Conversation
44d7bbd to
848d712
Compare
|
It was removed in 2022 - whoops. Does it still make sense to have as an option? It kinda looks more complex than most of the CPU extensions (from a virtualisation perspective), so maybe it does. |
| @@ -50,6 +50,9 @@ const AMX_BF16: u8 = 22; // AMX tile computation on bfloat16 numbers | |||
| const AMX_TILE: u8 = 24; // AMX tile load/store instructions | |||
| const AMX_INT8: u8 = 25; // AMX tile computation on 8-bit integers | |||
|
|
|||
| const AMX_FP16: u8 = 21; // AMX tile computation on fp16 numbers | |||
There was a problem hiding this comment.
nit: Your commit message says:
This PR addresses all of the aforementioned issues.
I don't think that's necessary in the commit.
I think it is still a good idea to have amx behind a runtime flag. When amx is enabled, the FPU state size for the task is increased significantly, thus, context switches will be slower. |
The Intel Granite Rapids processors include more AMX related features that are advertised in leaf 0x7 subleaf 0x1. If the VM is not configured to support AMX (the default) then these feature bits need to be masked out. Furthermore Tile information and TMUL information in leaves 0x1d and 0x1e respectively are also purely related to AMX and should also be zeroed whenever AMX support is disabled. Signed-off-by: Oliver Anderson <[email protected]> On-behalf-of: SAP <[email protected]>
848d712 to
390e062
Compare
0d884d3
The Intel Granite Rapids processors include more AMX related features that are advertised in leaf 0x7 subleaf 0x1. If the VM is not configured to support AMX (the default) then these feature bits need to be masked out.
Furthermore Tile information and TMUL information in leaves 0x1d and 0x1e respectively are also purely related to AMX and should also be zeroed whenever AMX support is disabled.
This PR addresses all of the aforementioned issues.