I need to get a new work computer that it's only use will be to use with excel, no browsing no gaming no nothing.
Will be using excel 64bit.
I currently have a 7700K running at 4.9GHz with 32 Gigs of RAM and a 8700K at 4.7GHz with 16 Gigs of RAM.
Now in the past I have had the luxury of running some tests to compare my 7700K to 2 different ZEON's ( I forget the model) but 1 was 12 cores at 2.6Ghz and the other was 18 cores at 2.3Ghz. and I ran a workbook that was 200,000KB in size
The results were that my 7700K ran a little more than 2X faster then both ZEON's. Although I was a little surprised at first it then seemed to make sense since my 7700K when running was on average pushing 60-70% CPU usage and it has a much higher clock speed.
The difference now is that I will be running multiple instances of this workbook at the same time. On my 8700K I've tested running varying degrees of multiple instances, bellow are the results.
<tbody>
[TD="width: 68, bgcolor: transparent"] Instances
[/TD]
[TD="width: 72, bgcolor: transparent"] Total Days
[/TD]
[TD="width: 72, bgcolor: transparent"] Avg. Time Hrs
[/TD]
[TD="width: 72, bgcolor: transparent"] Diff/Start
[/TD]
[TD="width: 72, bgcolor: transparent"] Diff
[/TD]
[TD="width: 68, bgcolor: transparent"] 1
[/TD]
[TD="width: 72, bgcolor: transparent"] 0.60
[/TD]
[TD="width: 72, bgcolor: transparent"] 14:28:00
[/TD]
[TD="width: 72, bgcolor: transparent"]
[/TD]
[TD="width: 72, bgcolor: transparent"]
[/TD]
[TD="width: 68, bgcolor: transparent"] 2
[/TD]
[TD="width: 72, bgcolor: transparent"] 0.80
[/TD]
[TD="width: 72, bgcolor: transparent"] 09:33:00
[/TD]
[TD="width: 72, bgcolor: transparent"] -34%
[/TD]
[TD="width: 72, bgcolor: transparent"] -34%
[/TD]
[TD="width: 68, bgcolor: transparent"] 3
[/TD]
[TD="width: 72, bgcolor: transparent"] 0.99
[/TD]
[TD="width: 72, bgcolor: transparent"] 07:53:00
[/TD]
[TD="width: 72, bgcolor: transparent"] -46%
[/TD]
[TD="width: 72, bgcolor: transparent"] -17%
[/TD]
[TD="width: 68, bgcolor: transparent"] 6
[/TD]
[TD="width: 72, bgcolor: transparent"] 1.57
[/TD]
[TD="width: 72, bgcolor: transparent"] 06:16:40
[/TD]
[TD="width: 72, bgcolor: transparent"] -57%
[/TD]
[TD="width: 72, bgcolor: transparent"] -20%
[/TD]
[TD="width: 68, bgcolor: transparent"] 8
[/TD]
[TD="width: 72, bgcolor: transparent"] 1.98
[/TD]
[TD="width: 72, bgcolor: transparent"] 05:56:45
[/TD]
[TD="width: 72, bgcolor: transparent"] -59%
[/TD]
[TD="width: 72, bgcolor: transparent"] -5%
[/TD]
[TD="width: 68, bgcolor: transparent"] 10
[/TD]
[TD="width: 72, bgcolor: transparent"] 2.40
[/TD]
[TD="width: 72, bgcolor: transparent"] 05:45:24
[/TD]
[TD="width: 72, bgcolor: transparent"] -60%
[/TD]
[TD="width: 72, bgcolor: transparent"] -3%
[/TD]
</tbody><strike style="background-attachment: scroll; background-clip: border-box; background-color: transparent; background-image: none; background-origin: padding-box; background-position-x: 0%; background-position-y: 0%; background-repeat: repeat; background-size: auto; border-bottom-color: rgb(34, 34, 34); border-bottom-style: none; border-bottom-width: 0px; border-image-outset: 0; border-image-repeat: stretch; border-image-slice: 100%; border-image-source: none; border-image-width: 1; border-left-color: rgb(34, 34, 34); border-left-style: none; border-left-width: 0px; border-right-color: rgb(34, 34, 34); border-right-style: none; border-right-width: 0px; border-top-color: rgb(34, 34, 34); border-top-style: none; border-top-width: 0px; font-family: Arial,Helvetica,sans-serif; font-size: 13.33px; font-size-adjust: none; font-stretch: 100%; font-style: normal; font-variant: normal; font-weight: 400; line-height: 19.99px; outline-color: transparent; outline-style: none; outline-width: 0px; overflow: visible; width: auto;"></strike>
<strike style="background-attachment: scroll; background-clip: border-box; background-color: transparent; background-image: none; background-origin: padding-box; background-position-x: 0%; background-position-y: 0%; background-repeat: repeat; background-size: auto; border-bottom-color: rgb(34, 34, 34); border-bottom-style: none; border-bottom-width: 0px; border-image-outset: 0; border-image-repeat: stretch; border-image-slice: 100%; border-image-source: none; border-image-width: 1; border-left-color: rgb(34, 34, 34); border-left-style: none; border-left-width: 0px; border-right-color: rgb(34, 34, 34); border-right-style: none; border-right-width: 0px; border-top-color: rgb(34, 34, 34); border-top-style: none; border-top-width: 0px; font-family: Arial,Helvetica,sans-serif; font-size: 13.33px; font-size-adjust: none; font-stretch: 100%; font-style: normal; font-variant: normal; font-weight: 400; line-height: 19.99px; outline-color: transparent; outline-style: none; outline-width: 0px; overflow: visible; width: auto;"></strike>
As you can see, the more instances the better the average time is. I haven't yet done more then 10 instances for a full run but I seem to be getting in the area of diminished returns with the CPU usage pinned to 100% constantly.
My main question is, Has anybody ever done similar tests on higher core consumer CPU's either with 10-18 cores using Intel or Threadripper? and would anybody know if even with a slower clock speed could more cores allow me to run even more instances with the result being an over lower average run time?
The other odd thing I wanted to mention was I ran a small test with 20 instances at one time and the RAM results were a little baffling to me. My 7700K with 32 gigs was using about 26gigs and ran the same test for the 8700K but my 8700K with 16 Gigs was "only" using 14-15 gigs and never peaked at 100% usage which I had expected. Any obvious reason why?
Thanks to anybody who can help!
MM
Will be using excel 64bit.
I currently have a 7700K running at 4.9GHz with 32 Gigs of RAM and a 8700K at 4.7GHz with 16 Gigs of RAM.
Now in the past I have had the luxury of running some tests to compare my 7700K to 2 different ZEON's ( I forget the model) but 1 was 12 cores at 2.6Ghz and the other was 18 cores at 2.3Ghz. and I ran a workbook that was 200,000KB in size
The results were that my 7700K ran a little more than 2X faster then both ZEON's. Although I was a little surprised at first it then seemed to make sense since my 7700K when running was on average pushing 60-70% CPU usage and it has a much higher clock speed.
The difference now is that I will be running multiple instances of this workbook at the same time. On my 8700K I've tested running varying degrees of multiple instances, bellow are the results.
