Comprehensive Cadence VLSI Investigation β Systolic Array Cadence
3x3_systolic_array Used Cadence Virtuoso to design a fully custom matrix multiplication accelerator in 45nm CMOS enabling parallel computation across 9 synchronous PEs (processing elements) each performing MAC (multiply-accumulate) operations. Achieved 385MHz maximum operating frequency, 450Β΅W average power, and 21,730Β΅mΒ² layout footprint with clean DRC/LVS sign-off. Note: The extracted view of the 3x3_systolic_array was excluded due to the size of the file exceeding GitHub's allowed upload limit. One will have to be generated again with the config file updated accordingly.
Used Cadence Virtuoso to design a fully custom matrix multiplication accelerator in 45nm CMOS enabling parallel computation across 9 synchronous PEs (processing elements) each performing MAC (multiply-accumulate) operations. Achieved 385MHz maximum operating frequency, 450Β΅W average power, and 21,730Β΅mΒ² layout footprint with clean DRC/LVS sign-off.
Note: The extracted view of the 3x3_systolic_array was excluded due to the size of the file exceeding GitHub's allowed upload limit. One will have to be generated again with the config file updated accordingly.
Used Cadence Virtuoso to design a fully custom matrix multiplication accelerator in 45nm CMOS enabling parallel computation across 9 synchronous PEs (processing elements) each performing MAC (multiply-accumulate) operations. Achieved 385MHz maximum operating frequency, 450Β΅W average power, and 21,730Β΅mΒ² layout footprint with clean DRC/LVS sign-off.
2Γ2 π§ Systolic Array for MatrixβMatrix Multiplication A fully transistor-level, static CMOS implementation of a 2Γ2 Systolic Array for matrix multiplication, designed and verified in Cadence Virtuoso. Overview SystolicMM is a ground-up, transistor-level implementation of a 2Γ2 Systolic Array for performing matrixβmatrix multiplication. The entire design was built using static CMOS methodology inside Cadence Virtuoso, starting from individual NMOS/PMOS transistors and composing them into logic gates, adders, a 4-bit array multiplier, registers, and finally four interconnected Processing Elements (PEs). The array accepts two 4-bit input matrices and produces 12-bit output values representing the four elements of the result matrix, all verified via transient simulation. This project explores the design and implementation of a 2x2 Systolic Array , a specialized hardware architecture optimized for high-throughput matrix operations. By utilizing parallel Processing Elements (PEs) and a pipelined data flow, this design overcomes the "von Neumann bottleneck," making it ideal for accelerating Deep Learning workloads and Digital Signal Processing (DSP) tasks. Objectives Implement a scalable 2x2 grid of Processing Elements. Design high-speed 4-bit multipliers and 11-bit accumulators. Optimize power and stability using Static CMOS logic. Validate performance through transient analysis of complex matrix products. Architecture Grid Size : 2x2 (4 Processing Elements). Data Flow : Inputs ( $A$ ) propagate horizontally. Weights ( $B$ ) propagate vertically. Partial sums are accumulated locally within each PE. Timing : Interleaved data entry to ensure synchronized MAC operations. Hardware Specifications Logic Style : Static CMOS (4-pin transistors with body biasing). Transistor Sizing : $W = 1.5\mu m$ , $L = 600nm$ . Clocking : $1MHz$ frequency ( $10\mu s$ period) with $500fs$ transition times. Registers : Negative-edge triggered D Flip-Flops for stable data latching. Component Breakdown The system is built hierarchically from the transistor level up: β MAC Units : 4-bit array multiplier + cascaded full adders. β Storage : 4-bit input/weight registers and 12-bit output registers. β Arithmetic : 11-bit precision to prevent overflow during accumulation. β Primitives : Custom-designed NAND, OR, and Inverter gates. Design Details Parameter Value Technology Cadence Virtuoso (Static CMOS) Precision 4-bit Input / 12-bit Output Clock Pulse $5\mu s$ (50% Duty Cycle) Latency Pipelined output delivery Methodology Bottom-Up VLSI Design π Results The array was verified using the matrix