- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
To confirm the statement that loads may be reordered with earlier stores on IA64 manual 8.2.3.4, I run a litmus test on a X86_64 machine(i5-8500) and the result confused me.
Here is the test program:
X86 SB
"Fre PodWR Fre PodWR"
{x=0; y=0;}
P0 | P1 ;
MOV [x],$1 | MOV [y],$1 ;
MOV EAX,[y] | MOV EBX,[x] ;
exists (0:EAX=0 /\ 1:EBX=1)
Here is the result:
Test SB Allowed
Histogram (2 states)
500000:>0:EAX=1; 1:EBX=0;
500000*>0:EAX=0; 1:EBX=1;
Ok
If Store-Load for can be reordered ,there will be result that EAX=0 && EBX = 0, but the result is not like this.
Can someone help me ?
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello LA_not_los_angeles,
Thank you for posting on the Intel® communities.
I would like to let you know that we have a specific community forum where you will receive appropriate support, it is the Intel Developer Zone. To access the forum, just use the following link:
- https://community.intel.com/t5/Software/ct-p/software-products
- https://software.intel.com/content/www/us/en/develop/home.html
Also, you may find more details here:
Regards,
Deivid A.
Intel Customer Support Technician

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page