Neuchips Tapes Out Recommendation Accelerator for World-Beating
Accuracy: https://www.eetimes.com/neuchips-tapes-out-recommendation-accelerator-for-world-beating-accuracy/
On Friday, June 24, 2022 at 9:00:02 AM UTC-7, Gary Scott wrote:
Neuchips Tapes Out Recommendation Accelerator for World-Beating
Accuracy:
https://www.eetimes.com/neuchips-tapes-out-recommendation-accelerator-for-world-beating-accuracy/
I would hope the new floating point formats are on-topic here.
For those TL;DR, they are (there are more than one) 8 bit formats.
Or, to keep up with the recent discussion.
REAL*1
There are even unsigned forms.
REAL*1
I once worked on a lossy data compression method for iterative
procedures that required only 3 or 4 bits of precision each iteration. I implemented it in fixed-point arithmetic, packed into integer words, but floating point would have also worked alright. In this 8-bit
representation, that would have been 1 sign bit, 4 exponent bits, and 3 mantissa bits (4 counting the hidden bit). The final result was a 64-bit floating point vector, but it was accumulated over several iterations, 3
or 4 bits at a time.
On Friday, June 24, 2022 at 11:05:10 PM UTC-7, Ron Shepard wrote:
(snip, I wrote)
It seems though that it allows, or can allow, for different exponentREAL*1I once worked on a lossy data compression method for iterative
procedures that required only 3 or 4 bits of precision each iteration. I implemented it in fixed-point arithmetic, packed into integer words, but floating point would have also worked alright. In this 8-bit representation, that would have been 1 sign bit, 4 exponent bits, and 3 mantissa bits (4 counting the hidden bit). The final result was a 64-bit floating point vector, but it was accumulated over several iterations, 3
or 4 bits at a time.
bits by 1s. SELECTED_REAL_KIND only allows counting
in units of 3.32 bits, so too coarse for this system.
And then there is unsigned.
On Saturday, June 25, 2022 at 10:13:18 AM UTC+2, gah4 wrote:
On Friday, June 24, 2022 at 11:05:10 PM UTC-7, Ron Shepard wrote:
(snip, I wrote)
It seems though that it allows, or can allow, for different exponentREAL*1I once worked on a lossy data compression method for iterative
procedures that required only 3 or 4 bits of precision each iteration. I >>> implemented it in fixed-point arithmetic, packed into integer words, but >>> floating point would have also worked alright. In this 8-bit
representation, that would have been 1 sign bit, 4 exponent bits, and 3
mantissa bits (4 counting the hidden bit). The final result was a 64-bit >>> floating point vector, but it was accumulated over several iterations, 3 >>> or 4 bits at a time.
bits by 1s. SELECTED_REAL_KIND only allows counting
in units of 3.32 bits, so too coarse for this system.
And then there is unsigned.
But that does not mean a special real kind is unreachable: it would appear in the list of supported real kinds and with KIND= you can also get variables of that special kind ...
On Friday, June 24, 2022 at 9:00:02 AM UTC-7, Gary Scott wrote:
Neuchips Tapes Out Recommendation Accelerator for World-BeatingI would hope the new floating point formats are on-topic here.
Accuracy: https://www.eetimes.com/neuchips-tapes-out-recommendation-accelerator-for-world-beating-accuracy/
On Friday, June 24, 2022 at 3:43:03 PM UTC-4, gah4 wrote:at least show that the forum is still alive.
On Friday, June 24, 2022 at 9:00:02 AM UTC-7, Gary Scott wrote:Recently there has been much spam about pirated textbooks posted in the Google Groups interface of comp.lang.fortran. I have been flagging it as spam and encourage others to do so. I think posts with an indirect connection to Fortran are fine here and
Neuchips Tapes Out Recommendation Accelerator for World-Beating Accuracy: https://www.eetimes.com/neuchips-tapes-out-recommendation-accelerator-for-world-beating-accuracy/I would hope the new floating point formats are on-topic here.
Sysop: | Keyop |
---|---|
Location: | Huddersfield, West Yorkshire, UK |
Users: | 159 |
Nodes: | 16 (0 / 16) |
Uptime: | 100:03:25 |
Calls: | 3,209 |
Files: | 10,563 |
Messages: | 3,009,979 |