> By the way, the code object V4 supports default "XNACK" value as "ANY". The compiler, then, produces code, which executes on a target configured for either value of the setting impacting the overall performance." "If a target feature is not specified, it defaults to a new concept of "any". So, if no "XNACK" target feature is specified, the generated code can be loaded and executed in a process with either setting of XNACK replay (but may be less performant) as mentioned here: "īy the way, the code object V4 supports default "XNACK" value as "ANY". That means runtimes older than ROCm 4.1 and an upcoming PAL version will not be able to run them. But we want to move the compilers to generate the V4 version by default. "We have worked hard to make the ROCr runtime and PAL runtime be able to load all earlier versions of code objects. So, I guess using two different driver versions may cause a compatibility issue for some cases, particularly when you generate the offline binary with a newer driver and try to run it with an older driver that doesn't support the new binary format. On windows, they are also updating the PAL implementation to include this support. With ROCm 4.1 release, this is already supported. From the feedback, it looks like the "code object V4" is going to be the default code version generated by the compilers ( ). However, on Windows, it seems like the XNACK configuration is fixed per target and currently it doesn't support to change the settings. >Is there a way to change the default value? If so, how does one do it?Īs I've come to know, on some targets there is a way to configure the Linux boot BIOS to set the XNACK setting.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |