freedreno/a6xx: Fix CP_ROQ_THRESHOLDS_1

Just by adding the ROQ_*_STAT registers following the previous pattern
it becomes obvious what these fields actually are.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19551>
This commit is contained in:
Connor Abbott 2022-10-17 16:52:30 +02:00 committed by Marge Bot
parent aba8aea2be
commit 44054b1f3b
2 changed files with 6 additions and 9 deletions

View file

@ -692,7 +692,7 @@ registers:
00000000 0x8aa: 00000000
00000000 0x8ab: 00000000
00000000 CP_PREEMPT_THRESHOLD: 0
8040362c CP_ROQ_THRESHOLDS_1: { RB_LO = 0xb0 | RB_HI = 0xd8 | IB1_START = 0x100 | IB2_START = 0x200 }
8040362c CP_ROQ_THRESHOLDS_1: { MRB_START = 0xb0 | VSD_START = 0xd8 | IB1_START = 0x100 | IB2_START = 0x200 }
010000c0 CP_ROQ_THRESHOLDS_2: { SDS_START = 0x300 | ROQ_SIZE = 0x400 }
00000080 CP_MEM_POOL_SIZE: 0x80
00000000 0x8c4: 00000000

View file

@ -1016,16 +1016,13 @@ to upconvert to 32b float internally?
<!-- all the threshold values seem to be in units of quad-dwords: -->
<reg32 offset="0x08C1" name="CP_ROQ_THRESHOLDS_1">
<doc>
b0..7 seems to contain the size of buffered by not yet processed
RB level cmdstream.. it's possible that it is a low threshold
and b8..15 is a high threshold?
b16..23 identifies where IB1 data starts (and RB data ends?)
b0..7 identifies where MRB data starts (and RB data ends)
b8.15 identifies where VSD data starts (and MRB data ends)
b16..23 identifies where IB1 data starts (and RB data ends)
b24..31 identifies where IB2 data starts (and IB1 data ends)
</doc>
<bitfield name="RB_LO" low="0" high="7" shr="2"/>
<bitfield name="RB_HI" low="8" high="15" shr="2"/>
<bitfield name="MRB_START" low="0" high="7" shr="2"/>
<bitfield name="VSD_START" low="8" high="15" shr="2"/>
<bitfield name="IB1_START" low="16" high="23" shr="2"/>
<bitfield name="IB2_START" low="24" high="31" shr="2"/>
</reg32>