Hansung Kim
|
327615e330
|
Add state regs and init/writeback transition
|
2024-10-14 17:28:51 -07:00 |
|
Hansung Kim
|
6a3aa549d3
|
Add skeleton for Hopper Tensor Core
|
2024-10-14 15:02:25 -07:00 |
|
Hansung Kim
|
32c7aed263
|
Fix fp exception by rounding right after MulRawFN
|
2024-08-07 11:09:55 -07:00 |
|
Hansung Kim
|
d8674b753e
|
Support fp16 input, fp32 output in TensorDPU
TODO could see improvement towards handling raw format as much as
possible.
|
2024-08-01 22:01:26 -07:00 |
|
Hansung Kim
|
4e3ed96c94
|
Support fp16 operand/accum in TensorDPU
TODO: fp32 accum
|
2024-07-31 16:37:01 -07:00 |
|
Hansung Kim
|
17886dc050
|
Implement proper stalls for dpu
|
2024-05-29 16:21:12 -07:00 |
|
Hansung Kim
|
4a43d0126d
|
Make dpu 2-stage
For debugging, need to revert.
|
2024-05-29 13:31:38 -07:00 |
|
Hansung Kim
|
40b27c9600
|
Fix test for DPU
|
2024-05-28 21:18:51 -07:00 |
|
Hansung Kim
|
907150e51c
|
Add accumulation to dpu
|
2024-05-28 18:40:47 -07:00 |
|
Hansung Kim
|
3b1ab4e10d
|
Write four-element dpu without accumulation
|
2024-05-28 18:27:56 -07:00 |
|
Hansung Kim
|
db889c5e22
|
Disable coalescer chiseltests
|
2024-05-28 16:43:02 -07:00 |
|
Hansung Kim
|
4dba0def01
|
Do proper recoding and boxing for FMA input
|
2024-05-28 16:41:44 -07:00 |
|
Hansung Kim
|
615815acf5
|
Add placeholder tensor core DPU module
|
2024-05-27 21:16:53 -07:00 |
|
Hansung Kim
|
7c7752a5a2
|
Disable uncoalescer unit test temporarily
|
2023-05-20 00:23:18 -07:00 |
|
Hansung Kim
|
1243fd75a2
|
Fix old param name in XBarUnitTest
|
2023-05-20 00:22:40 -07:00 |
|
Vamber Yang
|
ebf81babc1
|
Modified WithCoalescer to dynamically configure databusWidth and MaxCoalSize according to underlying SoC setting,
This makes running perf numbers easier
|
2023-05-16 05:59:41 -07:00 |
|
Richard Yan
|
80ffc6cc73
|
write striping across banks
|
2023-05-12 00:31:28 -07:00 |
|
Richard Yan
|
4e4b993287
|
Merge branch 'graphics' of https://github.com/hansungk/rocket-chip into graphics
|
2023-05-11 21:50:42 -07:00 |
|
Hansung Kim
|
9b7080a852
|
Delete old inflight table unittest
|
2023-05-11 18:50:47 -07:00 |
|
Hansung Kim
|
226e1d2d84
|
Fix uncoalescer unittest even more
|
2023-05-11 18:36:09 -07:00 |
|
Hansung Kim
|
b95b59cce0
|
Fix uncoalescer unittest
|
2023-05-11 18:30:15 -07:00 |
|
Hansung Kim
|
df68bfec84
|
Remove module dependency for uncoalescer instantiation
for easier unittesting. now builds.
