Github_Repos/cvw
1
0
Fork 1
mirror of https://github.com/openhwgroup/cvw synced 2025-02-11 06:05:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

control for bitmanip

Browse Source
This commit is contained in:
James E. Stine 2024-02-24 22:38:21 -06:00
parent ce975a6336
commit eb1780a66d
2 changed files with 233 additions and 62 deletions

76
src/ieu/bmu/bitmanipalu.sv
View File

@ -31,9 +31,11 @@
module bitmanipalu import cvw::*; #(parameter cvw_t P) (
input logic [P.XLEN-1:0] A, B, // Operands
input logic W64, // W64-type instruction
input logic [1:0] BSelect, // Binary encoding of if it's a ZBA_ZBB_ZBC_ZBS instruction
input logic [2:0] ZBBSelect, // ZBB mux select signal
input logic [3:0] BSelect, // Binary encoding of if it's a ZBA_ZBB_ZBC_ZBS instruction
input logic [3:0] ZBBSelect, // ZBB mux select signal
input logic [2:0] Funct3, // Funct3 field of opcode indicates operation to perform
input logic [6:0] Funct7, // Funct7 field for ZKND and ZKNE operations
input logic [4:0] Rs2E, // Register source2 for RNUM of ZKNE/ZKND
input logic LT, // less than flag
input logic LTU, // less than unsigned flag
input logic [2:0] BALUControl, // ALU Control signals for B instructions in Execute Stage
@ -43,7 +45,10 @@ module bitmanipalu import cvw::*; #(parameter cvw_t P) (
output logic [P.XLEN-1:0] CondShiftA, // A is conditionally shifted for ShAdd instructions
output logic [P.XLEN-1:0] ALUResult); // Result
logic [P.XLEN-1:0] ZBBResult, ZBCResult; // ZBB, ZBC Result
logic [P.XLEN-1:0] ZBBResult, ZBCResult; // ZBB, ZBC Result
logic [P.XLEN-1:0] ZBKBResult, ZBKCResult, ZBKXResult; // ZBKB, ZBKC Result
logic [P.XLEN-1:0] ZKNDResult, ZKNEResult; // ZKND, ZKNE Result
logic [P.XLEN-1:0] ZKNHResult; // ZKNH Result
logic [P.XLEN-1:0] MaskB; // BitMask of B
logic [P.XLEN-1:0] RevA; // Bit-reversed A
logic Rotate; // Indicates if it is Rotate instruction
@ -90,16 +95,69 @@ module bitmanipalu import cvw::*; #(parameter cvw_t P) (
// ZBB Unit
if (P.ZBB_SUPPORTED) begin: zbb
zbb #(P.XLEN) ZBB(.A(ABMU), .RevA, .B(BBMU), .W64, .LT, .LTU, .BUnsigned(Funct3[0]), .ZBBSelect, .ZBBResult);
zbb #(P.XLEN) ZBB(.A(ABMU), .RevA, .B(BBMU), .W64, .LT, .LTU, .BUnsigned(Funct3[0]), .ZBBSelect(ZBBSelect[2:0]), .ZBBResult);
end else assign ZBBResult = 0;
// ZBKB Unit
if (P.ZBKB_SUPPORTED) begin: zbkb
zbkb #(P.XLEN) ZBKB(.A(ABMU), .B(BBMU), .RevA, .W64, .Funct3, .ZBKBSelect(ZBBSelect[2:0]), .ZBKBResult);
end else assign ZBKBResult = 0;
// ZBKC Unit
if (P.ZBKC_SUPPORTED) begin: zbkc
zbkc #(P.XLEN) ZBKC(.A(ABMU), .B(BBMU), .ZBKCSelect(ZBBSelect[0]), .ZBKCResult);
end else assign ZBKCResult = 0;
// ZBKX Unit
if (P.ZBKX_SUPPORTED) begin: zbkx
zbkx #(P.XLEN) ZBKX(.A(ABMU), .B(BBMU), .ZBKXSelect(ZBBSelect[2:0]), .ZBKXResult);
end else assign ZBKXResult = 0;
// ZKND Unit
if (P.ZKND_SUPPORTED) begin: zknd
if (P.XLEN == 32) begin
zknd_32 #(P.XLEN) ZKND32(.A(ABMU), .B(BBMU), .Funct7, .ZKNDSelect(ZBBSelect[2:0]), .ZKNDResult);
end
else begin
zknd_64 #(P.XLEN) ZKND64(.A(ABMU), .B(BBMU), .Funct7, .RNUM(Rs2E[3:0]), .ZKNDSelect(ZBBSelect[2:0]), .ZKNDResult);
end
end else assign ZKNDResult = 0;
// ZKNE Unit
if (P.ZKNE_SUPPORTED) begin: zkne
if (P.XLEN == 32) begin
zkne_32 #(P.XLEN) ZKNE32(.A(ABMU), .B(BBMU), .Funct7, .ZKNESelect(ZBBSelect[2:0]), .ZKNEResult);
end
else begin
zkne_64 #(P.XLEN) ZKNE64(.A(ABMU), .B(BBMU), .Funct7, .RNUM(Rs2E[3:0]), .ZKNESelect(ZBBSelect[2:0]), .ZKNEResult);
end
end else assign ZKNEResult = 0;
// ZKNH Unit
if (P.ZKNH_SUPPORTED) begin: zknh
if (P.XLEN == 32) begin
zknh_32 ZKNH_32(.A(ABMU), .B(BBMU), .ZKNHSelect(ZBBSelect), .ZKNHResult(ZKNHResult));
end
else begin
zknh_64 ZKNH_64(.A(ABMU), .B(BBMU), .ZKNHSelect(ZBBSelect), .ZKNHResult(ZKNHResult));
end
end else assign ZKNHResult = 0;
// Result Select Mux
always_comb
case (BSelect)
// 00: ALU, 01: ZBA/ZBS, 10: ZBB, 11: ZBC
2'b00: ALUResult = PreALUResult;
2'b01: ALUResult = FullResult; // NOTE: We don't use ALUResult because ZBA/ZBS instructions don't sign extend the MSB of the right-hand word.
2'b10: ALUResult = ZBBResult;
2'b11: ALUResult = ZBCResult;
// 0000: ALU, 0001: ZBA/ZBS, 0010: ZBB, 0011: ZBC, 0100: ZBKB, 0101: ZBKC, 0110: ZBKX
// 0111: ZKND, 1000: ZKNE, 1001: ZKNH, 1010: ZKSED, 1011: ZKSH...
4'b0000: ALUResult = PreALUResult;
4'b0001: ALUResult = FullResult; // NOTE: We don't use ALUResult because ZBA/ZBS instructions don't sign extend the MSB of the right-hand word.
4'b0010: ALUResult = ZBBResult;
4'b0011: ALUResult = ZBCResult;
4'b0100: ALUResult = ZBKBResult;
4'b0101: ALUResult = ZBKCResult;
4'b0110: ALUResult = ZBKXResult;
4'b0111: ALUResult = ZKNDResult;
4'b1000: ALUResult = ZKNEResult;
4'b1001: ALUResult = ZKNHResult;
default: ALUResult = PreALUResult;
endcase
endmodule

219
src/ieu/bmu/bmuctrl.sv
View File

@ -34,8 +34,8 @@ module bmuctrl import cvw::*; #(parameter cvw_t P) (
input logic StallD, FlushD, // Stall, flush Decode stage
input logic [31:0] InstrD, // Instruction in Decode stage
input logic ALUOpD, // Regular ALU Operation
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 [3:0] BSelectD, // Indicates if ZBA_ZBB_ZBC_ZBS instruction in one-hot encoding in Decode stage
output logic [3:0] 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
@ -44,8 +44,8 @@ module bmuctrl import cvw::*; #(parameter cvw_t P) (
// Execute stage control signals
input logic StallE, FlushE, // Stall, flush Execute stage
output logic [2:0] ALUSelectD, // ALU select
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 [3:0] BSelectE, // Indicates if ZBA_ZBB_ZBC_ZBS instruction in one-hot encoding
output logic [3:0] ZBBSelectE, // ZBB mux select signal
output logic BRegWriteE, // Indicates if it is a R type B instruction in Execute
output logic [2:0] BALUControlE, // ALU Control signals for B instructions in Execute Stage
output logic BMUActiveE // Bit manipulation instruction being executed
@ -62,7 +62,7 @@ module bmuctrl import cvw::*; #(parameter cvw_t P) (
logic [2:0] BALUSelectD; // ALU Mux select signal in Decode Stage for BMU operations
logic BALUOpD; // Indicates if it is an ALU B instruction in Decode Stage
`define BMUCTRLW 17
`define BMUCTRLW 20
logic [`BMUCTRLW-1:0] BMUControlsD; // Main B Instructions Decoder control signals
@ -78,92 +78,205 @@ module bmuctrl import cvw::*; #(parameter cvw_t P) (
BMUControlsD = `BMUCTRLW'b000_00_000_0_0_0_0_0_0_0_0_1; // default: Illegal bmu instruction;
if (P.ZBA_SUPPORTED) begin
casez({OpD, Funct7D, Funct3D})
17'b0110011_0010000_010: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_0_1_0_0_0_1_0; // sh1add
17'b0110011_0010000_100: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_0_1_0_0_0_1_0; // sh2add
17'b0110011_0010000_110: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_0_1_0_0_0_1_0; // sh3add
17'b0110011_0010000_010: BMUControlsD = `BMUCTRLW'b000_0001_0000_1_0_0_1_0_0_0_1_0; // sh1add
17'b0110011_0010000_100: BMUControlsD = `BMUCTRLW'b000_0001_0000_1_0_0_1_0_0_0_1_0; // sh2add
17'b0110011_0010000_110: BMUControlsD = `BMUCTRLW'b000_0001_0000_1_0_0_1_0_0_0_1_0; // sh3add
endcase
if (P.XLEN==64)
casez({OpD, Funct7D, Funct3D})
17'b0111011_0010000_010: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_1_0; // sh1add.uw
17'b0111011_0010000_100: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_1_0; // sh2add.uw
17'b0111011_0010000_110: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_1_0; // sh3add.uw
17'b0111011_0000100_000: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_0_0; // add.uw
17'b0011011_000010?_001: BMUControlsD = `BMUCTRLW'b001_01_000_1_1_1_1_0_0_0_0_0; // slli.uw
17'b0111011_0010000_010: BMUControlsD = `BMUCTRLW'b000_0001_0000_1_0_1_1_0_0_0_1_0; // sh1add.uw
17'b0111011_0010000_100: BMUControlsD = `BMUCTRLW'b000_0001_0000_1_0_1_1_0_0_0_1_0; // sh2add.uw
17'b0111011_0010000_110: BMUControlsD = `BMUCTRLW'b000_0001_0000_1_0_1_1_0_0_0_1_0; // sh3add.uw
17'b0111011_0000100_000: BMUControlsD = `BMUCTRLW'b000_0001_0000_1_0_1_1_0_0_0_0_0; // add.uw
17'b0011011_000010?_001: BMUControlsD = `BMUCTRLW'b001_0001_0000_1_1_1_1_0_0_0_0_0; // slli.uw
endcase
end
if (P.ZBB_SUPPORTED) begin
casez({OpD, Funct7D, Funct3D})
17'b0110011_0110000_001: BMUControlsD = `BMUCTRLW'b001_01_111_1_0_0_1_0_1_0_0_0; // rol
17'b0110011_0110000_101: BMUControlsD = `BMUCTRLW'b001_01_111_1_0_0_1_0_1_0_0_0; // ror
17'b0010011_0110000_001: if ((Rs2D[4:1] == 4'b0010))
BMUControlsD = `BMUCTRLW'b000_10_001_1_1_0_1_0_0_0_0_0; // sign extend instruction
BMUControlsD = `BMUCTRLW'b000_0010_0001_1_1_0_1_0_0_0_0_0; // sign extend instruction
else if ((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
BMUControlsD = `BMUCTRLW'b000_0010_0000_1_1_0_1_0_0_0_0_0; // count instruction
// // coverage off: This case can't occur in RV64
// 17'b0110011_0000100_100: if (P.XLEN == 32)
// BMUControlsD = `BMUCTRLW'b000_10_001_1_1_0_1_0_0_0_0_0; // zexth (rv32)
// // coverage on
17'b0110011_0100000_111: BMUControlsD = `BMUCTRLW'b111_01_111_1_0_0_1_1_0_0_0_0; // andn
17'b0110011_0100000_110: BMUControlsD = `BMUCTRLW'b110_01_111_1_0_0_1_1_0_0_0_0; // orn
17'b0110011_0100000_100: BMUControlsD = `BMUCTRLW'b100_01_111_1_0_0_1_1_0_0_0_0; // xnor
17'b0010011_011010?_101: if ((P.XLEN == 32 ^ Funct7D[0]) & (Rs2D == 5'b11000))
BMUControlsD = `BMUCTRLW'b000_10_010_1_1_0_1_0_0_0_0_0; // rev8
17'b0010011_0010100_101: if (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: BMUControlsD = `BMUCTRLW'b000_10_111_1_0_0_1_1_0_0_0_0; // max
17'b0110011_0000101_111: BMUControlsD = `BMUCTRLW'b000_10_111_1_0_0_1_1_0_0_0_0; // maxu
17'b0110011_0000101_100: BMUControlsD = `BMUCTRLW'b000_10_011_1_0_0_1_1_0_0_0_0; // min
17'b0110011_0000101_101: BMUControlsD = `BMUCTRLW'b000_10_011_1_0_0_1_1_0_0_0_0; // minu
BMUControlsD = `BMUCTRLW'b000_0010_0010_1_1_0_1_0_0_0_0_0; // orc.b
17'b0110011_0000101_110: BMUControlsD = `BMUCTRLW'b000_0010_0111_1_0_0_1_1_0_0_0_0; // max
17'b0110011_0000101_111: BMUControlsD = `BMUCTRLW'b000_0010_0111_1_0_0_1_1_0_0_0_0; // maxu
17'b0110011_0000101_100: BMUControlsD = `BMUCTRLW'b000_0010_0011_1_0_0_1_1_0_0_0_0; // min
17'b0110011_0000101_101: BMUControlsD = `BMUCTRLW'b000_0010_0011_1_0_0_1_1_0_0_0_0; // minu
endcase
if (P.XLEN==32)
casez({OpD, Funct7D, Funct3D})
17'b0110011_0000100_100: BMUControlsD = `BMUCTRLW'b000_10_001_1_1_0_1_0_0_0_0_0; // zexth (rv32)
17'b0010011_0110000_101: BMUControlsD = `BMUCTRLW'b001_00_111_1_1_0_1_0_1_0_0_0; // rori (rv32)
17'b0110011_0000100_100: BMUControlsD = `BMUCTRLW'b000_0010_0001_1_1_0_1_0_0_0_0_0; // zexth (rv32)
endcase
else if (P.XLEN==64)
casez({OpD, Funct7D, Funct3D})
17'b0111011_0000100_100: BMUControlsD = `BMUCTRLW'b000_10_001_1_0_0_1_0_0_0_0_0; // zexth (rv64)
17'b0111011_0110000_001: BMUControlsD = `BMUCTRLW'b001_00_111_1_0_1_1_0_1_0_0_0; // rolw
17'b0111011_0110000_101: BMUControlsD = `BMUCTRLW'b001_00_111_1_0_1_1_0_1_0_0_0; // rorw
17'b0010011_011000?_101: BMUControlsD = `BMUCTRLW'b001_00_111_1_1_0_1_0_1_0_0_0; // rori (rv64)
17'b0011011_0110000_101: BMUControlsD = `BMUCTRLW'b001_00_111_1_1_1_1_0_1_0_0_0; // roriw
17'b0111011_0000100_100: BMUControlsD = `BMUCTRLW'b000_0010_0001_1_0_0_1_0_0_0_0_0; // zexth (rv64)
17'b0011011_0110000_001: if ((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
BMUControlsD = `BMUCTRLW'b000_0010_0000_1_1_1_1_0_0_0_0_0; // count word instruction
endcase
end
if (P.ZBC_SUPPORTED)
casez({OpD, Funct7D, Funct3D})
17'b0110011_0000101_0??: BMUControlsD = `BMUCTRLW'b000_11_000_1_0_0_1_0_0_0_0_0; // ZBC instruction
17'b0110011_0000101_0??: BMUControlsD = `BMUCTRLW'b000_0011_0000_1_0_0_1_0_0_0_0_0; // ZBC instruction
endcase
if (P.ZBS_SUPPORTED) begin // ZBS
casez({OpD, Funct7D, Funct3D})
17'b0110011_0100100_001: BMUControlsD = `BMUCTRLW'b111_01_000_1_0_0_1_1_0_1_0_0; // bclr
17'b0110011_0100100_101: BMUControlsD = `BMUCTRLW'b101_01_000_1_0_0_1_1_0_1_0_0; // bext
17'b0110011_0110100_001: BMUControlsD = `BMUCTRLW'b100_01_000_1_0_0_1_0_0_1_0_0; // binv
17'b0110011_0010100_001: BMUControlsD = `BMUCTRLW'b110_01_000_1_0_0_1_0_0_1_0_0; // bset
17'b0110011_0100100_001: BMUControlsD = `BMUCTRLW'b111_0001_0000_1_0_0_1_1_0_1_0_0; // bclr
17'b0110011_0100100_101: BMUControlsD = `BMUCTRLW'b101_0001_0000_1_0_0_1_1_0_1_0_0; // bext
17'b0110011_0110100_001: BMUControlsD = `BMUCTRLW'b100_0001_0000_1_0_0_1_0_0_1_0_0; // binv
17'b0110011_0010100_001: BMUControlsD = `BMUCTRLW'b110_0001_0000_1_0_0_1_0_0_1_0_0; // bset
endcase
if (P.XLEN==32) // ZBS 64-bit
casez({OpD, Funct7D, Funct3D})
17'b0010011_0100100_001: BMUControlsD = `BMUCTRLW'b111_01_000_1_1_0_1_1_0_1_0_0; // bclri
17'b0010011_0100100_101: BMUControlsD = `BMUCTRLW'b101_01_000_1_1_0_1_1_0_1_0_0; // bexti
17'b0010011_0110100_001: BMUControlsD = `BMUCTRLW'b100_01_000_1_1_0_1_0_0_1_0_0; // binvi
17'b0010011_0010100_001: BMUControlsD = `BMUCTRLW'b110_01_000_1_1_0_1_0_0_1_0_0; // bseti
17'b0010011_0100100_001: BMUControlsD = `BMUCTRLW'b111_0001_0000_1_1_0_1_1_0_1_0_0; // bclri
17'b0010011_0100100_101: BMUControlsD = `BMUCTRLW'b101_0001_0000_1_1_0_1_1_0_1_0_0; // bexti
17'b0010011_0110100_001: BMUControlsD = `BMUCTRLW'b100_0001_0000_1_1_0_1_0_0_1_0_0; // binvi
17'b0010011_0010100_001: BMUControlsD = `BMUCTRLW'b110_0001_0000_1_1_0_1_0_0_1_0_0; // bseti
endcase
else if (P.XLEN==64) // ZBS 64-bit
casez({OpD, Funct7D, Funct3D})
17'b0010011_010010?_001: BMUControlsD = `BMUCTRLW'b111_01_000_1_1_0_1_1_0_1_0_0; // bclri (rv64)
17'b0010011_010010?_101: BMUControlsD = `BMUCTRLW'b101_01_000_1_1_0_1_1_0_1_0_0; // bexti (rv64)
17'b0010011_011010?_001: BMUControlsD = `BMUCTRLW'b100_01_000_1_1_0_1_0_0_1_0_0; // binvi (rv64)
17'b0010011_001010?_001: BMUControlsD = `BMUCTRLW'b110_01_000_1_1_0_1_0_0_1_0_0; // bseti (rv64)
17'b0010011_010010?_001: BMUControlsD = `BMUCTRLW'b111_0001_0000_1_1_0_1_1_0_1_0_0; // bclri (rv64)
17'b0010011_010010?_101: BMUControlsD = `BMUCTRLW'b101_0001_0000_1_1_0_1_1_0_1_0_0; // bexti (rv64)
17'b0010011_011010?_001: BMUControlsD = `BMUCTRLW'b100_0001_0000_1_1_0_1_0_0_1_0_0; // binvi (rv64)
17'b0010011_001010?_001: BMUControlsD = `BMUCTRLW'b110_0001_0000_1_1_0_1_0_0_1_0_0; // bseti (rv64)
endcase
end
if (P.ZBB_SUPPORTED | P.ZBS_SUPPORTED) // rv32i/64i shift instructions need BMU ALUSelect when BMU shifter is used
casez({OpD, Funct7D, Funct3D})
17'b0110011_0?0000?_?01: BMUControlsD = `BMUCTRLW'b001_00_000_1_0_0_1_0_0_0_0_0; // sra, srl, sll
17'b0010011_0?0000?_?01: BMUControlsD = `BMUCTRLW'b001_00_000_1_1_0_1_0_0_0_0_0; // srai, srli, slli
17'b0111011_0?0000?_?01: BMUControlsD = `BMUCTRLW'b001_00_000_1_0_1_1_0_0_0_0_0; // sraw, srlw, sllw
17'b0011011_0?0000?_?01: BMUControlsD = `BMUCTRLW'b001_00_000_1_1_1_1_0_0_0_0_0; // sraiw, srliw, slliw
17'b0110011_0?0000?_?01: BMUControlsD = `BMUCTRLW'b001_0000_0000_1_0_0_1_0_0_0_0_0; // sra, srl, sll
17'b0010011_0?0000?_?01: BMUControlsD = `BMUCTRLW'b001_0000_0000_1_1_0_1_0_0_0_0_0; // srai, srli, slli
17'b0111011_0?0000?_?01: BMUControlsD = `BMUCTRLW'b001_0000_0000_1_0_1_1_0_0_0_0_0; // sraw, srlw, sllw
17'b0011011_0?0000?_?01: BMUControlsD = `BMUCTRLW'b001_0000_0000_1_1_1_1_0_0_0_0_0; // sraiw, srliw, slliw
endcase
if (P.ZBKB_SUPPORTED) begin // ZBKB Bitmanip
casez({OpD,Funct7D, Funct3D})
17'b0110011_0000100_100: BMUControlsD = `BMUCTRLW'b000_0100_0001_1_0_0_1_0_0_0_0_0; // pack
17'b0110011_0000100_111: BMUControlsD = `BMUCTRLW'b000_0100_0001_1_0_0_1_0_0_0_0_0; //packh
17'b0010011_0110100_101: if (Rs2D == 5'b00111)
BMUControlsD = `BMUCTRLW'b000_0100_0000_1_1_0_1_0_0_0_0_0; //brev8
endcase
if (P.XLEN==32)
casez({OpD, Funct7D, Funct3D})
17'b0010011_0000100_001: if (Rs2D == 5'b01111)
BMUControlsD = `BMUCTRLW'b000_0100_0011_1_1_0_1_0_0_0_0_0; //zip
17'b0010011_0000100_101: if (Rs2D == 5'b01111)
BMUControlsD = `BMUCTRLW'b000_0100_0011_1_1_0_1_0_0_0_0_0; //unzip
endcase
else if (P.XLEN==64)
casez({OpD,Funct7D, Funct3D})
17'b0111011_0000100_100: BMUControlsD = `BMUCTRLW'b000_0100_0101_1_0_1_1_0_0_0_0_0; //packw
endcase
end
if (P.ZBB_SUPPORTED | P.ZBKB_SUPPORTED) begin // ZBB and ZBKB shared instructions
casez({OpD, Funct7D, Funct3D})
17'b0110011_0110000_001: BMUControlsD = `BMUCTRLW'b001_0001_0111_1_0_0_1_0_1_0_0_0; // rol
17'b0110011_0110000_101: BMUControlsD = `BMUCTRLW'b001_0001_0111_1_0_0_1_0_1_0_0_0; // ror
17'b0110011_0100000_111: BMUControlsD = `BMUCTRLW'b111_0001_0111_1_0_0_1_1_0_0_0_0; // andn
17'b0110011_0100000_110: BMUControlsD = `BMUCTRLW'b110_0001_0111_1_0_0_1_1_0_0_0_0; // orn
17'b0110011_0100000_100: BMUControlsD = `BMUCTRLW'b100_0001_0111_1_0_0_1_1_0_0_0_0; // xnor
17'b0010011_011010?_101: if ((P.XLEN == 32 ^ Funct7D[0]) & (Rs2D == 5'b11000))
BMUControlsD = `BMUCTRLW'b000_0010_0010_1_1_0_1_0_0_0_0_0; // rev8
endcase
if (P.XLEN==32)
casez({OpD, Funct7D, Funct3D})
17'b0010011_0110000_101: BMUControlsD = `BMUCTRLW'b001_0000_0111_1_1_0_1_0_1_0_0_0; // rori (rv32)
endcase
else if (P.XLEN==64)
casez({OpD, Funct7D, Funct3D})
17'b0111011_0110000_001: BMUControlsD = `BMUCTRLW'b001_0000_0111_1_0_1_1_0_1_0_0_0; // rolw
17'b0111011_0110000_101: BMUControlsD = `BMUCTRLW'b001_0000_0111_1_0_1_1_0_1_0_0_0; // rorw
17'b0010011_011000?_101: BMUControlsD = `BMUCTRLW'b001_0000_0111_1_1_0_1_0_1_0_0_0; // rori (rv64)
17'b0011011_0110000_101: BMUControlsD = `BMUCTRLW'b001_0000_0111_1_1_1_1_0_1_0_0_0; // roriw
endcase
end
if (P.ZBKC_SUPPORTED) begin // ZBKC
casez({OpD, Funct7D, Funct3D})
17'b0110011_0000101_001: BMUControlsD = `BMUCTRLW'b000_0101_0000_1_0_0_1_0_0_0_0_0; // clmul
17'b0110011_0000101_011: BMUControlsD = `BMUCTRLW'b000_0101_0001_1_0_0_1_0_0_0_0_0; // clmulh
endcase
end
if (P.ZBKX_SUPPORTED) begin //ZBKX
casez({OpD, Funct7D, Funct3D})
17'b0110011_0010100_100: BMUControlsD = `BMUCTRLW'b000_0110_0000_1_0_0_1_0_0_0_0_0; // xperm8
17'b0110011_0010100_010: BMUControlsD = `BMUCTRLW'b000_0110_0001_1_0_0_1_0_0_0_0_0; // xperm4
endcase
end
if (P.ZKND_SUPPORTED) begin //ZKND
if (P.XLEN==32)
casez({OpD, Funct7D, Funct3D})
17'b0110011_??10101_000: BMUControlsD = `BMUCTRLW'b000_0111_0000_1_0_0_1_0_0_0_0_0; // aes32dsi - final round decrypt
17'b0110011_??10111_000: BMUControlsD = `BMUCTRLW'b000_0111_0001_1_0_0_1_0_0_0_0_0; // aes32dsmi - mid round decrypt
endcase
else if (P.XLEN==64)
casez({OpD, Funct7D, Funct3D})
17'b0110011_0011101_000: BMUControlsD = `BMUCTRLW'b000_0111_0000_1_0_0_1_0_0_0_0_0; // aes64ds - decrypt final round
17'b0110011_0011111_000: BMUControlsD = `BMUCTRLW'b000_0111_0001_1_0_0_1_0_0_0_0_0; // aes64dsm - decrypt mid round
17'b0010011_0011000_001: if (Rs2D == 5'b00000)
BMUControlsD = `BMUCTRLW'b000_0111_0010_1_1_0_1_0_0_0_0_0; // aes64im - decrypt keyschdule mixcolumns
endcase
end
if (P.ZKNE_SUPPORTED) begin //ZKNE
if (P.XLEN==32)
casez({OpD, Funct7D, Funct3D})
17'b0110011_??10001_000: BMUControlsD = `BMUCTRLW'b000_1000_0000_1_0_0_1_0_0_0_0_0; // aes32esi - final round encrypt
17'b0110011_??10011_000: BMUControlsD = `BMUCTRLW'b000_1000_0001_1_0_0_1_0_0_0_0_0; // aes32esmi - mid round encrypt
endcase
else if (P.XLEN==64)
casez({OpD, Funct7D, Funct3D})
17'b0110011_0011001_000: BMUControlsD = `BMUCTRLW'b000_1000_0000_1_0_0_1_0_0_0_0_0; // aes64es - encrypt final round
17'b0110011_0011011_000: BMUControlsD = `BMUCTRLW'b000_1000_0001_1_0_0_1_0_0_0_0_0; // aes64esm - encrypt mid round
endcase
end
if (P.ZKND_SUPPORTED | P.ZKNE_SUPPORTED) begin // ZKND and ZKNE shared instructions
casez({OpD, Funct7D, Funct3D})
17'b0010011_0011000_001: if (Rs2D[4] == 1'b1)
BMUControlsD = `BMUCTRLW'b000_0111_0011_1_0_0_1_0_0_0_0_0; // aes64ks1i - key schedule istr1 ... Don't know why this works here only ... P.XLEN is not 64 bits?
