- 19 9月, 2021 3 次提交
-
-
由 Yinan Xu 提交于
This commit adds load balance strategy in issue selection logic for reservation stations. Previously we have a load balance option in ExuBlock, but it cannot work if the function units have feedbacks to RS. In this commit it is removed. This commit adds a victim index option for oldestFirst. For LOAD, the first issue port has better performance and thus we set the victim index to 0. For other function units, we use the last issue port.
-
由 Yinan Xu 提交于
This commit adds timer counters for some important pipeline stages, including rename, dispatch, dispatch2, select, issue, execute, commit. We add performance counters for different types of instructions to see the latency in different pipeline stages.
-
由 zfw 提交于
This PR replaces coremark, microbench, and all perfromence test workloads by corresponding RV64GCB workloads.
-
- 18 9月, 2021 1 次提交
-
-
由 Jay 提交于
Fix fencei and physical tag bugs in ICache
-
- 17 9月, 2021 4 次提交
-
-
由 JinYue 提交于
* Using get_phy_tag function instead of get_tag * This bug happens when using VIPT ICache and setting lage set number
-
由 JinYue 提交于
-
由 rvcoresjw 提交于
* add top IOs * modify dma bus data width from 256 to 128 bits * add top single to SimTop.scala
-
由 Yinan Xu 提交于
This commit adds manual reset for every register in Regfile. Previously the reset is done by add reset values to the registers. However, physically general-purpose register file does not have reset values. Since all the regfile always has the same writeback data, we don't need to explicitly assign reset data.
-
- 16 9月, 2021 2 次提交
-
-
由 zhanglinjuan 提交于
-
由 Yinan Xu 提交于
This commit adds critical_wakeup_*_* counters to indicate which function units wake up the instructions in RS. Previously we have wait_for_src_* counters but they cannot represent where the critical operand (the last waiting operand) comes from. We need these counters to optimize fast wakeup logic. If some instructions critically depend on some other instructions, we can think of how we can optimize the wakeup process. Furthermore, this commit also adds a specific counter for FMAs that wakeup other FMAs' third operand. This helps us to decide which strategy is used for FMA fast issue.
-
- 15 9月, 2021 2 次提交
-
-
由 Lemover 提交于
nothing changed but add one parameter to control if ldtlb and sttlb are the same now there two similar parameters: outReplace: when this is true, two ldtlb are 'same', two sttlb are 'same' refillBothTlb: when this is true, the four tlb are same(require outReplace to be true) * mmu.tlb: add param refillBothTlb to refill both ld & st tlb * mmu.tlb: set param refillBothTlb to false
-
由 Lemover 提交于
-
- 14 9月, 2021 1 次提交
-
-
由 Lemover 提交于
-
- 13 9月, 2021 2 次提交
-
-
由 zhanglinjuan 提交于
-
由 Yinan Xu 提交于
This commit cleans up exception vector usages in backend. Previously the exception vector will go through the pipeline with the uop. However, instructions with exceptions will enter ROB when they are dispatched. Thus, actually we don't need the exception vector when an instruction enters a function unit. * exceptionVec, flushPipe, replayInst are reset when an instruction enters function units. * For execution units that don't have exceptions, we reset their output exception vectors to avoid ROB to record them. * Move replayInst to CtrlSignals.
-
- 12 9月, 2021 3 次提交
-
-
由 Steve Gou 提交于
BPU: Fix bug and significantly reduce false_hit
-
由 Yinan Xu 提交于
This commit moves issue select logic in reservation stations to stage 0 from stage 1. It helps timing of stage 1, which load-to-load requires. Now, reservation stations have the following stages: * S0: enqueue and wakeup, select. Selection results are RegNext-ed. * S1: data/uop read and data bypass. Bypassed results are RegNext-ed. * S2: issue instructions to function units.
-
由 Yinan Xu 提交于
This commit adds 3-bit shift fused instructions. When the program tries to add 8-byte index, these may be used. List of fused instructions added in this commit: * szewl3: `slli r1, r0, 32` + `srli r1, r0, 29` * sr29add: `srli r1, r0, 29` + `add r1, r1, r2`
-
- 11 9月, 2021 4 次提交
-
-
由 zoujr 提交于
-
由 zhanglinjuan 提交于
* MissQueue: send GrantAck immediately after first beat of GrantData * MissQueue: add perf cnts * MissQueue: fix assertion failure in perf cnt * MissQueue: add perf cnts for proportion of load merge / load reject * MissQueue: add perf cnt * MissQueue: fix merge-conflict error
-
由 Lemover 提交于
* mmu.l2tlb: add object TimeOutAssert * mmu.l2tlb: add TimeOutAssert to Repeater * mmu.l2tlb: cut down mem req buffer from 8 ptes to 1 pte each * util: move some utils from MMUBundle to utils
-
由 Yinan Xu 提交于
This commit simplifies status logic in reservations stations. Module StatusArray is mostly rewritten. The following optimizations are applied: * Wakeup now has higher priority than enqueue. This reduces the length of the critical path of ALU back-to-back wakeup. * Don't compare fpWen/rfWen if the reservation station does not have float/int operands. * Ignore status.valid or redirect for srcState update. For data capture, these are necessary and not changed. * Remove blocked and scheduled conditions in issue logic when the reservation station does not have loadWait bit and feedback.
