycle? Sure, back in those days, usually how many cycles per instruction! The 360/91 was a high end thing, said to cost $13 million. One was at the Navy lab, JHU.APL. As I recall, it could do 1 floating point (32 or 64 bits?) instruction per cycle and sometimes 3 in 2 cycles.