|
2023-05-11 18:20:19 -07:00 |
|
Richard Yan
|
f0a7fd852a
|
WIP bank striping
|
2023-05-11 18:12:25 -07:00 |
|
Hansung Kim
|
406f90b633
|
De-duplicate equivalent Request bundles using NonCoal/Coal variants
|
2023-05-11 15:55:15 -07:00 |
|
Hansung Kim
|
300eff4f9a
|
Fix misleading maxSize param in Req/RespQueueEntry
|
2023-05-10 23:25:57 -07:00 |
|
Richard Yan
|
7bd9fd43f8
|
Merge branch 'graphics' of https://github.com/hansungk/rocket-chip into graphics
|
2023-05-09 09:37:59 -07:00 |
|
Richard Yan
|
bce2c6230f
|
more test fixes
|
2023-05-09 09:36:29 -07:00 |
|
Hansung Kim
|
2d4e28e862
|
Use WithoutTLMonitors to slightly speed up chiseltests
|
2023-05-08 14:38:15 -07:00 |
|
Hansung Kim
|
737a760fcd
|
Enable coverage tests for chiseltest
|
2023-05-07 22:58:20 -07:00 |
|
Hansung Kim
|
a6dbfc3901
|
Fix config for unittest
|
2023-05-07 18:38:23 -07:00 |
|
Richard Yan
|
d2e56be157
|
update unit tests for new timing behavior & config
|
2023-05-07 14:35:53 -07:00 |
|
Richard Yan
|
86e7d3d60d
|
numerous coalescer bug fixes + working unit test
|
2023-05-07 02:31:28 -07:00 |
|
Hansung Kim
|
42b03edbf7
|
Update import path to cde to reflect upstream changes
|
2023-05-05 14:51:13 -07:00 |
|
Hansung Kim
|
1fa2e36740
|
Add global enable to coalescer config
|
2023-05-04 16:38:38 -07:00 |
|
Richard Yan
|
ebd6c54d67
|
tl graph changes, coalescer bug fixes & coalescer unit test
|
2023-05-03 17:58:25 -07:00 |
|
Richard Yan
|
459c14bb62
|
add testing infrastructure for coalescing unit
|
2023-05-02 17:38:49 -07:00 |
|
Richard Yan
|
997b421c42
|
active byte lane implementation for multi coalescer & add one shift queue test
|
2023-05-02 00:07:45 -07:00 |
|
Richard Yan
|
6757ea1bbd
|
shift queue bug fixes + new unit test
|
2023-05-01 00:51:31 -07:00 |
|
Richard Yan
|
55b2f7c33f
|
reworked shift queue
|
2023-04-30 17:59:10 -07:00 |
|
Richard Yan
|
12d2912368
|
Merge branch 'graphics' of https://github.com/hansungk/rocket-chip into graphics
|
2023-04-28 20:51:08 -07:00 |
|
Richard Yan
|
c655874470
|
width widget in DummyCoalescingUnitTB
|
2023-04-28 20:47:47 -07:00 |
|
Hansung Kim
|
fec788d648
|
Invalidate head when dequeued but allowShift was false
|
2023-04-28 15:46:45 -07:00 |
|
Hansung Kim
|
a49931ae60
|
Add invalidate/enq test case for depth=1 CoalShiftQueue
|
2023-04-28 15:08:39 -07:00 |
|
Hansung Kim
|
44d3c09b6d
|
Fix used bit logic when invalidating but not dequeueing
|
2023-04-28 14:58:47 -07:00 |
|
Hansung Kim
|
2622bf04d3
|
Add allowShift to CoalShiftQueue IO to synchronize shifting
|
2023-04-28 14:12:51 -07:00 |
|
Hansung Kim
|
f7bf277e89
|
Fix unittest for CoalShiftQueue deq.valid change
|
2023-04-28 00:50:34 -07:00 |
|
Hansung Kim
|
b5b1a7da66
|
Add uncoalescer test case for all-lane-same-offset case
|
2023-04-27 21:53:36 -07:00 |
|
Hansung Kim
|
edc05d51e6
|
Fix not respecting invalidate.valid from coalescer
|
2023-04-27 21:35:26 -07:00 |
|
Hansung Kim
|
699520073e
|
Make maxSize accessor function
|
2023-04-27 20:34:20 -07:00 |
|
Hansung Kim
|
ba2bc3020b
|
Fix truncation bug in matchCount
|
2023-04-27 20:24:15 -07:00 |
|