-
- 10 9月, 2021 3 次提交
-
-
由 zoujr 提交于
-
由 Jiawei Lin 提交于
* misc: add submodule huancun * huancun: integrate huancun to SoC as L3 * remove l2prefetcher * update huancun * Bump HuanCun * Use HuanCun instead old L2/L3 * bump huancun * bump huancun * Set L3NBanks to 4 * Update rocketchip * Bump huancun * Bump HuanCun * Optimize debug configs * Configs: fix L3 bug * Add TLLogger * TLLogger: fix release ack address * Support write prefix into database * Recoding more tilelink info * Add a database output format converter * missqueue: add difftest port for memory difftest during refill * misc: bump difftest * misc: bump difftest & huancun * missqueue: do not check refill data when get Grant * Add directory debug tool * config: increase client dir size for non-inclusive cache * Bump difftest and huancun * Update l2/l3 cache configs * Remove deprecated fpga/* * Remove cache test * Remove L2 preftecher * bump huancun * Params: turn on l2 prefetch by default * misc: remove duplicate chisel-tester2 * misc: remove sifive inclusive cache * bump difftest * bump huancun * config: use 4MB L3 cache * bump huancun * bump difftest * bump difftest Co-authored-by: Nwangkaifan <wangkaifan@ict.ac.cn> Co-authored-by: NTangDan <tangdan@ict.ac.cn>
-
由 Yinan Xu 提交于
This commit changes how uop and data are read in reservation stations. It helps the issue timing. Previously, we access payload array and data array after we decide the instructions that we want to issue. This method makes issue selection and array access serialized and brings critial path. In this commit, we add one more read port to payload array and data array. This extra read port is for the oldest instruction. We decide whether to issue the oldest instruction and read uop/data simultaneously. This change reduces the critical path to each selection logic + read + Mux (previously it's selection + arbitration + read). Variable oldestOverride indicates whether we choose the oldest ready instruction instead of the normal selection. An oldestFirst option is added to RSParams to parameterize whether we need the age logic. By default, it is set to true unless the RS is for ALU. If the timing for aged ALU rs meets, we will enable it later.
-
- 09 9月, 2021 3 次提交
-
-
由 Lemover 提交于
* mmu.l2tlb: l2tlb now support multiple parallel mem accesses 8 missqueue entry and 1 page table worker mq entry only supports page leaf entry ptw supports all the three level entries * mmu.tlb: fix bug of mq.refill_vpn and out.ready * mmu.tlb: fix bug of perf counter * mmu.tlb: l2tlb's l3 now 128 sets and 4 ways * mmu.tlb: miss queue now will 'merge' same mem req addr * mmu.l2tlb: ptw doesn't access last level pte * mmu.l2tlb: add mem req mask into ptw func block_decoupled doesn't work well and has bug in signal ready * mmu.l2tlb: fix bug of sfence to fsm add a new state s_check_pte to ptw fsm now take memPte from outside, doesn't store it inside mem_resp_valid will arrive a cycle before mem_resp_data * mmu.l2tlb: rm some state in fsm * mmu.tlb: set itlb default size * mmu.l2tlb: unkonwn mq wait bug, change code style to avoid it * mmu.l2tlb: opt, mq's entry with cache_l3 would not be blocked * mmu.l2tlb: add many time out assert * mmu.l2tlb: fix bug of mq enq state change & wait_id * Revert "mmu.tlb: l2tlb's l3 now 128 sets and 4 ways" This reverts commit 216e4192e4b01e68ce5502135318bc2473434907. * Revert "mmu.tlb: set itlb default size" This reverts commit 670bf1e408384964c601c0a55defbc767eb80698. * mmu.l2tlb: set miss queue size to 9 and set filter size to 8 if they are equal, itlb may loss its req
-
由 Yinan Xu 提交于
