Merge pull request #110 from kipmacsaigoren/bit-manip

Added support for bit manipulation extension
This commit is contained in:
David Harris 2023-03-23 06:38:28 -07:00 committed by GitHub
commit 2130c7485a
23 changed files with 975 additions and 110 deletions

View File

@ -145,10 +145,10 @@
`define DIVCOPIES 32'h4
// bit manipulation
`define ZBA_SUPPORTED 0
`define ZBB_SUPPORTED 0
`define ZBC_SUPPORTED 0
`define ZBS_SUPPORTED 0
`define ZBA_SUPPORTED 1
`define ZBB_SUPPORTED 1
`define ZBC_SUPPORTED 1
`define ZBS_SUPPORTED 1
// Memory synthesis configuration
`define USE_SRAM 0

View File

@ -148,10 +148,10 @@
`define DIVCOPIES 32'h4
// bit manipulation
`define ZBA_SUPPORTED 0
`define ZBB_SUPPORTED 0
`define ZBC_SUPPORTED 0
`define ZBS_SUPPORTED 0
`define ZBA_SUPPORTED 1
`define ZBB_SUPPORTED 1
`define ZBC_SUPPORTED 1
`define ZBS_SUPPORTED 1
// Memory synthesis configuration
`define USE_SRAM 0

View File

@ -79,7 +79,7 @@ for test in tests64i:
configs.append(tc)
tests32gcimperas = ["imperas32i", "imperas32f", "imperas32m", "imperas32c"] # unused
tests32gc = ["arch32f", "arch32d", "arch32i", "arch32priv", "arch32c", "arch32m", "arch32zi", "wally32a", "wally32priv", "wally32periph"]
tests32gc = ["arch32f", "arch32d", "arch32i", "arch32priv", "arch32c", "arch32m", "arch32zi", "arch32zba", "arch32zbb", "arch32zbc", "arch32zbs", "wally32a", "wally32priv", "wally32periph"]
for test in tests32gc:
tc = TestCase(
name=test,
@ -126,8 +126,7 @@ for test in ahbTests:
grepstr="All tests ran without failures")
configs.append(tc)
#tests64gc = ["arch64i", "arch64c", "arch64m"]
tests64gc = ["arch64f", "arch64d", "arch64i", "arch64priv", "arch64c", "arch64m", "arch64zi", "wally64a", "wally64periph", "wally64priv"]
tests64gc = ["arch64f", "arch64d", "arch64i", "arch64zba", "arch64zbb", "arch64zbc", "arch64zbs", "arch64priv", "arch64c", "arch64m", "arch64zi", "wally64a", "wally64periph", "wally64priv"]
if (coverage): # delete all but 64gc tests when running coverage
configs = []
tests64gc = ["arch64f", "arch64d", "arch64i", "arch64priv", "arch64c", "arch64m", "arch64zi", "wally64a", "wally64periph", "wally64priv", "imperas64f", "imperas64d", "imperas64c", "imperas64i"]

View File

@ -1,9 +1,9 @@
///////////////////////////////////////////
// alu.sv
//
// Written: David_Harris@hmc.edu, Sarah.Harris@unlv.edu
// Written: David_Harris@hmc.edu, Sarah.Harris@unlv.edu, kekim@hmc.edu
// Created: 9 January 2021
// Modified:
// Modified: 3 March 2023
//
// Purpose: RISC-V Arithmetic/Logic Unit
//
@ -30,31 +30,80 @@
`include "wally-config.vh"
module alu #(parameter WIDTH=32) (
input logic [WIDTH-1:0] A, B, // Operands
input logic [2:0] ALUControl, // With Funct3, indicates operation to perform
input logic [2:0] Funct3, // With ALUControl, indicates operation to perform
output logic [WIDTH-1:0] Result, // ALU result
output logic [WIDTH-1:0] Sum); // Sum of operands
input logic [WIDTH-1:0] A, B, // Operands
input logic [2:0] ALUControl, // With Funct3, indicates operation to perform
input logic [2:0] ALUSelect, // ALU mux select signal
input logic [1:0] BSelect, // One-Hot encoding of if it's a ZBA_ZBB_ZBC_ZBS instruction
input logic [2:0] ZBBSelect, // ZBB mux select signal
input logic [2:0] Funct3, // With ALUControl, indicates operation to perform NOTE: Change signal name to ALUSelect
input logic [1:0] CompFlags, // Comparator flags
input logic [2:0] BALUControl, // ALU Control signals for B instructions in Execute Stage
output logic [WIDTH-1:0] Result, // ALU result
output logic [WIDTH-1:0] Sum); // Sum of operands
// CondInvB = ~B when subtracting, B otherwise. Shift = shift result. SLT/U = result of a slt/u instruction.
// FullResult = ALU result before adjusting for a RV64 w-suffix instruction.
logic [WIDTH-1:0] CondInvB, Shift, FullResult; // Intermediate results
logic Carry, Neg; // Flags: carry out, negative
logic LT, LTU; // Less than, Less than unsigned
logic W64; // RV64 W-type instruction
logic SubArith; // Performing subtraction or arithmetic right shift
logic ALUOp; // 0 for address generation addition or 1 for regular ALU ops
logic Asign, Bsign; // Sign bits of A, B
logic [WIDTH-1:0] CondMaskInvB, Shift, FullResult,ALUResult; // Intermediate Signals
logic [WIDTH-1:0] ZBCResult, ZBBResult; // Result of ZBB, ZBC
logic [WIDTH-1:0] MaskB; // BitMask of B
logic [WIDTH-1:0] CondMaskB; // Result of B mask select mux
logic [WIDTH-1:0] CondShiftA; // Result of A shifted select mux
logic [WIDTH-1:0] CondExtA; // Result of Zero Extend A select mux
logic [WIDTH-1:0] RevA; // Bit-reversed A
logic Carry, Neg; // Flags: carry out, negative
logic LT, LTU; // Less than, Less than unsigned
logic W64; // RV64 W-type instruction
logic SubArith; // Performing subtraction or arithmetic right shift
logic ALUOp; // 0 for address generation addition or 1 for regular ALU ops
logic Asign, Bsign; // Sign bits of A, B
logic shSignA;
logic [WIDTH-1:0] rotA; // XLEN bit input source to shifter
logic [1:0] shASelect; // select signal for shifter source generation mux
logic Rotate; // Indicates if it is Rotate instruction
logic Mask; // Indicates if it is ZBS instruction
logic PreShift; // Inidicates if it is sh1add, sh2add, sh3add instruction
logic [1:0] PreShiftAmt; // Amount to Pre-Shift A
// Extract control signals from ALUControl.
assign {W64, SubArith, ALUOp} = ALUControl;
// Extract control signals from bitmanip ALUControl.
assign {Rotate, Mask, PreShift} = BALUControl;
// Pack control signals into shifter select
assign shASelect = {W64,SubArith};
assign PreShiftAmt = Funct3[2:1] & {2{PreShift}};
if (`ZBS_SUPPORTED) begin: zbsdec
decoder #($clog2(WIDTH)) maskgen (B[$clog2(WIDTH)-1:0], MaskB);
mux2 #(WIDTH) maskmux(B, MaskB, Mask, CondMaskB);
end else assign CondMaskB = B;
if (WIDTH == 64) begin
mux3 #(1) signmux(A[63], A[31], 1'b0, {~SubArith, W64}, shSignA);
mux3 #(64) extendmux({{32{1'b0}}, A[31:0]},{{32{A[31]}}, A[31:0]}, A,{~W64, SubArith}, CondExtA);
end else begin
mux2 #(1) signmux(1'b0, A[31], SubArith, shSignA);
assign CondExtA = A;
end
// shifter rotate source select mux
if (`ZBB_SUPPORTED & WIDTH == 64) begin
mux2 #(WIDTH) rotmux(A, {A[31:0], A[31:0]}, W64, rotA);
end else assign rotA = A;
if (`ZBA_SUPPORTED) begin: zbapreshift
// Pre-Shift
assign CondShiftA = CondExtA << (PreShiftAmt);
end else assign CondShiftA = A;
// Addition
assign CondInvB = SubArith ? ~B : B;
assign {Carry, Sum} = A + CondInvB + {{(WIDTH-1){1'b0}}, SubArith};
assign CondMaskInvB = SubArith ? ~CondMaskB : CondMaskB;
assign {Carry, Sum} = CondShiftA + CondMaskInvB + {{(WIDTH-1){1'b0}}, SubArith};
// Shifts
shifter sh(.A, .Amt(B[`LOG_XLEN-1:0]), .Right(Funct3[2]), .Arith(SubArith), .W64, .Y(Shift));
// Shifts (configurable for rotation)
shifter sh(.shA(CondExtA), .Sign(shSignA), .rotA, .Amt(B[`LOG_XLEN-1:0]), .Right(Funct3[2]), .W64, .Y(Shift), .Rotate);
// Condition code flags are based on subtraction output Sum = A-B.
// Overflow occurs when the numbers being subtracted have the opposite sign
@ -67,20 +116,59 @@ module alu #(parameter WIDTH=32) (
assign LTU = ~Carry;
// Select appropriate ALU Result
always_comb
if (~ALUOp) FullResult = Sum; // Always add for ALUOp = 0 (address generation)
else casez (Funct3) // Otherwise check Funct3
3'b000: FullResult = Sum; // add or sub
3'b?01: FullResult = Shift; // sll, sra, or srl
3'b010: FullResult = {{(WIDTH-1){1'b0}}, LT}; // slt
3'b011: FullResult = {{(WIDTH-1){1'b0}}, LTU}; // sltu
3'b100: FullResult = A ^ B; // xor
3'b110: FullResult = A | B; // or
3'b111: FullResult = A & B; // and
endcase
if (`ZBS_SUPPORTED | `ZBB_SUPPORTED) begin
always_comb
if (~ALUOp) FullResult = Sum; // Always add for ALUOp = 0 (address generation)
else casez (ALUSelect) // Otherwise check Funct3 NOTE: change signal name to ALUSelect
3'b000: FullResult = Sum; // add or sub
3'b001: FullResult = Shift; // sll, sra, or srl
3'b010: FullResult = {{(WIDTH-1){1'b0}}, LT}; // slt
3'b011: FullResult = {{(WIDTH-1){1'b0}}, LTU}; // sltu
3'b100: FullResult = A ^ CondMaskInvB; // xor, xnor, binv
3'b101: FullResult = {{(WIDTH-1){1'b0}},{|(A & CondMaskB)}};// bext
3'b110: FullResult = A | CondMaskInvB; // or, orn, bset
3'b111: FullResult = A & CondMaskInvB; // and, bclr
endcase
end
else begin
always_comb
if (~ALUOp) FullResult = Sum; // Always add for ALUOp = 0 (address generation)
else casez (ALUSelect) // Otherwise check Funct3 NOTE: change signal name to ALUSelect
3'b000: FullResult = Sum; // add or sub
3'b?01: FullResult = Shift; // sll, sra, or srl
3'b010: FullResult = {{(WIDTH-1){1'b0}}, LT}; // slt
3'b011: FullResult = {{(WIDTH-1){1'b0}}, LTU}; // sltu
3'b100: FullResult = A ^ B; // xor
3'b110: FullResult = A | B; // or
3'b111: FullResult = A & B; // and
endcase
end
if (`ZBC_SUPPORTED | `ZBB_SUPPORTED) begin: bitreverse
bitreverse #(WIDTH) brA(.A, .RevA);
end
if (`ZBC_SUPPORTED) begin: zbc
zbc #(WIDTH) ZBC(.A, .RevA, .B, .Funct3, .ZBCResult);
end else assign ZBCResult = 0;
if (`ZBB_SUPPORTED) begin: zbb
zbb #(WIDTH) ZBB(.A, .RevA, .B, .ALUResult, .W64, .lt(CompFlags[0]), .ZBBSelect, .ZBBResult);
end else assign ZBBResult = 0;
// Support RV64I W-type addw/subw/addiw/shifts that discard upper 32 bits and sign-extend 32-bit result to 64 bits
if (WIDTH == 64) assign Result = W64 ? {{32{FullResult[31]}}, FullResult[31:0]} : FullResult;
else assign Result = FullResult;
endmodule
if (WIDTH == 64) assign ALUResult = W64 ? {{32{FullResult[31]}}, FullResult[31:0]} : FullResult;
else assign ALUResult = FullResult;
// Final Result B instruction select mux
if (`ZBC_SUPPORTED | `ZBS_SUPPORTED | `ZBA_SUPPORTED | `ZBB_SUPPORTED) begin : zbdecoder
always_comb
case (BSelect)
// 00: ALU, 01: ZBA/ZBS, 10: ZBB, 11: ZBC
2'b00: Result = ALUResult;
2'b01: Result = FullResult; // NOTE: We don't use ALUResult because ZBA/ZBS instructions don't sign extend the MSB of the right-hand word.
2'b10: Result = ZBBResult;
2'b11: Result = ZBCResult;
endcase
end else assign Result = ALUResult;
endmodule

