chore(Parameters): remove the incorrect parameter description (#4391)

This is a misrepresentation; currently, there is only one item in the fofbuffer.

fix(trace): fix parameters of trace (#4561)

fix(LSU): misalign writeback aligned raw rollback (#4476)

By convention, we need to make `rollback` and `writeback` happen at the
same time, and not make `writeback` earlier than `rollback`.

Curren

fix(LSU): misalign writeback aligned raw rollback (#4476)

By convention, we need to make `rollback` and `writeback` happen at the
same time, and not make `writeback` earlier than `rollback`.

Currently, the `rollback` generated by raw occurs at `s4`.
A normal store would take an extra N beats after the end of s3 (based on
the number of RAWQueue entries, which is now 1 beat), which is
equivalent to `writeback` at `s4`
And misaligned would `writeback` at `s2`, then `writeback` after
switching to `s_wb` state, which is equivalent to `writeback` at `s3`

---

This pr adjusts the misaligned `writeback` logic to align with the
`StoreUnit`.
At the same time, it unified the way to calculate the number of beats.

show more ...

refactor(DFT): refactor `DFT` IO (#4530)

feat(backend): make wfi timeout configurable (#4491)

feat(Sram): add `SRAM_CTL` interface (#4474)

* add `SRAM_CTL` interface for SRAMTemplate
* use `SRAM_WITH_CTL` to enable,
e.g. `make sim-verilog CONFIG=KunminghuV2Config RELEASE=1
SRAM_WITH_CTL=

feat(Sram): add `SRAM_CTL` interface (#4474)

* add `SRAM_CTL` interface for SRAMTemplate
* use `SRAM_WITH_CTL` to enable,
e.g. `make sim-verilog CONFIG=KunminghuV2Config RELEASE=1
SRAM_WITH_CTL=1`

show more ...

fix(LoadUnit): enable EnableAccurateLoadError (#4363)

feat(dfx): integerate dfx components (#4312)

fix(StoreQueue): fix threshold condition for fore write sbuffer (#4306)

Previously, `ForceWrite` was conditioned to write dead (60, 55), which
no longer applies after we adjusted `StoreQueueSize`.

fix(StoreQueue): fix threshold condition for fore write sbuffer (#4306)

Previously, `ForceWrite` was conditioned to write dead (60, 55), which
no longer applies after we adjusted `StoreQueueSize`.

---

Now a more reasonable parameterized setting is used.
However, the conditions for optimal performance still need to be tested.

show more ...

feat(bitmap/memenc): support memory isolation by bitmap checking and memory encrpty used SM4-XTS (#3980)

- Add bitmap module in MMU for memory isolation
- Add memory encryption module based on AXI p

feat(bitmap/memenc): support memory isolation by bitmap checking and memory encrpty used SM4-XTS (#3980)

- Add bitmap module in MMU for memory isolation
- Add memory encryption module based on AXI protoco
- Can don't using these modules by setting the option `HasMEMencryption`
& `HasBitmapCheck` to false

show more ...

chore(dispatch): remove useless code and files (#4288)

chore(Parameters): add zawrs, zihintntl and ziccamoa into isa string (#4219)

submodule(utility): introduce XSPerfLevel for performance counter (#4238)

This change introduce XSPerfLevel, including
`VERBOSE`/`NORMAL`/`CRITICAL`. Only counters with level greater or equal
than t

submodule(utility): introduce XSPerfLevel for performance counter (#4238)

This change introduce XSPerfLevel, including
`VERBOSE`/`NORMAL`/`CRITICAL`. Only counters with level greater or equal
than threhold will be instantiated, which will reduce utilization and
compile time on Pallaium.

PerfLevel therhold can be set in command line, `VERBOSE` by default to
apply all counters.
An example usage as follows:
SIM_ARGS="--perf-level CRITICAL" or
PLDM_ARGS="--perf-level CRITICAL" PLDM=1

PerfLevel param is also `VERBOSE` by default, which means all counters
will be ignored now if threhold greater than that. User can explicitly
set params to keep some important counters instantiated, as follows:
XSPerfAccumulate(xx, yy, perfLevel = XSPerfLevel.CRITICAL)

show more ...

perf(Uncache): add merge policy when entering (#4154)

# Background

## Problem

How to design a more efficient entry rule for a new load/store request
when a load/store with the same address already

perf(Uncache): add merge policy when entering (#4154)

# Background

## Problem

How to design a more efficient entry rule for a new load/store request
when a load/store with the same address already exists in the `ubuffer`？

* **Old Design**: Always **reject** the new request.
* **New Desig**n: Consider **merging** requests.

## Merge Scenarios

‼️If the new one can be merge into the existing one, both need to be
`NC`.

1. **New Store Request:**
1. **Existing Store:** Merge (the new store is younger).
2. **Existing Load:** Reject.