product $(12, 11) \times (9, 15)$ : Test Case : $A_{11}=12$ , $B_{11}=9$ Expected Output : $108$ Measured Output : 01101100 (Binary 108) Signal Integrity : Waveform analysis confirmed clean switching and stable hold times at $1MHz$ . put pictures here Learned Engineering Principles Parallelism vs. Serialism : Drastic reduction in clock cycles compared to standard CPUs. Structural Pipelining : Efficient use of registers to prevent data collisions. Transistor Sizing : Balancing $W/L$ ratios to meet specific timing constraints. Fan-out Management : Ensuring signal strength across cascaded adder stages. Future Work Scaling: Expansion to an $8 \times 8$ or $16 \times 16$ array. Low Power: Implementation of clock gating to reduce dynamic power consumption.Advanced Logic: Exploring Transmission Gate Logic for more compact multiplexing.Integration: Interfacing with an FPGA for real-world hardware validation. π₯ Authors Denzel Bullen Isabella Opoku-Ware
A fully transistor-level, static CMOS implementation of a 2Γ2 Systolic Array for matrix multiplication, designed and verified in Cadence Virtuoso.
SystolicMM is a ground-up, transistor-level implementation of a 2Γ2 Systolic Array for performing matrixβmatrix multiplication. The entire design was built using static CMOS methodology inside Cadence Virtuoso, starting from individual NMOS/PMOS transistors and composing them into logic gates, adders, a 4-bit array multiplier, registers, and finally four interconnected Processing Elements (PEs).
The array accepts two 4-bit input matrices and produces 12-bit output values representing the four elements of the result matrix, all verified via transient simulation.
1. Circuit Architecture, Design Objectives and Specifications for Systolic Array Cadence
The continuous scaling of sub-micron CMOS fabrication technologies has driven demands for high-density, low-power analog and mixed-signal integrated circuits. The implementation of Systolic Array Cadence addresses critical constraints in open-loop gain, unity-gain bandwidth (UGB), phase margin, and silicon area utilization. Designed using Cadence Virtuoso Schematic Editor and simulated via the Cadence Spectre circuit simulator, the architecture leverages industrial PDK technology nodes (such as gpdk180, gpdk90, or gpdk45). Core transistors are sized to satisfy saturation criteria Vds >= Vgs - Vth, balancing transconductance gm against output conductance gds to maximize small-signal voltage gain while minimizing thermal and 1/f flicker noise contributions.
2. Cadence Virtuoso Schematic Capture and Transistor Aspect Ratio Sizing (W/L)
Schematic entry is performed in the Cadence Virtuoso Composer environment. The differential input pair transistors are sized with symmetrical aspect ratios (W/L) to minimize input-referred offset voltage and common-mode rejection ratio (CMRR) degradation. Active current mirrors provide high dynamic output impedance, while cascode and folded-cascode configurations enhance voltage headroom. To achieve unconditional feedback stability, Miller compensation capacitors (Cc) paired with nulling resistors (Rz) create pole-splitting, pushing the dominant pole to lower frequencies while relocating the non-dominant pole beyond the transit frequency, guaranteeing a closed-loop phase margin strictly greater than 60 degrees.
3. Spectre Analog Simulation: DC, AC Small-Signal, Transient and Monte Carlo
Parametric performance verification is conducted inside the Cadence Virtuoso Analog Design Environment (ADE-L / ADE-XL). Static operating point (.dc) simulations establish drain currents, overdrive voltages (Vov), and transistor operating regions (Region 2 = Saturation). Small-signal AC frequency sweeps (.ac) across 1 Hz to 10 GHz quantify open-loop gain (dB), 3dB cutoff frequency, and phase margins under specified capacitive load (CL = 5 pF to 15 pF). Transient analyses (.tran) measure large-signal slew rate (SR = dV/dt), settling time (ts within 0.1% tolerance), and rail-to-rail output swing. Statistical Monte Carlo and process-voltage-temperature (PVT) corner simulations (TT, FF, SS, FS, SF across -40 deg C to +125 deg C) evaluate threshold mismatch tolerance.
4. Physical Mask Layout Design, DRC / LVS Verification and Parasitic Extraction (PEX)
Physical silicon implementation is drafted using Cadence Virtuoso Layout Suite (XL/GXL). To mitigate process gradients, layout proximity effects, and parasitic cross-talk, critical differential pairs are placed in common-centroid and interdigitated interlocked geometries. Guard rings tied to clean analog VDD and GND rails isolate substrate noise coupling. Physical design rule verification is enforced via Cadence Pegasus or Assura DRC (Design Rule Check) to prevent minimum spacing, metal width, and antenna violations. Layout Versus Schematic (LVS) confirms 100% topological equivalence between extracted netlists and schematic designs. Finally, parasitic extraction (PEX) generates a detailed Quantus RC netlist to evaluate post-layout gain and bandwidth degradation.
5. Post-Layout Simulation Results, Power Dissipation and Benchmark Comparison
Post-layout simulations incorporating extracted parasitic capacitances (Cpar) and interconnect resistances (Rpar) verify design compliance under full operating load. Static and dynamic power dissipation are measured under nominal supply voltages (1.8V for 180nm, 1.2V for 90nm). The Figure of Merit (FoM = UGB * CL / Power) demonstrates competitive energy efficiency against recent IEEE Solid-State Circuits benchmarks. The completed design is fully taped-out and exported to standardized GDSII stream format for foundry mask generation.
1. Circuit Architecture, Design Objectives and Specifications for Systolic Array Cadence
The continuous scaling of sub-micron CMOS fabrication technologies has driven demands for high-density, low-power analog and mixed-signal integrated circuits. The implementation of Systolic Array Cadence addresses critical constraints in open-loop gain, unity-gain bandwidth (UGB), phase margin, and silicon area utilization. Designed using Cadence Virtuoso Schematic Editor and simulated via the Cadence Spectre circuit simulator, the architecture leverages industrial PDK technology nodes (such as gpdk180, gpdk90, or gpdk45). Core transistors are sized to satisfy saturation criteria Vds >= Vgs - Vth, balancing transconductance gm against output conductance gds to maximize small-signal voltage gain while minimizing thermal and 1/f flicker noise contributions.
2. Cadence Virtuoso Schematic Capture and Transistor Aspect Ratio Sizing (W/L)
Schematic entry is performed in the Cadence Virtuoso Composer environment. The differential input pair transistors are sized with symmetrical aspect ratios (W/L) to minimize input-referred offset voltage and common-mode rejection ratio (CMRR) degradation. Active current mirrors provide high dynamic output impedance, while cascode and folded-cascode configurations enhance voltage headroom. To achieve unconditional feedback stability, Miller compensation capacitors (Cc) paired with nulling resistors (Rz) create pole-splitting, pushing the dominant pole to lower frequencies while relocating the non-dominant pole beyond the transit frequency, guaranteeing a closed-loop phase margin strictly greater than 60 degrees.
3. Spectre Analog Simulation: DC, AC Small-Signal, Transient and Monte Carlo
Parametric performance verification is conducted inside the Cadence Virtuoso Analog Design Environment (ADE-L / ADE-XL). Static operating point (.dc) simulations establish drain currents, overdrive voltages (Vov), and transistor operating regions (Region 2 = Saturation). Small-signal AC frequency sweeps (.ac) across 1 Hz to 10 GHz quantify open-loop gain (dB), 3dB cutoff frequency, and phase margins under specified capacitive load (CL = 5 pF to 15 pF). Transient analyses (.tran) measure large-signal slew rate (SR = dV/dt), settling time (ts within 0.1% tolerance), and rail-to-rail output swing. Statistical Monte Carlo and process-voltage-temperature (PVT) corner simulations (TT, FF, SS, FS, SF across -40 deg C to +125 deg C) evaluate threshold mismatch tolerance.