42
src/ieu/bmu/bitreverse.sv Normal file
View File

@ -0,0 +1,42 @@
///////////////////////////////////////////
// bitreverse.sv
//
// Written: Kevin Kim <kekim@hmc.edu> and Kip Macsai-Goren <kmacsaigoren@hmc.edu>
// Created: 1 February 2023
// Modified: 6 March 2023
//
// Purpose: Bit reverse submodule
//
// Documentation: RISC-V System on Chip Design Chapter 15
//
// A component of the CORE-V-WALLY configurable RISC-V project.
//
// Copyright (C) 2021-23 Harvey Mudd College & Oklahoma State University
//
// SPDX-License-Identifier: Apache-2.0 WITH SHL-2.1
//
// Licensed under the Solderpad Hardware License v 2.1 (the “License”); you may not use this file
// except in compliance with the License, or, at your option, the Apache License version 2.0. You
// may obtain a copy of the License at
//
// https://solderpad.org/licenses/SHL-2.1/
//
// Unless required by applicable law or agreed to in writing, any work distributed under the
// License is distributed on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
// either express or implied. See the License for the specific language governing permissions
// and limitations under the License.
////////////////////////////////////////////////////////////////////////////////////////////////
`include "wally-config.vh"
module bitreverse #(parameter WIDTH=32) (
input logic [WIDTH-1:0] A,
output logic [WIDTH-1:0] RevA);
genvar i;
for (i=0; i<WIDTH;i++) begin:loop
assign RevA[WIDTH-i-1] = A[i];
end
endmodule

192
src/ieu/bmu/bmuctrl.sv Normal file
View File

@ -0,0 +1,192 @@
///////////////////////////////////////////
// bmuctrl.sv
//
// Written: Kevin Kim <kekim@hmc.edu>
// Created: 16 February 2023
// Modified: 6 March 2023
//
// Purpose: Top level bit manipulation instruction decoder
//
// Documentation: RISC-V System on Chip Design Chapter 15
//
// A component of the CORE-V-WALLY configurable RISC-V project.
//
// Copyright (C) 2021-23 Harvey Mudd College & Oklahoma State University
//
// SPDX-License-Identifier: Apache-2.0 WITH SHL-2.1
//
// Licensed under the Solderpad Hardware License v 2.1 (the “License”); you may not use this file
// except in compliance with the License, or, at your option, the Apache License version 2.0. You
// may obtain a copy of the License at
//
// https://solderpad.org/licenses/SHL-2.1/
//
// Unless required by applicable law or agreed to in writing, any work distributed under the
// License is distributed on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
// either express or implied. See the License for the specific language governing permissions
// and limitations under the License.
////////////////////////////////////////////////////////////////////////////////////////////////
`include "wally-config.vh"
module bmuctrl(
input logic clk, reset,
// Decode stage control signals
input logic StallD, FlushD, // Stall, flush Decode stage
input logic [31:0] InstrD, // Instruction in Decode stage
output logic [2:0] ALUSelectD, // ALU Mux select signal in Decode Stage
output logic [1:0] BSelectD, // Indicates if ZBA_ZBB_ZBC_ZBS instruction in one-hot encoding in Decode stage
output logic [2:0] ZBBSelectD, // ZBB mux select signal in Decode stage NOTE: do we need this in decode?
output logic BRegWriteD, // Indicates if it is a R type B instruction in Decode Stage
output logic BALUSrcBD, // Indicates if it is an I/IW (non auipc) type B instruction in Decode Stage
output logic BW64D, // Indiciates if it is a W type B instruction in Decode Stage
output logic BALUOpD, // Indicates if it is an ALU B instruction in Decode Stage
output logic BSubArithD, // TRUE if ext, clr, andn, orn, xnor instruction in Decode Stage
output logic IllegalBitmanipInstrD, // Indicates if it is unrecognized B instruction in Decode Stage
// Execute stage control signals
input logic StallE, FlushE, // Stall, flush Execute stage
output logic [2:0] ALUSelectE,
output logic [1:0] BSelectE, // Indicates if ZBA_ZBB_ZBC_ZBS instruction in one-hot encoding
output logic [2:0] ZBBSelectE, // ZBB mux select signal
output logic BRegWriteE, // Indicates if it is a R type B instruction in Execute
output logic BComparatorSignedE, // Indicates if comparator signed in Execute Stage
output logic [2:0] BALUControlE // ALU Control signals for B instructions in Execute Stage
);
logic [6:0] OpD; // Opcode in Decode stage
logic [2:0] Funct3D; // Funct3 field in Decode stage
logic [6:0] Funct7D; // Funct7 field in Decode stage
logic [4:0] Rs2D; // Rs2 source register in Decode stage
logic BComparatorSignedD; // Indicates if comparator signed (max, min instruction) in Decode Stage
logic RotateD; // Indicates if rotate instruction in Decode Stage
logic MaskD; // Indicates if zbs instruction in Decode Stage
logic PreShiftD; // Indicates if sh1add, sh2add, sh3add instruction in Decode Stage
logic [2:0] BALUControlD; // ALU Control signals for B instructions
`define BMUCTRLW 17
`define BMUCTRLWSUB3 14
logic [`BMUCTRLW-1:0] BMUControlsD; // Main B Instructions Decoder control signals
// Extract fields
assign OpD = InstrD[6:0];
assign Funct3D = InstrD[14:12];
assign Funct7D = InstrD[31:25];
assign Rs2D = InstrD[24:20];
// Main Instruction Decoder
always_comb begin
BMUControlsD = {Funct3D, `BMUCTRLWSUB3'b00_000_0_0_0_0_0_0_0_0_1}; // default: Illegal instruction
casez({OpD, Funct7D, Funct3D})
// ALUSelect_BSelect_ZBBSelect_BRegWrite_BALUSrcB_BW64_BALUOp_BSubArithD_RotateD_MaskD_PreShiftD_IllegalBitmanipInstrD
// ZBS
17'b0010011_0100100_001: if (`ZBS_SUPPORTED)
BMUControlsD = `BMUCTRLW'b111_01_000_1_1_0_1_1_0_1_0_0; // bclri
17'b0010011_0100101_001: if (`XLEN == 64 & `ZBS_SUPPORTED)
BMUControlsD = `BMUCTRLW'b111_01_000_1_1_0_1_1_0_1_0_0; // bclri (rv64)
17'b0010011_0100100_101: if (`ZBS_SUPPORTED)
BMUControlsD = `BMUCTRLW'b101_01_000_1_1_0_1_1_0_1_0_0; // bexti
17'b0010011_0100101_101: if (`XLEN == 64 & `ZBS_SUPPORTED)
BMUControlsD = `BMUCTRLW'b101_01_000_1_1_0_1_1_0_1_0_0; // bexti (rv64)
17'b0010011_0110100_001: if (`ZBS_SUPPORTED)
BMUControlsD = `BMUCTRLW'b100_01_000_1_1_0_1_0_0_1_0_0; // binvi
17'b0010011_0110101_001: if (`XLEN == 64 & `ZBS_SUPPORTED)
BMUControlsD = `BMUCTRLW'b100_01_000_1_1_0_1_0_0_1_0_0; // binvi (rv64)
17'b0010011_0010100_001: if (`ZBS_SUPPORTED)
BMUControlsD = `BMUCTRLW'b110_01_000_1_1_0_1_0_0_1_0_0; // bseti
17'b0010011_0010101_001: if (`XLEN == 64 & `ZBS_SUPPORTED)
BMUControlsD = `BMUCTRLW'b110_01_000_1_1_0_1_0_0_1_0_0; // bseti (rv64)
17'b0110011_0100100_001: if (`ZBS_SUPPORTED)
BMUControlsD = `BMUCTRLW'b111_01_000_1_0_0_1_1_0_1_0_0; // bclr
17'b0110011_0100100_101: if (`ZBS_SUPPORTED)
BMUControlsD = `BMUCTRLW'b101_01_000_1_0_0_1_1_0_1_0_0; // bext
17'b0110011_0110100_001: if (`ZBS_SUPPORTED)
BMUControlsD = `BMUCTRLW'b100_01_000_1_0_0_1_0_0_1_0_0; // binv
17'b0110011_0010100_001: if (`ZBS_SUPPORTED)
BMUControlsD = `BMUCTRLW'b110_01_000_1_0_0_1_0_0_1_0_0; // bset
17'b0110011_0?0000?_?01: if (`ZBS_SUPPORTED | `ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b001_00_000_1_0_0_1_0_0_0_0_0; // sra, srl, sll
17'b0010011_0?0000?_?01: if (`ZBS_SUPPORTED | `ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b001_00_000_1_1_0_1_0_0_0_0_0; // srai, srli, slli
17'b0111011_0?0000?_?01: if (`ZBS_SUPPORTED | `ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b001_00_000_1_0_1_1_0_0_0_0_0; // sraw, srlw, sllw
17'b0011011_0?0000?_?01: if (`ZBS_SUPPORTED | `ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b001_00_000_1_1_1_1_0_0_0_0_0; // sraiw, srliw, slliw
// ZBC
17'b0110011_0000101_0??: if (`ZBC_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_11_000_1_0_0_1_0_0_0_0_0; // ZBC instruction
// ZBA
17'b0110011_0010000_010: if (`ZBA_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_01_000_1_0_0_1_0_0_0_1_0; // sh1add
17'b0110011_0010000_100: if (`ZBA_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_01_000_1_0_0_1_0_0_0_1_0; // sh2add
17'b0110011_0010000_110: if (`ZBA_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_01_000_1_0_0_1_0_0_0_1_0; // sh3add
17'b0111011_0010000_010: if (`XLEN == 64 & `ZBA_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_1_0; // sh1add.uw
17'b0111011_0010000_100: if (`XLEN == 64 & `ZBA_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_1_0; // sh2add.uw
17'b0111011_0010000_110: if (`XLEN == 64 & `ZBA_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_1_0; // sh3add.uw
17'b0111011_0000100_000: if (`XLEN == 64 & `ZBA_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_0_0; // add.uw
17'b0011011_000010?_001: if (`XLEN == 64 & `ZBA_SUPPORTED)
BMUControlsD = `BMUCTRLW'b001_01_000_1_1_1_1_0_0_0_0_0; // slli.uw
// ZBB
17'b0110011_0110000_001: if (`ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b001_01_111_1_0_0_1_0_1_0_0_0; // rol
17'b0111011_0110000_001: if (`XLEN == 64 & `ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b001_00_111_1_0_1_1_0_1_0_0_0; // rolw
17'b0110011_0110000_101: if (`ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b001_01_111_1_0_0_1_0_1_0_0_0; // ror
17'b0111011_0110000_101: if (`XLEN == 64 & `ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b001_00_111_1_0_1_1_0_1_0_0_0; // rorw
//17'b0010011_0110000_101: if (`ZBB_SUPPORTED)
// BMUControlsD = `BMUCTRLW'b001_00_111_1_1_0_1_0_1_0_0_0; // rori (rv32)
17'b0010011_011000?_101: if ((`XLEN == 64 | ~Funct7D[0]) & `ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b001_00_111_1_1_0_1_0_1_0_0_0; // rori (rv64)
17'b0011011_0110000_101: if (`XLEN == 64 & `ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b001_00_111_1_1_1_1_0_1_0_0_0; // roriw
17'b0010011_0110000_001: if (`ZBB_SUPPORTED & (Rs2D[4:1] == 4'b0010))
BMUControlsD = `BMUCTRLW'b000_10_001_1_1_0_1_0_0_0_0_0; // sign extend instruction
else if (`ZBB_SUPPORTED & ((Rs2D[4:2]==3'b000) & ~(Rs2D[1] & Rs2D[0])))
BMUControlsD = `BMUCTRLW'b000_10_000_1_1_0_1_0_0_0_0_0; // count instruction
17'b0011011_0110000_001: if (`XLEN == 64 & `ZBB_SUPPORTED & ((Rs2D[4:2]==3'b000) & ~(Rs2D[1] & Rs2D[0])))
BMUControlsD = `BMUCTRLW'b000_10_000_1_1_1_1_0_0_0_0_0; // count word instruction
17'b0111011_0000100_100: if (`XLEN == 64 & `ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_10_001_1_0_0_1_0_0_0_0_0; // zexth (rv64)
17'b0110011_0000100_100: if (`XLEN == 32 & `ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_10_001_1_1_0_1_0_0_0_0_0; // zexth (rv32)
17'b0110011_0100000_111: if (`ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b111_01_111_1_0_0_1_1_0_0_0_0; // andn
17'b0110011_0100000_110: if (`ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b110_01_111_1_0_0_1_1_0_0_0_0; // orn
17'b0110011_0100000_100: if (`ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b100_01_111_1_0_0_1_1_0_0_0_0; // xnor
17'b0010011_011010?_101: if ((`XLEN == 32 ^ Funct7D[0]) & `ZBB_SUPPORTED & (Rs2D == 5'b11000))
BMUControlsD = `BMUCTRLW'b000_10_010_1_1_0_1_0_0_0_0_0; // rev8
17'b0010011_0010100_101: if (`ZBB_SUPPORTED & Rs2D[4:0] == 5'b00111)
BMUControlsD = `BMUCTRLW'b000_10_010_1_1_0_1_0_0_0_0_0; // orc.b
17'b0110011_0000101_110: if (`ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_10_111_1_0_0_1_0_0_0_0_0; // max
17'b0110011_0000101_111: if (`ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_10_111_1_0_0_1_0_0_0_0_0; // maxu
17'b0110011_0000101_100: if (`ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_10_011_1_0_0_1_0_0_0_0_0; // min
17'b0110011_0000101_101: if (`ZBB_SUPPORTED)
BMUControlsD = `BMUCTRLW'b000_10_011_1_0_0_1_0_0_0_0_0; // minu
endcase
end
// Unpack Control Signals
assign {ALUSelectD,BSelectD,ZBBSelectD, BRegWriteD,BALUSrcBD, BW64D, BALUOpD, BSubArithD, RotateD, MaskD, PreShiftD, IllegalBitmanipInstrD} = BMUControlsD;
// Pack BALUControl Signals
assign BALUControlD = {RotateD, MaskD, PreShiftD};
// Comparator should perform signed comparison when min/max instruction. We have overlap in funct3 with some branch instructions so we use opcode to differentiate betwen min/max and branches
assign BComparatorSignedD = (Funct3D[2]^Funct3D[0]) & ~OpD[6];
// BMU Execute stage pipieline control register
flopenrc#(13) controlregBMU(clk, reset, FlushE, ~StallE, {ALUSelectD, BSelectD, ZBBSelectD, BRegWriteD, BComparatorSignedD, BALUControlD}, {ALUSelectE, BSelectE, ZBBSelectE, BRegWriteE, BComparatorSignedE, BALUControlE});
endmodule

46
src/ieu/bmu/byte.sv Normal file
View File

@ -0,0 +1,46 @@
///////////////////////////////////////////
// byte.sv
//
// Written: Kevin Kim <kekim@hmc.edu>
// Created: 1 February 2023
// Modified: 6 March 2023
//
// Purpose: RISCV bitmanip byte-wise operation unit
//
// Documentation: RISC-V System on Chip Design Chapter 15
//
// A component of the CORE-V-WALLY configurable RISC-V project.
//
// Copyright (C) 2021-23 Harvey Mudd College & Oklahoma State University
//
// SPDX-License-Identifier: Apache-2.0 WITH SHL-2.1
//
// Licensed under the Solderpad Hardware License v 2.1 (the “License”); you may not use this file
// except in compliance with the License, or, at your option, the Apache License version 2.0. You
// may obtain a copy of the License at
//
// https://solderpad.org/licenses/SHL-2.1/
//
// Unless required by applicable law or agreed to in writing, any work distributed under the
// License is distributed on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
// either express or implied. See the License for the specific language governing permissions
// and limitations under the License.
////////////////////////////////////////////////////////////////////////////////////////////////
`include "wally-config.vh"
module byteUnit #(parameter WIDTH=32) (
input logic [WIDTH-1:0] A, // Operands
input logic ByteSelect, // LSB of Immediate
output logic [WIDTH-1:0] ByteResult); // rev8, orcb result
logic [WIDTH-1:0] OrcBResult, Rev8Result;
genvar i;
for (i=0;i<WIDTH;i+=8) begin:loop
assign OrcBResult[i+7:i] = {8{|A[i+7:i]}};
assign Rev8Result[WIDTH-i-1:WIDTH-i-8] = A[i+7:i];
end
mux2 #(WIDTH) bytemux(Rev8Result, OrcBResult, ByteSelect, ByteResult);
endmodule

51
src/ieu/bmu/clmul.sv Normal file
View File

@ -0,0 +1,51 @@
///////////////////////////////////////////
// clmul.sv
//
// Written: Kevin Kim <kekim@hmc.edu> and Kip Macsai-Goren <kmacsaigoren@hmc.edu>
// Created: 1 February 2023
// Modified:
//
// Purpose: Carry-Less multiplication unit
//
// Documentation: RISC-V System on Chip Design Chapter 15
//
// A component of the CORE-V-WALLY configurable RISC-V project.
//
// Copyright (C) 2021-23 Harvey Mudd College & Oklahoma State University
//
// SPDX-License-Identifier: Apache-2.0 WITH SHL-2.1
//
// Licensed under the Solderpad Hardware License v 2.1 (the “License”); you may not use this file
// except in compliance with the License, or, at your option, the Apache License version 2.0. You
// may obtain a copy of the License at
//
// https://solderpad.org/licenses/SHL-2.1/
//
// Unless required by applicable law or agreed to in writing, any work distributed under the
// License is distributed on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
// either express or implied. See the License for the specific language governing permissions
// and limitations under the License.
////////////////////////////////////////////////////////////////////////////////////////////////
`include "wally-config.vh"
module clmul #(parameter WIDTH=32) (
input logic [WIDTH-1:0] A, B, // Operands
output logic [WIDTH-1:0] ClmulResult); // ZBS result
logic [(WIDTH*WIDTH)-1:0] s; // intermediary signals for carry-less multiply
integer i,j;
always_comb begin
for (i=0;i<WIDTH;i++) begin: outer
s[WIDTH*i]=A[0]&B[i];
for (j=1;j<=i;j++) begin: inner
s[WIDTH*i+j] = (A[j]&B[i-j])^s[WIDTH*i+j-1];
end
ClmulResult[i] = s[WIDTH*i+j-1];
end
end
endmodule

65
src/ieu/bmu/cnt.sv Normal file
View File

@ -0,0 +1,65 @@
///////////////////////////////////////////
// cnt.sv
//
// Written: Kevin Kim <kekim@hmc.edu>
// Created: 4 February 2023
// Modified:
//
// Purpose: Count Instruction Submodule
//
// Documentation: RISC-V System on Chip Design Chapter 15
//
// A component of the CORE-V-WALLY configurable RISC-V project.
//
// Copyright (C) 2021-23 Harvey Mudd College & Oklahoma State University
//
// SPDX-License-Identifier: Apache-2.0 WITH SHL-2.1
//
// Licensed under the Solderpad Hardware License v 2.1 (the “License”); you may not use this file
// except in compliance with the License, or, at your option, the Apache License version 2.0. You
// may obtain a copy of the License at
//
// https://solderpad.org/licenses/SHL-2.1/
//
// Unless required by applicable law or agreed to in writing, any work distributed under the
// License is distributed on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
// either express or implied. See the License for the specific language governing permissions
// and limitations under the License.
////////////////////////////////////////////////////////////////////////////////////////////////
`include "wally-config.vh"
module cnt #(parameter WIDTH = 32) (
input logic [WIDTH-1:0] A, RevA, // Operands
input logic [4:0] B, // Last 5 bits of immediate
input logic W64, // Indicates word operation
output logic [WIDTH-1:0] CntResult // count result
);
//count instructions
logic [WIDTH-1:0] czResult; // count zeros result
logic [WIDTH-1:0] cpopResult; // population count result
logic [WIDTH-1:0] lzcA, popcntA;
//only in rv64
if (WIDTH==64) begin
//clz input select mux
mux4 #(WIDTH) lzcmux64(A, {A[31:0],{32{1'b1}}}, RevA, {RevA[63:32],{32{1'b1}}}, {B[0],W64}, lzcA);
//cpop select mux
mux2 #(WIDTH) popcntmux64(A, {{32{1'b0}}, A[31:0]}, W64, popcntA);
end
//rv32
else begin
assign popcntA = A;
mux2 #(WIDTH) lzcmux32(A, RevA, B[0], lzcA);
end
lzc #(WIDTH) lzc(.num(lzcA), .ZeroCnt(czResult[$clog2(WIDTH):0]));
popcnt #(WIDTH) popcntw(.num(popcntA), .PopCnt(cpopResult[$clog2(WIDTH):0]));
// zero extend these results to fit into width
assign czResult[WIDTH-1:$clog2(WIDTH)+1] = '0;
assign cpopResult[WIDTH-1:$clog2(WIDTH)+1] = '0;
mux2 #(WIDTH) cntresultmux(czResult, cpopResult, B[1], CntResult);
endmodule

45
src/ieu/bmu/ext.sv Normal file
View File

@ -0,0 +1,45 @@
///////////////////////////////////////////
// ext.sv
//
// Written: Kevin Kim <kekim@hmc.edu>
// Created: 4 February 2023
// Modified:
//
// Purpose: Sign/Zero Extension Submodule
//
// Documentation: RISC-V System on Chip Design Chapter 15
//
// A component of the CORE-V-WALLY configurable RISC-V project.
//
// Copyright (C) 2021-23 Harvey Mudd College & Oklahoma State University
//
// SPDX-License-Identifier: Apache-2.0 WITH SHL-2.1
//
// Licensed under the Solderpad Hardware License v 2.1 (the “License”); you may not use this file
// except in compliance with the License, or, at your option, the Apache License version 2.0. You
// may obtain a copy of the License at
//
// https://solderpad.org/licenses/SHL-2.1/
//
// Unless required by applicable law or agreed to in writing, any work distributed under the
// License is distributed on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
// either express or implied. See the License for the specific language governing permissions
// and limitations under the License.
////////////////////////////////////////////////////////////////////////////////////////////////
`include "wally-config.vh"
module ext #(parameter WIDTH = 32) (
input logic [WIDTH-1:0] A, // Operands
input logic [1:0] ExtSelect, // B[2], B[0] of immediate
output logic [WIDTH-1:0] ExtResult); // Extend Result
logic [WIDTH-1:0] sexthResult, zexthResult, sextbResult;
assign sexthResult = {{(WIDTH-16){A[15]}},A[15:0]};
assign zexthResult = {{(WIDTH-16){1'b0}},A[15:0]};
assign sextbResult = {{(WIDTH-8){A[7]}},A[7:0]};
mux3 #(WIDTH) extmux(sextbResult, sexthResult, zexthResult, ExtSelect, ExtResult);
endmodule

44
src/ieu/bmu/popcnt.sv Normal file
View File

@ -0,0 +1,44 @@
///////////////////////////////////////////
// popccnt.sv
// Written: Kevin Kim <kekim@hmc.edu>
// Modified: 2/4/2023
//
// Purpose: Population Count
//
// Documentation: RISC-V System on Chip Design Chapter 15
//
// A component of the CORE-V-WALLY configurable RISC-V project.
//
// Copyright (C) 2021-23 Harvey Mudd College & Oklahoma State University
//
// SPDX-License-Identifier: Apache-2.0 WITH SHL-2.1
//
// Licensed under the Solderpad Hardware License v 2.1 (the “License”); you may not use this file
// except in compliance with the License, or, at your option, the Apache License version 2.0. You
// may obtain a copy of the License at
//
// https://solderpad.org/licenses/SHL-2.1/
//
// Unless required by applicable law or agreed to in writing, any work distributed under the
// License is distributed on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
// either express or implied. See the License for the specific language governing permissions
// and limitations under the License.
////////////////////////////////////////////////////////////////////////////////////////////////
module popcnt #(parameter WIDTH = 32) (
input logic [WIDTH-1:0] num, // number to count total ones
output logic [$clog2(WIDTH):0] PopCnt // the total number of ones
);
logic [$clog2(WIDTH):0] sum;
always_comb begin
sum = 0;
for (int i=0;i<WIDTH;i++) begin:loop
sum = (num[i]) ? sum + 1 : sum;
end
end
assign PopCnt = sum;
endmodule

55
src/ieu/bmu/zbb.sv Normal file
View File

@ -0,0 +1,55 @@
///////////////////////////////////////////
// zbb.sv
//
// Written: Kevin Kim <kekim@hmc.edu> and Kip Macsai-Goren <kmacsaigoren@hmc.edu>
// Created: 2 February 2023
// Modified: March 6 2023
//
// Purpose: RISC-V ZBB top level unit
//
// Documentation: RISC-V System on Chip Design Chapter 15
//
// A component of the CORE-V-WALLY configurable RISC-V project.
//
// Copyright (C) 2021-23 Harvey Mudd College & Oklahoma State University
//
// SPDX-License-Identifier: Apache-2.0 WITH SHL-2.1
//
// Licensed under the Solderpad Hardware License v 2.1 (the “License”); you may not use this file
// except in compliance with the License, or, at your option, the Apache License version 2.0. You
// may obtain a copy of the License at
//
// https://solderpad.org/licenses/SHL-2.1/
//
// Unless required by applicable law or agreed to in writing, any work distributed under the
// License is distributed on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
// either express or implied. See the License for the specific language governing permissions
// and limitations under the License.
////////////////////////////////////////////////////////////////////////////////////////////////
`include "wally-config.vh"
module zbb #(parameter WIDTH=32) (
input logic [WIDTH-1:0] A, RevA, B, // Operands
input logic [WIDTH-1:0] ALUResult, // ALU Result
input logic W64, // Indicates word operation
input logic lt, // lt flag
input logic [2:0] ZBBSelect, // Indicates word operation
output logic [WIDTH-1:0] ZBBResult); // ZBB result
logic [WIDTH-1:0] CntResult; // count result
logic [WIDTH-1:0] MinMaxResult; // min,max result
logic [WIDTH-1:0] ByteResult; // byte results
logic [WIDTH-1:0] ExtResult; // sign/zero extend results
cnt #(WIDTH) cnt(.A, .RevA, .B(B[4:0]), .W64, .CntResult);
byteUnit #(WIDTH) bu(.A, .ByteSelect(B[0]), .ByteResult);
ext #(WIDTH) ext(.A, .ExtSelect({~B[2], {B[2] & B[0]}}), .ExtResult);
// ZBBSelect[2] differentiates between min(u) vs max(u) instruction
mux2 #(WIDTH) minmaxmux(B, A, lt^ZBBSelect[2], MinMaxResult);
// ZBB Result select mux
mux4 #(WIDTH) zbbresultmux(CntResult, ExtResult, ByteResult, MinMaxResult, ZBBSelect[1:0], ZBBResult);
endmodule

54
src/ieu/bmu/zbc.sv Normal file
View File

@ -0,0 +1,54 @@
///////////////////////////////////////////
// zbc.sv
//
// Written: Kevin Kim <kekim@hmc.edu> and Kip Macsai-Goren <kmacsaigoren@hmc.edu>
// Created: 2 February 2023
// Modified: 3 March 2023
//
// Purpose: RISC-V ZBC top-level unit
//
// Documentation: RISC-V System on Chip Design Chapter 15
//
// A component of the CORE-V-WALLY configurable RISC-V project.
//
// Copyright (C) 2021-23 Harvey Mudd College & Oklahoma State University
//
// SPDX-License-Identifier: Apache-2.0 WITH SHL-2.1
//
// Licensed under the Solderpad Hardware License v 2.1 (the “License”); you may not use this file
// except in compliance with the License, or, at your option, the Apache License version 2.0. You
// may obtain a copy of the License at
//
// https://solderpad.org/licenses/SHL-2.1/
//
// Unless required by applicable law or agreed to in writing, any work distributed under the
// License is distributed on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
// either express or implied. See the License for the specific language governing permissions
// and limitations under the License.
////////////////////////////////////////////////////////////////////////////////////////////////
`include "wally-config.vh"
module zbc #(parameter WIDTH=32) (
input logic [WIDTH-1:0] A, RevA, B, // Operands
input logic [2:0] Funct3, // Indicates operation to perform
output logic [WIDTH-1:0] ZBCResult); // ZBC result
logic [WIDTH-1:0] ClmulResult, RevClmulResult;
logic [WIDTH-1:0] RevB;
logic [WIDTH-1:0] x,y;
logic [1:0] select;
assign select = ~Funct3[1:0];
bitreverse #(WIDTH) brB(.A(B), .RevA(RevB));
mux3 #(WIDTH) xmux({RevA[WIDTH-2:0], {1'b0}}, RevA, A, select, x);
mux3 #(WIDTH) ymux({{1'b0},RevB[WIDTH-2:0]}, RevB, B, select, y);
clmul #(WIDTH) clm(.A(x), .B(y), .ClmulResult(ClmulResult));
bitreverse #(WIDTH) brClmulResult(.A(ClmulResult), .RevA(RevClmulResult));
mux2 #(WIDTH) zbcresultmux(ClmulResult, RevClmulResult, Funct3[1], ZBCResult);
endmodule

View File

@ -1,9 +1,9 @@
///////////////////////////////////////////
// controller.sv
//
// Written: David_Harris@hmc.edu, Sarah.Harris@unlv.edu
// Written: David_Harris@hmc.edu, Sarah.Harris@unlv.edu, kekim@hmc.edu
// Created: 9 January 2021
// Modified:
// Modified: 3 March 2023
//
// Purpose: Top level controller module
//
@ -48,6 +48,7 @@ module controller(
output logic [2:0] ALUControlE, // ALU operation to perform
output logic ALUSrcAE, ALUSrcBE, // ALU operands
output logic ALUResultSrcE, // Selects result to pass on to Memory stage
output logic [2:0] ALUSelectE, // ALU mux select signal
output logic MemReadE, CSRReadE, // Instruction reads memory, reads a CSR (needed for Hazard unit)
output logic [2:0] Funct3E, // Instruction's funct3 field
output logic IntDivE, // Integer divide
@ -57,6 +58,10 @@ module controller(
output logic BranchE, // Branch instruction
output logic SCE, // Store Conditional instruction
output logic BranchSignedE, // Branch comparison operands are signed (if it's a branch)
output logic [1:0] BSelectE, // One-Hot encoding of if it's ZBA_ZBB_ZBC_ZBS instruction
output logic [2:0] ZBBSelectE, // ZBB mux select signal in Execute stage
output logic [2:0] BALUControlE, // ALU Control signals for B instructions in Execute Stage
// Memory stage control signals
input logic StallM, FlushM, // Stall, flush Memory stage
output logic [1:0] MemRWM, // Mem read/write: MemRWM[1] = 1 for read, MemRWM[0] = 1 for write
@ -88,7 +93,12 @@ module controller(
logic [2:0] ResultSrcD, ResultSrcE, ResultSrcM; // Select which result to write back to register file
logic [1:0] MemRWD, MemRWE; // Store (write to memory)
logic ALUOpD; // 0 for address generation, 1 for all other operations (must use Funct3)
logic BaseALUOpD, BaseW64D; // ALU operation and W64 for Base instructions specifically
logic BaseRegWriteD; // Indicates if Base instruction register write instruction
logic BaseSubArithD; // Indicates if Base instruction subtracts, sra, slt, sltu
logic BaseALUSrcBD; // Base instruction ALU B source select signal
logic [2:0] ALUControlD; // Determines ALU operation
logic [2:0] ALUSelectD; // ALU mux select signal
logic ALUSrcAD, ALUSrcBD; // ALU inputs
logic ALUResultSrcD, W64D, MDUD; // ALU result, is RV64 W-type, is multiply/divide instruction
logic CSRZeroSrcD; // Ignore setting and clearing zeros to CSR
@ -100,18 +110,28 @@ module controller(
logic PrivilegedD, PrivilegedE; // Privileged instruction
logic InvalidateICacheE, FlushDCacheE;// Invalidate I$, flush D$
logic [`CTRLW-1:0] ControlsD; // Main Instruction Decoder control signals
logic SubArithD; // TRUE for R-type subtracts and sra, slt, sltu
logic SubArithD; // TRUE for R-type subtracts and sra, slt, sltu or B-type ext clr, andn, orn, xnor
logic subD, sraD, sltD, sltuD; // Indicates if is one of these instructions
logic BranchTakenE; // Branch is taken
logic eqE, ltE; // Comparator outputs
logic unused;
logic BranchFlagE; // Branch flag to use (chosen between eq or lt)
logic IEURegWriteE; // Register write
logic BRegWriteE; // Register write from BMU controller in Execute Stage
logic IllegalERegAdrD; // RV32E attempts to write upper 16 registers
logic IllegalBitmanipInstrD; // Unrecognized B instruction
logic [1:0] AtomicE; // Atomic instruction
logic FenceD, FenceE; // Fence instruction
logic SFenceVmaD; // sfence.vma instruction
logic IntDivM; // Integer divide instruction
logic [1:0] BSelectD; // One-Hot encoding if it's ZBA_ZBB_ZBC_ZBS instruction in decode stage
logic [2:0] ZBBSelectD; // ZBB Mux Select Signal
logic BRegWriteD; // Indicates if it is a R type B instruction in decode stage
logic BW64D; // Indicates if it is a W type B instruction in decode stage
logic BALUOpD; // Indicates if it is an ALU B instruction in decode stage
logic BSubArithD; // TRUE for B-type ext, clr, andn, orn, xnor
logic BALUSrcBD; // B-type alu src select signal
logic BComparatorSignedE; // Indicates if max, min (signed comarison) instruction in Execute Stage
logic IFunctD, RFunctD, MFunctD; // Detect I, R, and M-type RV32IM/Rv64IM instructions
logic LFunctD, SFunctD, BFunctD; // Detect load, store, branch instructions
logic JFunctD; // detect jalr instruction
@ -213,25 +233,61 @@ module controller(
// Squash control signals if coming from an illegal compressed instruction
// On RV32E, can't write to upper 16 registers. Checking reads to upper 16 is more costly so disregard them.
assign IllegalERegAdrD = `E_SUPPORTED & `ZICSR_SUPPORTED & ControlsD[`CTRLW-1] & InstrD[11];
assign IllegalBaseInstrD = ControlsD[0] | IllegalERegAdrD;
assign {RegWriteD, ImmSrcD, ALUSrcAD, ALUSrcBD, MemRWD,
ResultSrcD, BranchD, ALUOpD, JumpD, ALUResultSrcD, W64D, CSRReadD,
assign IllegalBaseInstrD = (ControlsD[0] & IllegalBitmanipInstrD) | IllegalERegAdrD ; //NOTE: Do we want to segregate the IllegalBitmanipInstrD into its own output signal
//assign IllegalBaseInstrD = 1'b0;
assign {BaseRegWriteD, ImmSrcD, ALUSrcAD, BaseALUSrcBD, MemRWD,
ResultSrcD, BranchD, BaseALUOpD, JumpD, ALUResultSrcD, BaseW64D, CSRReadD,
PrivilegedD, FenceXD, MDUD, AtomicD, unused} = IllegalIEUFPUInstrD ? `CTRLW'b0 : ControlsD;
// If either bitmanip signal or base instruction signal
assign ALUOpD = BaseALUOpD | BALUOpD;
assign RegWriteD = BaseRegWriteD | BRegWriteD;
assign W64D = BaseW64D | BW64D;
assign ALUSrcBD = BaseALUSrcBD | BALUSrcBD;
assign SubArithD = BaseSubArithD | BSubArithD; // TRUE If B-type or R-type instruction involves inverted operand
assign CSRZeroSrcD = InstrD[14] ? (InstrD[19:15] == 0) : (Rs1D == 0); // Is a CSR instruction using zero as the source?
assign CSRWriteD = CSRReadD & !(CSRZeroSrcD & InstrD[13]); // Don't write if setting or clearing zeros
assign SFenceVmaD = PrivilegedD & (InstrD[31:25] == 7'b0001001);
assign FenceD = SFenceVmaD | FenceXD; // possible sfence.vma or fence.i
// ALU Decoding is lazy, only using func7[5] to distinguish add/sub and srl/sra
assign sltD = (Funct3D == 3'b010);
assign sltuD = (Funct3D == 3'b011);
assign sltuD = (Funct3D == 3'b011);
assign subD = (Funct3D == 3'b000 & Funct7D[5] & OpD[5]); // OpD[5] needed to distinguish sub from addi
assign sraD = (Funct3D == 3'b101 & Funct7D[5]);
assign SubArithD = ALUOpD & (subD | sraD | sltD | sltuD); // TRUE for R-type subtracts and sra, slt, sltu
assign BaseSubArithD = ALUOpD & (subD | sraD | sltD | sltuD);
assign ALUControlD = {W64D, SubArithD, ALUOpD};
// bit manipulation Configuration Block
if (`ZBS_SUPPORTED | `ZBA_SUPPORTED | `ZBB_SUPPORTED | `ZBC_SUPPORTED) begin: bitmanipi //change the conditional expression to OR any Z supported flags
bmuctrl bmuctrl(.clk, .reset, .StallD, .FlushD, .InstrD, .ALUSelectD, .BSelectD, .ZBBSelectD,
.BRegWriteD, .BALUSrcBD, .BW64D, .BALUOpD, .BSubArithD, .IllegalBitmanipInstrD, .StallE, .FlushE,
.ALUSelectE, .BSelectE, .ZBBSelectE, .BRegWriteE, .BComparatorSignedE, .BALUControlE);
if (`ZBA_SUPPORTED) begin
// ALU Decoding is more comprehensive when ZBA is supported. slt and slti conflicts with sh1add, sh1add.uw
assign sltD = (Funct3D == 3'b010 & (~(Funct7D[4]) | ~OpD[5])) ;
end else assign sltD = (Funct3D == 3'b010);
end else begin: bitmanipi
assign ALUSelectD = Funct3D;
assign ALUSelectE = Funct3E;
assign BSelectE = 2'b00;
assign BSelectD = 2'b00;
assign ZBBSelectE = 3'b000;
assign BRegWriteD = 1'b0;
assign BW64D = 1'b0;
assign BALUOpD = 1'b0;
assign BRegWriteE = 1'b0;
assign BSubArithD = 1'b0;
assign BComparatorSignedE = 1'b0;
assign BALUControlE = 3'b0;
assign BALUSrcBD = 1'b0;
assign sltD = (Funct3D == 3'b010);
assign IllegalBitmanipInstrD = 1'b1;
end
// Fences
// Ordinary fence is presently a nop
// fence.i flushes the D$ and invalidates the I$ if Zifencei is supported and I$ is implemented
@ -256,7 +312,8 @@ module controller(
// Branch Logic
// The comparator handles both signed and unsigned branches using BranchSignedE
// Hence, only eq and lt flags are needed
assign BranchSignedE = ~(Funct3E[2:1] == 2'b11);
// We also want comparator to handle signed comparison on a max/min bitmanip instruction
assign BranchSignedE = (~(Funct3E[2:1] == 2'b11) & BranchE) | BComparatorSignedE;
assign {eqE, ltE} = FlagsE;
mux2 #(1) branchflagmux(eqE, ltE, Funct3E[2], BranchFlagE);
assign BranchTakenE = BranchFlagE ^ Funct3E[0];
@ -284,4 +341,4 @@ module controller(
// the synchronous DTIM cannot read immediately after write
// a cache cannot read or write immediately after a write
assign StoreStallD = MemRWE[0] & ((MemRWD[1] | (MemRWD[0] & `DCACHE_SUPPORTED)) | (|AtomicD));
endmodule
endmodule