endcase
if (P.XLEN==64)
casez({OpD, Funct7D, Funct3D})
17'b0110011_0111111_000: BMUControlsD = `BMUCTRLW'b000_0111_0100_1_0_0_1_0_0_0_0_0; // aes64ks2 - key schedule istr2
endcase
end
if (P.ZKNH_SUPPORTED) begin // ZKNH
casez({OpD, Funct7D, Funct3D})
17'b0010011_0001000_001:
if (Rs2D == 5'b00010) BMUControlsD = `BMUCTRLW'b000_1001_0000_1_0_0_1_0_0_0_0_0; // sha256sig0
else if (Rs2D == 5'b00011) BMUControlsD = `BMUCTRLW'b000_1001_0001_1_0_0_1_0_0_0_0_0; // sha256sig1
else if (Rs2D == 5'b00000) BMUControlsD = `BMUCTRLW'b000_1001_0010_1_0_0_1_0_0_0_0_0; // sha256sum0
else if (Rs2D == 5'b00001) BMUControlsD = `BMUCTRLW'b000_1001_0011_1_0_0_1_0_0_0_0_0; // sha256sum1
endcase
if (P.XLEN==32)
casez({OpD, Funct7D, Funct3D})
17'b0110011_0101110_000: BMUControlsD = `BMUCTRLW'b000_1001_0100_1_0_0_1_0_0_0_0_0; // sha512sig0h
17'b0110011_0101010_000: BMUControlsD = `BMUCTRLW'b000_1001_0101_1_0_0_1_0_0_0_0_0; // sha512sig0l
17'b0110011_0101111_000: BMUControlsD = `BMUCTRLW'b000_1001_0110_1_0_0_1_0_0_0_0_0; // sha512sig1h
17'b0110011_0101011_000: BMUControlsD = `BMUCTRLW'b000_1001_0111_1_0_0_1_0_0_0_0_0; // sha512sig1l
17'b0110011_0101000_000: BMUControlsD = `BMUCTRLW'b000_1001_1000_1_0_0_1_0_0_0_0_0; // sha512sum0r
17'b0110011_0101001_000: BMUControlsD = `BMUCTRLW'b000_1001_1001_1_0_0_1_0_0_0_0_0; // sha512sum1r
endcase
else if (P.XLEN==64)
casez({OpD, Funct7D, Funct3D})
17'b0010011_0001000_001:
if (Rs2D == 5'b00110) BMUControlsD = `BMUCTRLW'b000_1001_1010_1_0_0_1_0_0_0_0_0; // sha512sig0
else if (Rs2D == 5'b00111) BMUControlsD = `BMUCTRLW'b000_1001_1011_1_0_0_1_0_0_0_0_0; // sha512sig1
else if (Rs2D == 5'b00100) BMUControlsD = `BMUCTRLW'b000_1001_1100_1_0_0_1_0_0_0_0_0; // sha512sum0
else if (Rs2D == 5'b00101) BMUControlsD = `BMUCTRLW'b000_1001_1101_1_0_0_1_0_0_0_0_0; // sha512sum1
endcase
end
end
// Unpack Control Signals
@ -176,5 +289,5 @@ module bmuctrl import cvw::*; #(parameter cvw_t P) (
assign ALUSelectD = BALUOpD ? BALUSelectD : (ALUOpD ? Funct3D : 3'b000);
// BMU Execute stage pipieline control register
flopenrc #(10) controlregBMU(clk, reset, FlushE, ~StallE, {BSelectD, ZBBSelectD, BRegWriteD, BALUControlD, ~IllegalBitmanipInstrD}, {BSelectE, ZBBSelectE, BRegWriteE, BALUControlE, BMUActiveE});
flopenrc #(13) controlregBMU(clk, reset, FlushE, ~StallE, {BSelectD, ZBBSelectD, BRegWriteD, BALUControlD, ~IllegalBitmanipInstrD}, {BSelectE, ZBBSelectE, BRegWriteE, BALUControlE, BMUActiveE});
endmodule