2. **New Load Request:**
1. **Existing Load:** Merge (the new load may be younger or older. Both
are ok to merge).
2. **Existing Store:** Reject.

# What this PR do?

## 1. Entry Actions

1. **Allocate** a new entry and mark as `valid`
1. When there is no matching address.
2. **Allocate** a new entry and mark as `valid` and `waitSame`:
1. When there is a matching address, and:
* The virtual addresses and attributes are the same.
* The older entry is either selected to issue or issued.
3. **Merge** into an Existing Entry:
1. When there is a matching address, and:
* The virtual addresses and attributes are the same.
* The older entry is **not** selected to issue or issued.
4. **Reject** the New Request:
1. When the ubuffer is full.
2. When there is a matching address, but:
* The virtual addresses or attributes are **different**.

**NOTE:** According to the definition in the TL-UL SPEC, the `mask` must
be continuous and naturally aligned, and the `addr` must correspond to
the mask. Therefore, the "**same attributes**" here introduces a new
condition: the merged `mask` must meet the requirements of being
continuous and naturally aligned (function `continueAndAlign`). During
merging, the block offset of addr must be synchronously updated in
`UncacheEntry.update`.

## 2. Handshake Mechanism Between `LoadQueueUncache (M)` and `Uncache
(S)`

> `mid`: master id
>
> `sid`: slave id

**Old Design:**

- `M` sends a `req` with a **`mid`**.
- `S` receives the `req`, records the **`mid`**.
- `S` sends a `resp` with the **`mid`**.
- `M` receives the `resp` and matches it with the recorded **`mid`**.

**New Design:**

- `M` sends a `req` with a **`mid`**.
- `S` receives the `req` and responds with `{mid, sid}` .
- `M` matches it with the **`mid`** and updates its record with the
received **`sid`**.
- `S` sends a `resp` with the its **`sid`**.
- `M` receives the `resp` and matches it with the recorded **`sid`**.

**Benefit:** The new design allows `S` to merge requests when new
request enters.

## 3. Forwarding Mechanism

**Old Design:** Each address in the `ubuffer` is **unique**, so
forwarding is straightforward based on a match.

**New Design:**

* A single address may have up to two entries matched in the `ubuffer`.
* If it has two matched enties, it must be true that one entry is marked
`inflight` and the other entry is marked `waitSame`. In this case, the
forwarded data comes from the merged data of two entries, with the
`inflight` entry being the older one.

## 4. Bug Fixes

1. In the `loadUnit`, `!tlbMiss` cannot be directly used as `tlbHit`,
because when `tlbValid` is false, `!tlbMiss` can still be true.
2. `Uncache` state machine transition: The state indicating "**able to
send requests**" (previously `s_refill_req`, now `s_inflight`) should
not be triggered by `reqFire` but rather by `acquireFire`.

<img width="747" alt="image"
src="https://github.com/user-attachments/assets/75fbc761-1da8-43d9-a0e6-615cc58cefef"
/>

# Evaluation

- ✅ timing
- ✅ performance

| Type | 4B*1000 | Speedup1-IO | 1B*4096 | Speedup2-IO |
| -------------- | ------- | ----------- | ------- | ----------- |
| IO | 51026 | 1 | 208149 | 1.00 |
| NC | 42343 | 1.21 | 169248 | 1.23 |
| NC+OT | 20379 | 2.50 | 160101 | 1.30 |
| NC+OT+mergeOpt | 16308 | 3.13 | 126369 | 1.65 |
| cache | 1298 | 39.31 | 4410 | 47.20 |

show more ...

feat(Config): add yaml parser for complicated parametrization (#4147)

This commit enables complicated parameterization by yaml parsing. We use
circe to do this.

In this commit, we implement 6 confi

feat(Config): add yaml parser for complicated parametrization (#4147)

This commit enables complicated parameterization by yaml parsing. We use
circe to do this.

In this commit, we implement 6 configurations:

- PmemRanges: physical memory ranges
- PMAConfigs
- CHIAsyncBridge: set depth to 0 to disable it
- L2CacheConfig
- L3CacheConfig
- DebugModuleBaseAddr

For better human-readability, this commit changes `WithNKBL2/3` to
`L2/3CacheConfig`, changing to case classes, and making the first
parameter only accept human-readable size configuration like `0.5 MB` or
`256kB`.

This commit also changes PMAConfigs and PmemRanges into List of case
classes.

show more ...

chore(Parameters): add svnapot extension string (#4133)

feat(ICache): ECC error injection (#4044)

This PR is part of *RAS(Reliability, Accessibility, Serviceability)* error recovery features.

- Add a series of mmio-mapped CSR to control ICache ECC check

feat(ICache): ECC error injection (#4044)

This PR is part of *RAS(Reliability, Accessibility, Serviceability)* error recovery features.

