- 06 6月, 2022 3 次提交
-
-
由 Jenius 提交于
* add SRAM ready (resetfinish) condition for *Array (metaArray/dataArray) req.ready
-
由 Jenius 提交于
* fix mmio_resend_af wrong assignment * fix wb_half_flush missOffset(using wb_lastIdx instead of PredictWidth -1) * change pipeline ready condition (this_ready = this_stage_fire || this_stage_empty) * delete 500-cycle ready condition (toICache(*).ready means the SRAM has been reset and ready for read)
-
由 Lemover 提交于
* bump huancun, update Chisel3, revert sram hazard enhancement * util.sram: rm a r/w hazard mux which is not needed. bump huancun
-
- 31 5月, 2022 2 次提交
-
-
由 Yinan Xu 提交于
-
由 Jiuyang Liu 提交于
* fix for chipsalliance/rocket-chip#2967 * decode: fix width of BitPat(?) in decode logic Co-authored-by: NYinan Xu <xuyinan@ict.ac.cn>
-
- 29 5月, 2022 1 次提交
-
-
由 Jenius 提交于
-
- 27 5月, 2022 1 次提交
-
-
由 Yinan Xu 提交于
Previously we made a mistake to connect rtc_clock to rtcTick for CLINT. rtcTick should be on io_clock clock domain and asserted only one clock cycle in io_clock for every cycle in rtc_clock. We add sampling registers in this commit to fix this.
-
- 26 5月, 2022 1 次提交
-
-
由 Jiuyang Liu 提交于
-
- 25 5月, 2022 1 次提交
-
-
由 Steve Gou 提交于
sramtemplate: fix waymask in FoldedSRAMTemplate
-
- 24 5月, 2022 1 次提交
-
-
由 Lingrui98 提交于
-
- 22 5月, 2022 1 次提交
-
-
由 wakafa 提交于
Provide two issue template.
-
- 21 5月, 2022 1 次提交
-
-
由 Lemover 提交于
-
- 12 5月, 2022 1 次提交
-
-
由 Hazard 提交于
-
- 11 5月, 2022 3 次提交
-
-
由 William Wang 提交于
* difftest: disable runahead to make vcs happy * difftest: bump huancun to make vcs happy * difftest: bump difftest and ready-to-run * difftest support ramsize and paddr base config * 8GB/16GB nemu so are provided by ready-to-run * ci: update nightly ci, manually set ram_size * difftest: bump huancun to make vcs happy * difftest,nemu: support run-time assign mem size * ci: polish nightly ci script
-
由 wakafa 提交于
-
由 Yinan Xu 提交于
An instruction with exceptions may have arbitrary instr values and may be decoded into WFI instructions, which cause errors.
-
- 09 5月, 2022 4 次提交
-
-
由 Li Qianruo 提交于
-
由 Jenius 提交于
-
由 Yinan Xu 提交于
Use 16GB memory as default. SPEC CPU2017 requires more than 8GB memory.
-
由 Steve Gou 提交于
* sc: fix a performance bug * tage: fix number of use-alt-on-na counters * tage: update provider u-bit according to provider results
-
- 07 5月, 2022 1 次提交
-
-
由 Guokai Chen 提交于
-
- 06 5月, 2022 4 次提交
-
-
由 Haojin Tang 提交于
* feat: parameterize load/store pipeline, etc. * fix: use LoadPipelineWidth rather than LoadQueueSize * fix: parameterize `rdataPtrExtNext` * SBuffer: fix idx update logic * atomic: parameterize atomic logic in `MemBlock` * StoreQueue: update allow enque requirement * feat: support one load/store pipeline * feat: parameterize `EnsbufferWidth` * chore: resharp codes for better generated name
-
由 Yinan Xu 提交于
-
由 William Wang 提交于
* chore: remove sc too many fail assertion * chore: use XSWarn()
-
由 Yinan Xu 提交于
difftest: fix support for Spike
-
- 05 5月, 2022 5 次提交
-
-
由 Yinan Xu 提交于
-
由 William Wang 提交于
s1_tag_match_way is vaild iff tag_read.valid and meta_read.valid in s0 for the same req
-
由 Yinan Xu 提交于
-
由 Yinan Xu 提交于
XiangShan does not support fs=0 because when fs=0, all floating-point states are not accessible. Spike supports fs=0. To diff with Spike, we temporarily set fs to 1 when initialized.
-
由 Yinan Xu 提交于
Add support for the WFI instruction
-
- 04 5月, 2022 2 次提交
- 29 4月, 2022 1 次提交
-
-
由 Yinan Xu 提交于
-
- 28 4月, 2022 2 次提交
-
-
由 Yinan Xu 提交于
To test WFI, we delay the interrupts for more cycles.
-
由 Yinan Xu 提交于
The RISC-V WFI instruction is previously decoded as NOP. This commit adds support for the real wait-for-interrupt (WFI). We add a state_wfi FSM in the ROB. After WFI leaves the ROB, the next instruction will wait in the ROB until an interrupt.
-
- 26 4月, 2022 1 次提交
-
-
由 Jay 提交于
*** Description *** - During multi-thread verilator emulation, the reset_ncycle(size_t cycles) function will trigger the flash_read() function where a NULL pointer *flash_base will be used since we init flash after the reset_ncycle. - This bug is triggered in some seeds, while others runs in a normal way. *** Solution *** - init flash before reset_cycles()
-
- 25 4月, 2022 3 次提交
-
-
由 wakafa 提交于
* difftest: fix false-positive difftest intRF writeback, adapt to new difftest API * csr: skip mip difftest * bump difftest * bump difftest
-
由 cui fliter 提交于
* fix some typos Signed-off-by: Ncuishuang <imcusg@gmail.com>
-
由 Jay 提交于
* Bump difftest and ready-to-run * add copy-and-run test for CI * Bump ready-to-run: update NEMU * CI: specify reference in ready-to-run repo
-
- 14 4月, 2022 1 次提交
-
-
由 Lemover 提交于
old missqueue: cache req miss slot and mem access-er Problem: these two func are totally different, make mq hard to handle in a single select policy. Solution: divide these two funciton into two module. new MissQueue: only hold reqs that page cache miss and need re-req cache, a simple flushable queue llptw: Last level ptw, only access ptes, priorityMux queue * mmu: rename PTW.scala to L2TLB.scala * mmu: rename PTW to L2TLB * mmu: rename PtwFsm to PTW * mmu.l2tlb: divide missqueue into 'missqueue' and llptw old missqueue: cache req miss slot and mem access-er Problem: these two func are totally different, make mq hard to handle in single select policy. Solution: divide these two funciton into two module. new MissQueue: only hold reqs that page cache miss and new re-req cache llptw: Last level ptw, only access ptes * mmu.l2tlb: syntax bug that misses io assign * mmu.l2tlb: fix bug that mistakes ptw's block signal
-