View File

@ -43,8 +43,12 @@ module datapath (
input logic [2:0] ALUControlE, // Indicate operation ALU performs
input logic ALUSrcAE, ALUSrcBE, // ALU operands
input logic ALUResultSrcE, // Selects result to pass on to Memory stage
input logic [2:0] ALUSelectE, // ALU mux select signal
input logic JumpE, // Is a jump (j) instruction
input logic BranchSignedE, // Branch comparison operands are signed (if it's a branch)
input logic [1:0] BSelectE, // One hot encoding of ZBA_ZBB_ZBC_ZBS instruction
input logic [2:0] ZBBSelectE, // ZBB mux select signal
input logic [2:0] BALUControlE, // ALU Control signals for B instructions in Execute Stage
output logic [1:0] FlagsE, // Comparison flags ({eq, lt})
output logic [`XLEN-1:0] IEUAdrE, // Address computed by ALU
output logic [`XLEN-1:0] ForwardedSrcAE, ForwardedSrcBE, // ALU sources before the mux chooses between them and PCE to put in srcA/B
@ -56,7 +60,7 @@ module datapath (
output logic [`XLEN-1:0] WriteDataM, // Write data in Memory stage
// Writeback stage signals
input logic StallW, FlushW, // Stall, flush Writeback stage
input logic RegWriteW, IntDivW, // Write register file, integer divide instruction
input logic RegWriteW, IntDivW, // Write register file, integer divide instruction
input logic SquashSCW, // Squash a store conditional when a conflict arose
input logic [2:0] ResultSrcW, // Select source of result to write back to register file
input logic [`XLEN-1:0] FCvtIntResW, // FPU convert fp to integer result
@ -109,7 +113,7 @@ module datapath (
comparator #(`XLEN) comp(ForwardedSrcAE, ForwardedSrcBE, BranchSignedE, FlagsE);
mux2 #(`XLEN) srcamux(ForwardedSrcAE, PCE, ALUSrcAE, SrcAE);
mux2 #(`XLEN) srcbmux(ForwardedSrcBE, ImmExtE, ALUSrcBE, SrcBE);
alu #(`XLEN) alu(SrcAE, SrcBE, ALUControlE, Funct3E, ALUResultE, IEUAdrE);
alu #(`XLEN) alu(SrcAE, SrcBE, ALUControlE, ALUSelectE, BSelectE, ZBBSelectE, Funct3E, FlagsE, BALUControlE, ALUResultE, IEUAdrE);
mux2 #(`XLEN) altresultmux(ImmExtE, PCLinkE, JumpE, AltResultE);
mux2 #(`XLEN) ieuresultmux(ALUResultE, AltResultE, ALUResultSrcE, IEUResultE);
@ -141,4 +145,4 @@ module datapath (
// handle Store Conditional result if atomic extension supported
if (`A_SUPPORTED) assign SCResultW = {{(`XLEN-1){1'b0}}, SquashSCW};
else assign SCResultW = 0;
endmodule
endmodule

View File

@ -80,9 +80,13 @@ module ieu (
logic ALUSrcAE, ALUSrcBE; // ALU source operands
logic [2:0] ResultSrcW; // Selects result in Writeback stage
logic ALUResultSrcE; // Selects ALU result to pass on to Memory stage
logic [2:0] ALUSelectE; // ALU select mux signal
logic SCE; // Store Conditional instruction
logic FWriteIntM; // FPU writing to integer register file
logic IntDivW; // Integer divide instruction
logic [1:0] BSelectE; // Indicates if ZBA_ZBB_ZBC_ZBS instruction in one-hot encoding
logic [2:0] ZBBSelectE; // ZBB Result Select Signal in Execute Stage
logic [2:0] BALUControlE; // ALU Control signals for B instructions in Execute Stage
// Forwarding signals
logic [4:0] Rs1D, Rs2D, Rs1E, Rs2E; // Source and destination registers
@ -92,19 +96,19 @@ module ieu (
logic BranchSignedE; // Branch does signed comparison on operands
logic MDUE; // Multiply/divide instruction
controller c(
controller c(
.clk, .reset, .StallD, .FlushD, .InstrD, .ImmSrcD,
.IllegalIEUFPUInstrD, .IllegalBaseInstrD, .StallE, .FlushE, .FlagsE, .FWriteIntE,
.PCSrcE, .ALUControlE, .ALUSrcAE, .ALUSrcBE, .ALUResultSrcE, .MemReadE, .CSRReadE,
.Funct3E, .IntDivE, .MDUE, .W64E, .BranchD, .BranchE, .JumpD, .JumpE, .SCE, .BranchSignedE, .StallM, .FlushM, .MemRWM,
.PCSrcE, .ALUControlE, .ALUSrcAE, .ALUSrcBE, .ALUResultSrcE, .ALUSelectE, .MemReadE, .CSRReadE,
.Funct3E, .IntDivE, .MDUE, .W64E, .BranchD, .BranchE, .JumpD, .JumpE, .SCE, .BranchSignedE, .BSelectE, .ZBBSelectE, .BALUControlE, .StallM, .FlushM, .MemRWM,
.CSRReadM, .CSRWriteM, .PrivilegedM, .AtomicM, .Funct3M,
.RegWriteM, .FlushDCacheM, .InstrValidM, .InstrValidE, .InstrValidD, .FWriteIntM,
.StallW, .FlushW, .RegWriteW, .IntDivW, .ResultSrcW, .CSRWriteFenceM, .InvalidateICacheM, .StoreStallD);
datapath dp(
.clk, .reset, .ImmSrcD, .InstrD, .StallE, .FlushE, .ForwardAE, .ForwardBE,
.ALUControlE, .Funct3E, .ALUSrcAE, .ALUSrcBE, .ALUResultSrcE, .JumpE, .BranchSignedE,
.PCE, .PCLinkE, .FlagsE, .IEUAdrE, .ForwardedSrcAE, .ForwardedSrcBE,
.ALUControlE, .Funct3E, .ALUSrcAE, .ALUSrcBE, .ALUResultSrcE, .ALUSelectE, .JumpE, .BranchSignedE,
.PCE, .PCLinkE, .FlagsE, .IEUAdrE, .ForwardedSrcAE, .ForwardedSrcBE, .BSelectE, .ZBBSelectE, .BALUControlE,
.StallM, .FlushM, .FWriteIntM, .FIntResM, .SrcAM, .WriteDataM, .FCvtIntW,
.StallW, .FlushW, .RegWriteW, .IntDivW, .SquashSCW, .ResultSrcW, .ReadDataW, .FCvtIntResW,
.CSRReadValW, .MDUResultW, .FIntDivResultW, .Rs1D, .Rs2D, .Rs1E, .Rs2E, .RdE, .RdM, .RdW);

View File

@ -1,9 +1,9 @@
///////////////////////////////////////////
// shifter.sv
//
// Written: David_Harris@hmc.edu, Sarah.Harris@unlv.edu
// Written: David_Harris@hmc.edu, Sarah.Harris@unlv.edu, Kevin Kim <kekim@hmc.edu>
// Created: 9 January 2021
// Modified:
// Modified: 6 February 2023
//
// Purpose: RISC-V 32/64 bit shifter
//
@ -30,42 +30,49 @@
`include "wally-config.vh"
module shifter (
input logic [`XLEN-1:0] A, // Source
input logic [`LOG_XLEN-1:0] Amt, // Shift amount
input logic Right, Arith, W64, // Shift right, arithmetic, RV64 W-type shift
output logic [`XLEN-1:0] Y); // Shifted result
input logic [`XLEN-1:0] shA, // shift Source
input logic [`XLEN-1:0] rotA, // rotate source
input logic [`LOG_XLEN-1:0] Amt, // Shift amount
input logic Right, Rotate, W64, Sign, // Shift right, rotate signals
output logic [`XLEN-1:0] Y); // Shifted result
logic [2*`XLEN-2:0] z, zshift; // Input to funnel shifter, shifted amount before truncated to 32 or 64 bits
logic [`LOG_XLEN-1:0] amttrunc, offset; // Shift amount adjusted for RV64, right-shift amount
logic [2*`XLEN-2:0] z, zshift; // Input to funnel shifter, shifted amount before truncated to 32 or 64 bits
logic [`LOG_XLEN-1:0] amttrunc, offset; // Shift amount adjusted for RV64, right-shift amount
// Handle left and right shifts with a funnel shifter.
// For RV32, only 32-bit shifts are needed.
// For RV64, 32- and 64-bit shifts are needed, with sign extension.
// Funnel shifter input (see CMOS VLSI Design 4e Section 11.8.1, note Table 11.11 shift types wrong)
if (`XLEN==32) begin:shifter // RV32
always_comb // funnel mux
if (Right)
if (Arith) z = {{31{A[31]}}, A};
else z = {31'b0, A};
else z = {A, 31'b0};
assign amttrunc = Amt; // shift amount
end else begin:shifter // RV64
always_comb // funnel mux
if (W64) begin // 32-bit shifts
if (Right)
if (Arith) z = {64'b0, {31{A[31]}}, A[31:0]};
else z = {95'b0, A[31:0]};
else z = {32'b0, A[31:0], 63'b0};
end else begin
if (Right)
if (Arith) z = {{63{A[63]}}, A};
else z = {63'b0, A};
else z = {A, 63'b0};
end
assign amttrunc = W64 ? {1'b0, Amt[4:0]} : Amt; // 32- or 64-bit shift
if (`ZBB_SUPPORTED) begin: rotfunnel
if (`XLEN==32) begin // rv32 with rotates
always_comb // funnel mux
case({Right, Rotate})
2'b00: z = {shA[31:0], 31'b0};
2'b01: z = {rotA,rotA[31:1]};
2'b10: z = {{31{Sign}}, shA[31:0]};
2'b11: z = {rotA[30:0],rotA};
endcase
assign amttrunc = Amt; // shift amount
end else begin // rv64 with rotates
always_comb // funnel mux
case ({Right, Rotate})
2'b00: z = {shA[63:0],{63'b0}};
2'b01: z = {rotA, rotA[63:1]};
2'b10: z = {{63{Sign}},shA[63:0]};
2'b11: z = {rotA[62:0],rotA[63:0]};
endcase
assign amttrunc = W64 ? {1'b0, Amt[4:0]} : Amt; // 32- or 64-bit shift
end
end else begin: norotfunnel
if (`XLEN==32) begin:shifter // RV32
always_comb // funnel mux
if (Right) z = {{31{Sign}}, shA[31:0]};
else z = {shA[31:0], 31'b0};
assign amttrunc = Amt; // shift amount
end else begin:shifter // RV64
always_comb // funnel mux
if (Right) z = {{63{Sign}},shA[63:0]};
else z = {shA[63:0],{63'b0}};
assign amttrunc = W64 ? {1'b0, Amt[4:0]} : Amt; // 32- or 64-bit shift
end
end
// Opposite offset for right shifts
assign offset = Right ? amttrunc : ~amttrunc;