<tbody>
[TD="width: 68, bgcolor: transparent"] Instances
[/TD]
[TD="width: 72, bgcolor: transparent"] Total Days
[/TD]
[TD="width: 72, bgcolor: transparent"] Avg. Time Hrs
[/TD]
[TD="width: 72, bgcolor: transparent"] Diff/Start
[/TD]
[TD="width: 72, bgcolor: transparent"] Diff
[/TD]
[TD="width: 68, bgcolor: transparent"] 1
[/TD]
[TD="width: 72, bgcolor: transparent"] 0.60
[/TD]
[TD="width: 72, bgcolor: transparent"] 14:28:00
[/TD]
[TD="width: 72, bgcolor: transparent"]
[/TD]
[TD="width: 72, bgcolor: transparent"]
[/TD]
[TD="width: 68, bgcolor: transparent"] 2
[/TD]
[TD="width: 72, bgcolor: transparent"] 0.80
[/TD]
[TD="width: 72, bgcolor: transparent"] 09:33:00
[/TD]
[TD="width: 72, bgcolor: transparent"] -34%
[/TD]
[TD="width: 72, bgcolor: transparent"] -34%
[/TD]
[TD="width: 68, bgcolor: transparent"] 3
[/TD]
[TD="width: 72, bgcolor: transparent"] 0.99
[/TD]
[TD="width: 72, bgcolor: transparent"] 07:53:00
[/TD]
[TD="width: 72, bgcolor: transparent"] -46%
[/TD]
[TD="width: 72, bgcolor: transparent"] -17%
[/TD]
[TD="width: 68, bgcolor: transparent"] 6
[/TD]
[TD="width: 72, bgcolor: transparent"] 1.57
[/TD]
[TD="width: 72, bgcolor: transparent"] 06:16:40
[/TD]
[TD="width: 72, bgcolor: transparent"] -57%
[/TD]
[TD="width: 72, bgcolor: transparent"] -20%
[/TD]
[TD="width: 68, bgcolor: transparent"] 8
[/TD]
[TD="width: 72, bgcolor: transparent"] 1.98
[/TD]
[TD="width: 72, bgcolor: transparent"] 05:56:45
[/TD]
[TD="width: 72, bgcolor: transparent"] -59%
[/TD]
[TD="width: 72, bgcolor: transparent"] -5%
[/TD]
[TD="width: 68, bgcolor: transparent"] 10
[/TD]
[TD="width: 72, bgcolor: transparent"] 2.40
[/TD]
[TD="width: 72, bgcolor: transparent"] 05:45:24
[/TD]
[TD="width: 72, bgcolor: transparent"] -60%
[/TD]
[TD="width: 72, bgcolor: transparent"] -3%
[/TD]
</tbody>
<strike style="background-attachment: scroll; background-clip: border-box; background-color: transparent; background-image: none; background-origin: padding-box; background-position-x: 0%; background-position-y: 0%; background-repeat: repeat; background-size: auto; border-bottom-color: rgb(34, 34, 34); border-bottom-style: none; border-bottom-width: 0px; border-image-outset: 0; border-image-repeat: stretch; border-image-slice: 100%; border-image-source: none; border-image-width: 1; border-left-color: rgb(34, 34, 34); border-left-style: none; border-left-width: 0px; border-right-color: rgb(34, 34, 34); border-right-style: none; border-right-width: 0px; border-top-color: rgb(34, 34, 34); border-top-style: none; border-top-width: 0px; font-family: Arial,Helvetica,sans-serif; font-size: 13.33px; font-size-adjust: none; font-stretch: 100%; font-style: normal; font-variant: normal; font-weight: 400; line-height: 19.99px; outline-color: transparent; outline-style: none; outline-width: 0px; overflow: visible; width: auto;"></strike>
As you can see, the more instances the better the average time is. I haven't yet done more then 10 instances for a full run but I seem to be getting in the area of diminished returns with the CPU usage pinned to 100% constantly.
My main question is, Has anybody ever done similar tests on higher core consumer CPU's either with 10-18 cores using Intel or Threadripper? and would anybody know if even with a slower clock speed could more cores allow me to run even more instances with the result being an over lower average run time?
The other odd thing I wanted to mention was I ran a small test with 20 instances at one time and the RAM results were a little baffling to me. My 7700K with 32 gigs was using about 26gigs and ran the same test for the 8700K but my 8700K with 16 Gigs was "only" using 14-15 gigs and never peaked at 100% usage which I had expected. Any obvious reason why?
Thanks to anybody who can help!
MM