- Add a series of mmio-mapped CSR to control ICache ECC check & ECC inject features
- Implement ICache ECC injection
- M-state software can write `eccctrl` to trigger error injection to meta/dataArray, next read can trigger auto-recovery (implemented in #3899)
- Remove custom CSR `Sfetchctl`

# Details
## CSR
The base address of the added mmio-mapped CSR is `0x38022080` and the registers is defined as below:
```
64 10 7 4 2 1 0
0x00 eccctrl | WARL | ierror | istatus | itarget | inject | enable |

64 PAddrBits-1 0
0x08 ecciaddr | WARL | paddr |
```
| CSR | field | desp |
| --- | --- | --- |
| eccctrl | enable | ECC check enable |
| eccctrl | inject | ECC inject enable (write 1 to trigger injection, read always 0) |
| eccctrl | itarget | ECC inject target<br>0: metaArray<br>1: rsvd<br>2: dataArray<br>3: rsvd |
| eccctrl | istatus | ECC inject status (read-only)<br>0: idle: inject controller idle, goes to working when received a inject request (i.e. write 1 to eccctrl.inject)<br>1: working: inject controller working, goes to injected when finished / error when failed<br>2: injected, goes to idle after read<br>3: rsvd<br>4: rsvd<br>5: rsvd<br>6: rsvd<br>7: error: inject failed (check eccctl.ierror for reason), goes to idle after read |
| eccctrl | ierror | ECC error reason (read-only, valid only if `eccctrl.istatus==error`)<br>0: ECC check is not enabled (i.e. `!eccctrl.enable`)<br>1: inject target invalid (i.e. `eccctrl.itarget==rsvd`)<br>2: inject addr (i.e. `ecciaddr.paddr`) not in ICache<br>3: rsvd<br>4: rsvd<br>5: rsvd<br>6: rsvd<br>7: rsvd |
| ecciaddr | paddr | Physical address of the inject target |

## Inject method
```asm
$INJECT_ADDR:
# maybe do something else
ret

test:
la t0, $BASE_ADDR # load icache control base addr
la t1, $INJECT_ADDR # load inject addr
jalr ra, 0(t1) # jump to injected addr to load it i
sd t1, 8(t0) # set inject addr
la t2, (target << 2 | 1 << 1 | 1 << 0) # load inject target & inject enable & ecc enable
sd t1, 0(t0) # set inject enable & ecc enable
loop:
ld t1, 0(t0) # get ecc control state
andi t1, t1, (0b11 << (4+1)) # get high bits of inject state
beqz t1, loop # if is idle, or working, loop

addi t1, t1, -1 # t1 = inject_state[2:1] - 1
bnez t1, error # if is not injected, error or rsvd

jalr ra, 0(t1) # jump to injected addr to trigger error
j finish

error:
# handle error
finish:
# finish
```
Or, checkout https://github.com/OpenXiangShan/nexus-am/pull/48

show more ...

fix(LoadQueueRAR): aligning the size of `RARSize` to `VLQSize` (#4086)

For vectors, if the size of the `RAR` is not equal to the `VLQ`, it can
lead to a jam. This is because:

A `uop` of a vector sp

fix(LoadQueueRAR): aligning the size of `RARSize` to `VLQSize` (#4086)

For vectors, if the size of the `RAR` is not equal to the `VLQ`, it can
lead to a jam. This is because:

A `uop` of a vector splits into multiple Load operations and occupies
multiple `VLQ`. The release condition of the `RAR` is that the `VLQ` are
dequeue, whereas the vector requires that all Load operations of the
`uop` are written back to the `MergeBuffer` before the `VLQ` can be let
out of the queue.

Therefore, it may happen that when the deqptr of `VLQ` waits for vector
`uop` to write back all, but the `RAR` is already full, the Load
operation split by vector `uop` can not enter the `RAR`, so it will wait
in the `ReplayQueue` for the `RAR` to be non-full, and the `RAR` can not
be released because `VLQ` can not get dequeue, which leads to deadlock.

show more ...

power(MemBlock): power optimization in MemBlock (#4059)

power optimization：
(1) use “withClockGate” instead of ClockGate in DCache
(2) reduce LSQ entries

fix(dispatch): fix bug of index vld instr, each uop can be index vld instr

timing(backend): each IQ has at least two simple entries

area(backend): reduce a vfcvt for better area

Revert "area(Backend): reduce VfScheduler iq num from 3 to 2 and remove a vfcvt fu"

This reverts commit 10b44fa68ead2a8d79ce215b6bb116912f72f3a4.

area(Backend): reduce VfScheduler iq num from 3 to 2 and remove a vfcvt fu

area(backend): reduce 4 fexu to 3 fexu