View File

@ -106,6 +106,10 @@ logic [3:0] dummy;
"coremark": tests = coremark;
"fpga": tests = fpga;
"ahb" : tests = ahb;
"arch64zba": if (`ZBA_SUPPORTED) tests = arch64zba;
"arch64zbb": if (`ZBB_SUPPORTED) tests = arch64zbb;
"arch64zbc": if (`ZBC_SUPPORTED) tests = arch64zbc;
"arch64zbs": if (`ZBS_SUPPORTED) tests = arch64zbs;
endcase
end else begin // RV32
case (TEST)
@ -130,7 +134,10 @@ logic [3:0] dummy;
"wally32periph": tests = wally32periph;
"embench": tests = embench;
"coremark": tests = coremark;
"arch32ba": if (`ZBA_SUPPORTED) tests = arch32ba;
"arch32zba": if (`ZBA_SUPPORTED) tests = arch32zba;
"arch32zbb": if (`ZBB_SUPPORTED) tests = arch32zbb;
"arch32zbc": if (`ZBC_SUPPORTED) tests = arch32zbc;
"arch32zbs": if (`ZBS_SUPPORTED) tests = arch32zbs;
endcase
end
if (tests.size() == 0) begin

View File

@ -881,12 +881,52 @@ string imperas32f[] = '{
"rv32i_m/Zifencei/src/Fencei.S"
};
string arch32ba[] = '{
string arch32zba[] = '{
`RISCVARCHTEST,
// *** unclear why add.uw isn't in the list
"rv64i_m/B/src/sh1add-01.S",
"rv64i_m/B/src/sh1add-02.S",
"rv64i_m/B/src/sh1add-013.S"
"rv32i_m/B/src/sh1add-01.S",
"rv32i_m/B/src/sh2add-01.S",
"rv32i_m/B/src/sh3add-01.S"
};
string arch32zbb[] = '{
`RISCVARCHTEST,
"rv32i_m/B/src/max-01.S",
"rv32i_m/B/src/maxu-01.S",
"rv32i_m/B/src/min-01.S",
"rv32i_m/B/src/minu-01.S",
"rv32i_m/B/src/orcb_32-01.S",
"rv32i_m/B/src/rev8_32-01.S",
"rv32i_m/B/src/andn-01.S",
"rv32i_m/B/src/orn-01.S",
"rv32i_m/B/src/xnor-01.S",
"rv32i_m/B/src/zext.h_32-01.S",
"rv32i_m/B/src/sext.b-01.S",
"rv32i_m/B/src/sext.h-01.S",
"rv32i_m/B/src/clz-01.S",
"rv32i_m/B/src/cpop-01.S",
"rv32i_m/B/src/ctz-01.S",
"rv32i_m/B/src/ror-01.S",
"rv32i_m/B/src/rori-01.S",
"rv32i_m/B/src/rol-01.S"
};
string arch32zbc[] = '{
`RISCVARCHTEST,
"rv32i_m/B/src/clmul-01.S",
"rv32i_m/B/src/clmulh-01.S",
"rv32i_m/B/src/clmulr-01.S"
};
string arch32zbs[] = '{
`RISCVARCHTEST,
"rv32i_m/B/src/bclr-01.S",
"rv32i_m/B/src/bclri-01.S",
"rv32i_m/B/src/bext-01.S",
"rv32i_m/B/src/bexti-01.S",
"rv32i_m/B/src/binv-01.S",
"rv32i_m/B/src/binvi-01.S",
"rv32i_m/B/src/bset-01.S",
"rv32i_m/B/src/bseti-01.S"
};
string arch64m[] = '{
@ -1326,6 +1366,65 @@ string imperas32f[] = '{
"rv64i_m/D/src/fssub.d_b8-01.S"
};
string arch64zba[] = '{
`RISCVARCHTEST,
"rv64i_m/B/src/slli.uw-01.S",
"rv64i_m/B/src/add.uw-01.S",
"rv64i_m/B/src/sh1add-01.S",
"rv64i_m/B/src/sh2add-01.S",
"rv64i_m/B/src/sh3add-01.S",
"rv64i_m/B/src/sh1add.uw-01.S",
"rv64i_m/B/src/sh2add.uw-01.S",
"rv64i_m/B/src/sh3add.uw-01.S"
};
string arch64zbb[] = '{
`RISCVARCHTEST,
"rv64i_m/B/src/max-01.S",
"rv64i_m/B/src/maxu-01.S",
"rv64i_m/B/src/min-01.S",
"rv64i_m/B/src/minu-01.S",
"rv64i_m/B/src/orcb_64-01.S",
"rv64i_m/B/src/rev8-01.S",
"rv64i_m/B/src/andn-01.S",
"rv64i_m/B/src/orn-01.S",
"rv64i_m/B/src/xnor-01.S",
"rv64i_m/B/src/zext.h-01.S",
"rv64i_m/B/src/sext.b-01.S",
"rv64i_m/B/src/sext.h-01.S",
"rv64i_m/B/src/clz-01.S",
"rv64i_m/B/src/clzw-01.S",
"rv64i_m/B/src/cpop-01.S",
"rv64i_m/B/src/cpopw-01.S",
"rv64i_m/B/src/ctz-01.S",
"rv64i_m/B/src/ctzw-01.S",
"rv64i_m/B/src/rolw-01.S",
"rv64i_m/B/src/ror-01.S",
"rv64i_m/B/src/rori-01.S",
"rv64i_m/B/src/roriw-01.S",
"rv64i_m/B/src/rorw-01.S",
"rv64i_m/B/src/rol-01.S"
};
string arch64zbc[] = '{
`RISCVARCHTEST,
"rv64i_m/B/src/clmul-01.S",
"rv64i_m/B/src/clmulh-01.S",
"rv64i_m/B/src/clmulr-01.S"
};
string arch64zbs[] = '{
`RISCVARCHTEST,
"rv64i_m/B/src/bclr-01.S",
"rv64i_m/B/src/bclri-01.S",
"rv64i_m/B/src/bext-01.S",
"rv64i_m/B/src/bexti-01.S",
"rv64i_m/B/src/binv-01.S",
"rv64i_m/B/src/binvi-01.S",
"rv64i_m/B/src/bset-01.S",
"rv64i_m/B/src/bseti-01.S"
};
string arch32priv[] = '{
`RISCVARCHTEST,
"rv32i_m/privilege/src/ebreak.S",

View File

@ -9,7 +9,7 @@ current_dir = $(shell pwd)
#XLEN ?= 64
#all: root wally32 wally64
all: root arch32 wally32 wally32e arch64 wally64
all: root arch32 wally32 wally32e arch64 wally64
root:
mkdir -p $(work_dir)

View File

@ -105,6 +105,14 @@ class spike(pluginTemplate):
self.isa += 'd'
if "C" in ispec["ISA"]:
self.isa += 'c'
if "Zba" in ispec["ISA"]:
self.isa += '_Zba'
if "Zbb" in ispec["ISA"]:
self.isa += '_Zbb'
if "Zbc" in ispec["ISA"]:
self.isa += '_Zbc'
if "Zbs" in ispec["ISA"]:
self.isa += '_Zbs'
#TODO: The following assumes you are using the riscv-gcc toolchain. If
# not please change appropriately

View File

@ -1,7 +1,6 @@
hart_ids: [0]
hart0:
ISA: RV32IMAFDCZicsr_Zifencei
# ISA: RV32IMAFDCZicsr_Zifencei_Zba_Zbb_Zbc_Zbs
ISA: RV32IMAFDCZicsr_Zifencei_Zba_Zbb_Zbc_Zbs
physical_addr_sz: 32
User_Spec_Version: '2.3'
supported_xlen: [32]

View File

@ -1,7 +1,6 @@
hart_ids: [0]
hart0:
ISA: RV64IMAFDCSUZicsr_Zifencei
# ISA: RV64IMAFDCSUZicsr_Zifencei_Zba_Zbb_Zbc_Zbs
ISA: RV64IMAFDCSUZicsr_Zifencei_Zba_Zbb_Zbc_Zbs
physical_addr_sz: 56
User_Spec_Version: '2.3'
supported_xlen: [64]