mirror of
https://github.com/torvalds/linux.git
synced 2026-10-06 18:46:02 +02:00
db9deec5a3
Bits 15:14 of NPU_SET_{IFM,OFM}_PRECISION select the activation storage
mode on U85 only. On U65 the same field holds the rounding mode, and the
command stream parser has read it as a storage mode since the driver was
added.
That went unnoticed while unknown values fell through the switch, but
now that they are rejected, every U65 command stream that asks for
natural rounding (2) fails CMDSTREAM_BO_CREATE with -EINVAL. Mesa emits
it for average pooling, concatenation, split, unpack, strided slice, LUT
and argmax, which is 72 failures of the Teflon test suite on an i.MX93.
Truncating rounding (1) is misread as well: it picks the two-tile
address path and computes a bogus feature map size from tile bases the
command stream never set.
Read the field as a storage mode only on the hardware where it is one.
Fixes:
|
||
|---|---|---|
| .. | ||
| amdxdna | ||
| ethosu | ||
| habanalabs | ||
| ivpu | ||
| qaic | ||
| rocket | ||
| drm_accel.c | ||
| Kconfig | ||
| Makefile | ||