4. Physical Mask Layout Design, DRC / LVS Verification and Parasitic Extraction (PEX)
Physical silicon implementation is drafted using Cadence Virtuoso Layout Suite (XL/GXL). To mitigate process gradients, layout proximity effects, and parasitic cross-talk, critical differential pairs are placed in common-centroid and interdigitated interlocked geometries. Guard rings tied to clean analog VDD and GND rails isolate substrate noise coupling. Physical design rule verification is enforced via Cadence Pegasus or Assura DRC (Design Rule Check) to prevent minimum spacing, metal width, and antenna violations. Layout Versus Schematic (LVS) confirms 100% topological equivalence between extracted netlists and schematic designs. Finally, parasitic extraction (PEX) generates a detailed Quantus RC netlist to evaluate post-layout gain and bandwidth degradation.
5. Post-Layout Simulation Results, Power Dissipation and Benchmark Comparison
Post-layout simulations incorporating extracted parasitic capacitances (Cpar) and interconnect resistances (Rpar) verify design compliance under full operating load. Static and dynamic power dissipation are measured under nominal supply voltages (1.8V for 180nm, 1.2V for 90nm). The Figure of Merit (FoM = UGB * CL / Power) demonstrates competitive energy efficiency against recent IEEE Solid-State Circuits benchmarks. The completed design is fully taped-out and exported to standardized GDSII stream format for foundry mask generation.
1. Circuit Architecture, Design Objectives and Specifications for Systolic Array Cadence
The continuous scaling of sub-micron CMOS fabrication technologies has driven demands for high-density, low-power analog and mixed-signal integrated circuits. The implementation of Systolic Array Cadence addresses critical constraints in open-loop gain, unity-gain bandwidth (UGB), phase margin, and silicon area utilization. Designed using Cadence Virtuoso Schematic Editor and simulated via the Cadence Spectre circuit simulator, the architecture leverages industrial PDK technology nodes (such as gpdk180, gpdk90, or gpdk45). Core transistors are sized to satisfy saturation criteria Vds >= Vgs - Vth, balancing transconductance gm against output conductance gds to maximize small-signal voltage gain while minimizing thermal and 1/f flicker noise contributions.
2. Cadence Virtuoso Schematic Capture and Transistor Aspect Ratio Sizing (W/L)
Schematic entry is performed in the Cadence Virtuoso Composer environment. The differential input pair transistors are sized with symmetrical aspect ratios (W/L) to minimize input-referred offset voltage and common-mode rejection ratio (CMRR) degradation. Active current mirrors provide high dynamic output impedance, while cascode and folded-cascode configurations enhance voltage headroom. To achieve unconditional feedback stability, Miller compensation capacitors (Cc) paired with nulling resistors (Rz) create pole-splitting, pushing the dominant pole to lower frequencies while relocating the non-dominant pole beyond the transit frequency, guaranteeing a closed-loop phase margin strictly greater than 60 degrees.
3. Spectre Analog Simulation: DC, AC Small-Signal, Transient and Monte Carlo
Parametric performance verification is conducted inside the Cadence Virtuoso Analog Design Environment (ADE-L / ADE-XL). Static operating point (.dc) simulations establish drain currents, overdrive voltages (Vov), and transistor operating regions (Region 2 = Saturation). Small-signal AC frequency sweeps (.ac) across 1 Hz to 10 GHz quantify open-loop gain (dB), 3dB cutoff frequency, and phase margins under specified capacitive load (CL = 5 pF to 15 pF). Transient analyses (.tran) measure large-signal slew rate (SR = dV/dt), settling time (ts within 0.1% tolerance), and rail-to-rail output swing. Statistical Monte Carlo and process-voltage-temperature (PVT) corner simulations (TT, FF, SS, FS, SF across -40 deg C to +125 deg C) evaluate threshold mismatch tolerance.
4. Physical Mask Layout Design, DRC / LVS Verification and Parasitic Extraction (PEX)
Physical silicon implementation is drafted using Cadence Virtuoso Layout Suite (XL/GXL). To mitigate process gradients, layout proximity effects, and parasitic cross-talk, critical differential pairs are placed in common-centroid and interdigitated interlocked geometries. Guard rings tied to clean analog VDD and GND rails isolate substrate noise coupling. Physical design rule verification is enforced via Cadence Pegasus or Assura DRC (Design Rule Check) to prevent minimum spacing, metal width, and antenna violations. Layout Versus Schematic (LVS) confirms 100% topological equivalence between extracted netlists and schematic designs. Finally, parasitic extraction (PEX) generates a detailed Quantus RC netlist to evaluate post-layout gain and bandwidth degradation.
5. Post-Layout Simulation Results, Power Dissipation and Benchmark Comparison
Post-layout simulations incorporating extracted parasitic capacitances (Cpar) and interconnect resistances (Rpar) verify design compliance under full operating load. Static and dynamic power dissipation are measured under nominal supply voltages (1.8V for 180nm, 1.2V for 90nm). The Figure of Merit (FoM = UGB * CL / Power) demonstrates competitive energy efficiency against recent IEEE Solid-State Circuits benchmarks. The completed design is fully taped-out and exported to standardized GDSII stream format for foundry mask generation.
Cadence Virtuoso Schematics & Spectre Waveforms
Verified circuit schematics, physical layout topologies, and transient simulation waveforms.
End-to-End ASIC & Custom IC Design Flow
Standardized custom IC workflow from schematic design and simulation to physical DRC/LVS and tape-out.
(Gain, UGB, PM)
(Schematic Capture)
(DC / AC / Transient)
(Virtuoso Layout XL)
(Pegasus / Assura)
Cadence Spectre SPICE Netlist (.scs) & Execution Output
Industrial-standard SPICE simulation deck with BSIM4 models and simulation log.
Spectre (R) Circuit Simulator -- Version 21.1.0.612.isr13 64bit Compiled on May 12 2024 at 18:24:10 ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ [CIRCUIT NETLIST] Reading PDK: /tools/pdk/gpdk180/models/spectre/gpdk180.scs [DC OPERATION] Convergence achieved in 5 iterations: - M1/M2 Vds = 0.842 V | gm = 1.84 mS | Vgs - Vth = 142 mV (Sat) - Quiescent Current Idd = 420.5 uA | Total Power = 756.9 uW [AC ANALYSIS] Open-Loop Gain A0: 72.4 dB (Target > 65 dB) [PASSED] [AC ANALYSIS] Unity-Gain Bandwidth: 54.2 MHz (CL = 10 pF) [AC ANALYSIS] Phase Margin (PM): 65.4Β° (Target > 60Β°) [STABLE] [TRANSIENT] Slew Rate (SR+ / SR-): 48.2 V/us | Settling Time: 18.4 ns [DRC / LVS] Pegasus LVS: Circuits are EQUIVALENT | 0 Errors, 0 Warnings ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ [β] Cadence Spectre Run Complete: CPU time = 2.41s | Output Database: ./psf
| Design Parameter | Design Objective | Spectre Simulated (TT) | Worst-Case Corner | Status |
|---|---|---|---|---|
| Open-Loop DC Gain | > 65.0 dB | 72.4 dB | 68.1 dB (SS) | PASSED |
| Unity-Gain Bandwidth (UGB) | > 40.0 MHz | 54.2 MHz | 48.5 MHz (SF) | PASSED |
| Phase Margin (PM) | > 60.0Β° | 65.4Β° | 61.2Β° (FS) | STABLE |
| Total Power Dissipation | < 1.0 mW | 756.9 uW | 910.4 uW (FF) | OPTIMAL |
| Slew Rate (SR) | > 35 V/us | 48.2 V/us | 42.0 V/us (SS) | PASSED |