Head of Product at Temporal. Previously lead architect and low-level systems programmer for scale out SaaS offering. Game engine developer, ML engineering expert. DMs open on Twitter.
It's a funny situation, in some ways, we've progressed a lot since 2006. But in terms of the underlying mechanisms, much is unchanged.
I'm not saying hardware isn't improving btw, just not fundamentally like it was in the late 90's-early 2000's. Branch prediction is much better and they add a ton of extra instructions to chipset. Part of what "Inside the Machine" covers, is the "4 GHz race". This is where Intel and AMD duked it out trying to be the first with a 4GHz clock. What they ended up finding out (this is early 2000's), is that clocks over 4GHz tend to melt. This discovery changed the landscape quite a bit, because instead of just trying to add more transistors and increase clock cycles, they actually had to find new areas to improve.
That event, in combination with a cultural shift towards mobile technologies has had a very noticeable effect on microprocessor development. Intel focuses more on ways to save power, and improve task parallelism, as opposed to increase clock speeds and raw processor power.
I would say the bigger changes to hardware are what's happening outside of traditional processors. FPGA's and ASIC's are a real force these days, and Nvidia is obviously killing Intel in terms of recent GPU stuff. Overall I think the book is still 95% as useful as it was when I read it.
Experienced software and UX guy. Over 20 years making professional software. Lots of tech/tools/languages. Father of 7. Armchair philosopher. Currently focused on full stack dev with React, Node..
Really appreciate your insights! Just wanted to make sure I wouldn't invest too much time to be learning stuff that is/would be soon outdated. Thanks for both write ups!
For further actions, you may consider blocking this person and/or reporting abuse
We're a place where coders share, stay up-to-date and grow their careers.
It's a funny situation, in some ways, we've progressed a lot since 2006. But in terms of the underlying mechanisms, much is unchanged.
I'm not saying hardware isn't improving btw, just not fundamentally like it was in the late 90's-early 2000's. Branch prediction is much better and they add a ton of extra instructions to chipset. Part of what "Inside the Machine" covers, is the "4 GHz race". This is where Intel and AMD duked it out trying to be the first with a 4GHz clock. What they ended up finding out (this is early 2000's), is that clocks over 4GHz tend to melt. This discovery changed the landscape quite a bit, because instead of just trying to add more transistors and increase clock cycles, they actually had to find new areas to improve.
That event, in combination with a cultural shift towards mobile technologies has had a very noticeable effect on microprocessor development. Intel focuses more on ways to save power, and improve task parallelism, as opposed to increase clock speeds and raw processor power.
I would say the bigger changes to hardware are what's happening outside of traditional processors. FPGA's and ASIC's are a real force these days, and Nvidia is obviously killing Intel in terms of recent GPU stuff. Overall I think the book is still 95% as useful as it was when I read it.
Really appreciate your insights! Just wanted to make sure I wouldn't invest too much time to be learning stuff that is/would be soon outdated. Thanks for both write ups!