This commit adds some simple instruction fusion cases in decode stage. Currently we only implement instruction pairs that can be fused into RV64GCB instructions. Instruction fusions are detected in the decode stage by FusionDecoder. The decoder checks every two instructions and marks the first instruction fused if they can be fused into one instruction. The second instruction is removed by setting the valid field to false. Simple fusion cases include sh1add, sh2add, sh3add, sexth, zexth, etc. Currently, ftq in frontend needs every instruction to commit. However, the second instruction is removed from the pipeline and will not commit. To solve this issue, we temporarily add more bits to isFused to indicate the offset diff of the two fused instruction. There are four possibilities now. This feature may be removed later. This commit also adds more instruction fusion cases that need changes in both the decode stage and the funtion units. In this commit, we add some opcode to the function units and fuse the new instruction pairs into these new internal uops. The list of opcodes we add in this commit is shown below: - szewl1: `slli r1, r0, 32` + `srli r1, r0, 31` - szewl2: `slli r1, r0, 32` + `srli r1, r0, 30` - byte2: `srli r1, r0, 8` + `andi r1, r1, 255` - sh4add: `slli r1, r0, 4` + `add r1, r1, r2` - sr30add: `srli r1, r0, 30` + `add r1, r1, r2` - sr31add: `srli r1, r0, 31` + `add r1, r1, r2` - sr32add: `srli r1, r0, 32` + `add r1, r1, r2` - oddadd: `andi r1, r0, 1`` + `add r1, r1, r2` - oddaddw: `andi r1, r0, 1`` + `addw r1, r1, r2` - orh48: mask off the first 16 bits and or with another operand (`andi r1, r0, -256`` + `or r1, r1, r2`) Furthermore, this commit adds some complex instruction fusion cases to the decode stage and function units. The complex instruction fusion cases are detected after the instructions are decoded into uop and their CtrlSignals are used for instruction fusion detection. We add the following complex instruction fusion cases: - addwbyte: addw and mask it with 0xff (extract the first byte) - addwbit: addw and mask it with 0x1 (extract the first bit) - logiclsb: logic operation and mask it with 0x1 (extract the first bit) - mulw7: andi 127 and mulw instructions. Input to mul is AND with 0x7f if mulw7 bit is set to true.
-
由 Lemover 提交于
* mmu.tlb: l2tlb's l3 now 128 sets and 4 ways * mmu.tlb: set itlb default size
-
- 08 9月, 2021 1 次提交
-
-
由 zfw 提交于
* Alu: fix andn, orn, xnor * Decode: change instruction name
-
- 06 9月, 2021 4 次提交
-
-
由 Steve Gou 提交于
add new ittage indirect target predictor
-
由 William Wang 提交于
dcache,lq: make dcache to lq refill faster
-
由 Yinan Xu 提交于
This commit assigns exu.io.out.fflags to RegNext(fu.io.fflags) if the function unit has fastUopOut but has not implemented it. Previously it causes a bug that fflags may be one cycle earlier than expected. This commit also removes the extra logic in FmacExeUnit and FmiscExeUnit. They are exactly the same as ExeUnit now.
-
由 YikeZhou 提交于
* backend, rename: support elimination of mv inst whose lsrc=0 [known bug] instr page fault not properly raised after sfence.vma * backend, roq: [bug fix] won't label me with exception as writebacked
-
- 05 9月, 2021 5 次提交
-
-
由 Jiawei Lin 提交于
-
由 Lingrui98 提交于
-
由 Yinan Xu 提交于
This commit adds support for load balance between different issue ports when the function unit is not pipelined and the reservation station has more than one issue ports. We use a ping pong bit to decide which port to issue the instruction. At every clock cycle, the bit is flipped.
-
由 Lemover 提交于
* mmu.l2tlb: l2tlb now support multiple parallel mem accesses 8 missqueue entry and 1 page table worker mq entry only supports page leaf entry ptw supports all the three level entries * mmu.tlb: fix bug of mq.refill_vpn and out.ready
-
由 Yinan Xu 提交于
This commit adds assertion in MaskData to check the width of mask and data. When the width of mask is smaller than the width of data, (~mask & data) and (mask & data) will always clear the upper bits of the data. This usually causes unexpected behavior. This commit adds explicit width declarations where MaskData is used.
-
- 04 9月, 2021 2 次提交
-
-
由 Jiawei Lin 提交于
* Makefile: add '--gen-mem-verilog'
-
由 Jiawei Lin 提交于
* FMA: spearate fadd/fmul/fma * exu: enable fast uop out from fmacExeUnit Co-authored-by: NYinan Xu <xuyinan@ict.ac.cn>
-