#
bb2f3f51 |
| 12-Jul-2024 |
Tang Haojin <[email protected]> |
perf: use perfUtils in `Utility` (#3190)
Currently, log and perf utilities such as `XSPerfAccumulate` are
implemented in many repositories like XiangShan, CoupledL2 and HuanCun.
This PR unifies th
perf: use perfUtils in `Utility` (#3190)
Currently, log and perf utilities such as `XSPerfAccumulate` are
implemented in many repositories like XiangShan, CoupledL2 and HuanCun.
This PR unifies them and put them in Utility repository.
show more ...
|
#
2d12882c |
| 09-Jun-2024 |
xiaofeibao <[email protected]> |
FuConfig: split dataBits into destDataBits and srcDataBits for distinguish input and output data width
|
#
81cbff07 |
| 17-Apr-2024 |
chengguanghui <[email protected]> |
FU: fix mgu for body elements's agnostic
* Modify the signal names about divided vector elements to be consistent with RVV Spec.
|
#
e8e02b74 |
| 19-Feb-2024 |
sinceforYy <[email protected]> |
rv64v: add fire sign as enable of RegNext
|
#
904d2184 |
| 29-Dec-2023 |
Ziyue Zhang <[email protected]> |
rv64v: fix vxsat and vd compute for fixed-point instruction
|
#
92c6b7ed |
| 08-Nov-2023 |
zhanglinjuan <[email protected]> |
Mgu: use sew as element width instead of eew for indexed loads/stores
|
#
c33d4a9e |
| 16-Oct-2023 |
Xuan Hu <[email protected]> |
vector: convert mgu's assertion to EX_II
|
#
83ba63b3 |
| 11-Oct-2023 |
Xuan Hu <[email protected]> |
fix merge error
|
#
b3e2881c |
| 04-Sep-2023 |
xiaofeibao-xjtu <[email protected]> |
assert: mgu's vl must <= vlmax
|
#
1a6cfb3d |
| 26-Jun-2023 |
xgkiri <[email protected]> |
fix: use mask to generate the vxsat
|
#
cdf8c16c |
| 26-Jun-2023 |
xgkiri <[email protected]> |
modify the fix-point vector alu wrapper and mgu
|
#
d16a780c |
| 29-May-2023 |
Xuan Hu <[email protected]> |
vector: fix source data of vmadd and vnmsub
* The input of VIMac data module should be exchanged when opcode is vmadd or vnmsub, since source data are not exchanged in data module.
|
#
11ca0f73 |
| 27-May-2023 |
Xuan Hu <[email protected]> |
vector: fix VIMacU widen insts error
* Vector source data should be localed at high bits of vimacs.vs1|2, when widen=1 and vuopIdx is a odd number * The odd uop of widen insts should use high part o
vector: fix VIMacU widen insts error
* Vector source data should be localed at high bits of vimacs.vs1|2, when widen=1 and vuopIdx is a odd number * The odd uop of widen insts should use high part of vs1 and vs2. * The eew of widen insts should be double of sew.
show more ...
|
#
205fce4e |
| 26-May-2023 |
Xuan Hu <[email protected]> |
vector: fix VIMacU error
|
#
2ee1e93d |
| 26-May-2023 |
Xuan Hu <[email protected]> |
vector: add VImacU wrapper and configs
|