Question

我一直在尝试修改火箭核心的rocc接口，我目前已经修改了rocc接口，作为一个暂存器，我们可以使用custom0指令加载和存储数据。当我尝试将数据推送到我在凿子中创建并在我的暂存器中实例化的堆栈内存时，我面临一个问题。我使用相同的custom0指令和不同的funct字段值来推送和弹出到堆栈。

凿子中的代码如下所示，用于暂存器和我的堆栈

class Comm_Scratchpad(n: Int = 8)(implicit p: Parameters) extends RoCC()(p) {
  val Stack_Lo = Module(new Stack_Snd(64) )
  val Scratchpad_Loc = Mem(UInt(width = xLen), n:Int)
  val busy = Reg(init=Vec(Bool(false), n))

  val cmd = Queue(io.cmd) //wired to decoupled command coming into rocc interface from rocket core
  val funct = cmd.bits.inst.funct //Function to decide what operation to perform
  val addr = cmd.bits.inst.rs2(log2Up(n)-1,0) //converts address specified by user(0,1,2,3) into address that can be used for scratchpad
  val doWrite = funct === UInt(0) //Used to check whether user wants to do a write derieves its value from funct
  val doRead = funct === UInt(1) //Ignored for now as every operation is by default performing a read
  val doPush = funct === UInt(2) //Funct will be used to load to lifo with the same custom instruction
  val doPop = funct === UInt(3) //funct will be used to load back from lifo

  Stack_Lo.io.en := Mux((doPush || doPop), Bool(true), Bool(false))
  Stack_Lo.io.push := Mux(doPush, Bool(true), Bool(false))
  Stack_Lo.io.pop := Mux(doPop, Bool(true), Bool(false))

  // datapath
  val data_in = cmd.bits.rs1
  val wdata = data_in
  val rdata = Mux(doPop, Stack_Lo.io.dataOut, Scratchpad_Loc(addr))
  Stack_Lo.io.dataIn := Mux(doPush, data_in, UInt(0))

  when (cmd.fire() && (doWrite)) {
    Scratchpad_Loc(addr) := wdata
  }

  val doResp = cmd.bits.inst.xd
  val stallReg = busy(addr)
  //val stallLoad = doLoad && !io.mem.req.ready
  val stallResp = doResp && !io.resp.ready && (doPush || doPop)

  cmd.ready := !stallReg && !stallResp //removed stall load as we are not loading from memory
    // command resolved if no stalls AND not issuing a load that will need a request

  // PROC RESPONSE INTERFACE
  io.resp.valid := cmd.valid && doResp && !stallReg //&& !stallLoad
    // valid response if valid command, need a response, and no stalls
  io.resp.bits.rd := cmd.bits.inst.rd
    // Must respond with the appropriate tag or undefined behavior
  io.resp.bits.data := rdata
    // Semantics is to always send out prior accumulator register value

  io.busy := cmd.valid || busy.reduce(_||_)
    // Be busy when have pending memory requests or committed possibility of pending requests
  io.interrupt := Bool(false)
    // Set this true to trigger an interrupt on the processor (please refer to supervisor documentation)

}


class Stack_IO (implicit p: Parameters) extends CoreBundle
{ 
    val dataIn  = UInt(INPUT,  64) 
    val dataOut = UInt(OUTPUT, 64) 
    val push    = Bool(INPUT) 
    val pop     = Bool(INPUT) 
    val en      = Bool(INPUT) 
}

class Stack_Snd(depth: Int) (implicit p: Parameters) extends CoreModule {

  val io = new Stack_IO;
  // declare the memory for the stack 
  val stack_mem = 
    Mem(UInt(width = 64), depth) 
  val sp = Reg(init = UInt(0, width = log2Up(depth))) 
  val dataOut = Reg(init = UInt(0, width = 64)) 

  // Push condition - make sure stack isn't full 
  when(io.en && io.push && (sp != UInt(depth-1))) { 
    stack_mem(sp) := io.dataIn 
    sp := sp + UInt(1)  
  } 
  // Pop condition - make sure the stack isn't empty 
  .elsewhen(io.en && io.pop && (sp > UInt(0))) { 
    dataOut := stack_mem(sp - UInt(1))
    sp := sp - UInt(1) 
  } 
 io.dataOut := dataOut
}

我在前端服务器中执行的C代码如下所示。

// The following is a RISC-V program to test the functionality of the
// dummy RoCC accelerator.
// Compile with riscv64-unknown-elf-gcc dummy_rocc_test.c
// Run with spike --extension=dummy_rocc pk a.out

#include <assert.h>
#include <stdio.h>
#include <stdint.h>


int main() {
  uint64_t x = 1, y = 456, z = 0, a=2, b=3, c=4, d=5, e=6;

  asm volatile ("custom0 x0, %0, 0, 2" : : "r"(x));
  asm volatile ("custom0 x0, %0, 1, 2" : : "r"(a));
  asm volatile ("custom0 x0, %0, 2, 2" : : "r"(b));
  asm volatile ("custom0 x0, %0, 3, 2" : : "r"(c));
  asm volatile ("custom0 x0, %0, 4, 2" : : "r"(d));
  asm volatile ("custom0 x0, %0, 5, 2" : : "r"(e));


  asm volatile ("custom0 %0, x0, 0, 3" : "=r"(z));
  printf("The popped value of z 0 is:- %d \n",z);

  asm volatile ("custom0 %0, x0, 1, 3" : "=r"(z));
  printf("The popped value of z 1 is:- %d \n",z);

  asm volatile ("custom0 %0, x0, 2, 3" : "=r"(z));
  printf("The popped value of z 2 is:- %d \n",z);

  asm volatile ("custom0 %0, x0, 3, 3" : "=r"(z));
  printf("The popped value of z 3 is:- %d \n",z);

  asm volatile ("custom0 %0, x0, 4, 3" : "=r"(z));
  printf("The popped value of z 4 is:- %d \n",z);

  asm volatile ("custom0 %0, x0, 5, 3" : "=r"(z));
  printf("The popped value of z 5 is:- %d \n",z);

  printf("success!\n");
}

所以你可以看到我试图从1-6中推出一系列数字但是当我在zed板上运行这个代码时，这就是我得到的输出。

root@zynq:~# ./fesvr-zynq pk /sdcard/Custom\ elfs/rocc_fifo 
The popped value of z 0 is:- 1 
The popped value of z 1 is:- 0 
The popped value of z 2 is:- 2 
The popped value of z 3 is:- 2 
The popped value of z 4 is:- 2 
The popped value of z 5 is:- 2

理想情况下应该弹出6,5,4,3,2,1

Answer 1

我解决了这个问题，当堆栈的推送信号为高电平时，pop信号必须保持低电平，反之亦然，当我们将pop信号推高时，我们立即几乎同时弹出该值并且因此输出就像在上面的日志中看到的那样。花了很长时间让我调试，因此后期重新发布

堆栈内存实现在火箭芯片的凿子中不能正常工作

1 个答案: