Tom Ross didn't explain it, but did say the compiler developer was quite
enthusiastic about it.
So we have to write a COBOL program, get the new compiler to generate
the code, get a z13 and run z/XDC to see what the instruction actually does!
Not too likely this week, I suppose.
Gary Weinhold
DKL
On 2015-03-12 03:15, [email protected] wrote:
Pages 7 to 8 of this presentation:
https://share.confex.com/share/124/webprogram/Session16609.html
Evidently the code with SIMD instructions is the equivalent of what the
millicode does for SRST, but I may have misinterpreted what was said.
Using the millicoded instruction is evidently less efficient because there is
transition time to get into millicode mode.
And I have no idea how it works.
That was quite interesting. I wasn't SRST in any way but a now I at least got
some clue what one could do with these new instructions. I'm still puzzled by
this by the way:
VGBM VRF26,0x0
VSUMB VRF25,VRF25,VRF26
VSUMQF VRF25,VRF25,VRF26
This would seem to count every space (counted in VRF25) twice instead of only
once. I'm still missing something or maybe I don't quite get the description of
VSUM...
Fred!
-----------------------------------------------------------------
ATTENTION:
The information in this electronic mail message is private and
confidential, and only intended for the addressee. Should you
receive this message by mistake, you are hereby notified that
any disclosure, reproduction, distribution or use of this
message is strictly prohibited. Please inform the sender by
reply transmission and delete the message without copying or
opening it.
Messages and attachments are scanned for all viruses known.
If this message contains password-protected attachments, the
files have NOT been scanned for viruses by the ING mail domain.
Always scan attachments before opening them.
-----------------------------------------------------------------
