Cloud native EDA tools & pre-optimized hardware platforms
ASIP Designer comes with an extensive library of example processor models provided as nML source code. They can be used as a starting point for architectural exploration and customer-specific production designs, or just be partially leveraged as reference implementation for selected architectural features. All these models come with a fully working toolset, SDK and synthesizable RTL, but are not to be considered as verified IP.
Compact 16-bit RISC microcontroller
Compact 16-bit RISC microcontroller with reduced hardware
Trv (Family)
Variants of microcontrollers with RISC-V ISA
DLX (Family)
Variants of Hennessy & Patterson 32-bit RISC microcontroller DLX
16/32-bit DSP with single MAC unit, dual load-store units with post-modify addressing, and 3-way instruction-level parallelism in 16/32-bit variable-length instructions
Tvec (Family)
Variants of wide SIMD processor, with per-lane predication controlled by predicate registers, and gather/scatter-based vector addressing. Additional family member supports compilation of OpenCL C kernels
Tvliw (Family)
Variants of a 4-slot VLIW processor, with predication of VLIW slots and instruction compaction
Tutorial model used in basic processor modeling hands-on laboratory
Workshop model: Matrix multiplication on a RISC-V scalar core (Trv32p5x) with SIMD vector and ILP extensions
Historic educational model used in manuals
Video accelerator for motion estimation
Accelerator for gaussian image filtering
SIMD vector processor for communication kernels, supporting complex-type operations
Scalar accelerator for block matrix inversion
Scalar FFT accelerator
Accelerator for 5G New Radio MMSE equalization using Cholesky decomposition
Accelerator for SHA256 hashing by extension of a RISC-V scalar core
Accelerator for the Kyber key encapsulation mechanism (post-quantum cryptography) by extension of a RISC-V scalar core
AI accelerator for MobileNet Convolutional Neural Network
Medium-throughput AI accelerator supporting TFLM
Primecore *
ASIP for FFT and DFT computation in 4G/5G mobile devices, supporting:
Tcrypt *
Accelerator for AES encryption and decryption
Tvox *
Accelerator for simultaneous localization and mapping (SLAM)
JEMA/JEMB *
Dual-ASIP design for JPEG encoding
* Available on demand. For more information, please contact 草榴社区 by sending your request to asipinfo@synopsys.com
16-bit microcontroller |
|
Back to example models overview
16-bit microcontroller with reduced hardware (based on Tmicro) |
Differences to Tmicro:
|
Back to example models overview
The Trv family is a collection of RISC-V processor models combining different data path widths, pipeline depths, and optional extensions. The base models, supporting integer and multiplication instructions, are labeled Trv<ww>p<n>[f][x][c], with <ww> denoting the data path width (32 or 64) and <n> denoting the pipeline depth (3 or 5). Optional extensions are indicated by additional suffixes:
A separate model, Trv32p3sdx, with “sdx” denoting “simple data path extensions” contains a low-barrier modeling skeleton for custom data path extensions and comes with a set of example implementations for different application domains, such as FFT, SHA256 encryption, and a neural network for keyword spotting.
The following table lists the features of the available Trv family models in detail.
Trv32p3 (base model): 32-bit RISC-V microcontroller with with 3-stage pipeline
|
|
Trv32p3x (variant): Trv32p3 with DSP extensions |
Features on top of Trv32p3:
|
Trv32p3f (variant): Trv32p3 with floating-point hardware support |
Features on top of Trv32p3:
|
Trv32p3fx (variant): Trv32p3f with DSP extensions |
Features on top of Trv32p3f:
|
Trv32p3c (variant): Trv32p3 with compressed instruction support |
Features on top of/different from Trv32p3:
|
Trv32p5 (variant): 32-bit RISC-V microcontroller with 5-stage pipeline |
Features different from Trv32p3:
|
Trv32p5x (variant): Trv32p5 with DSP extensions |
Features on top of Trv32p5:
|
Trv32p5f (variant): Trv32p5 with floating-point hardware support |
Features on top of Trv32p5:
|
Trv32p5fx (variant): Trv32p5f with DSP extensions |
Features on top of Trv32p5f:
|
Trv64p3 (base model): 64-bit RISC-V microcontroller with 3-stage pipeline
|
|
Trv64p3x (variant): Trv64p3 with DSP extensions |
Features on top of Trv64p3:
|
Trv64p5 (variant): 64-bit RISC-V microcontroller with 5-stage pipeline |
Features different from Trv64p3:
|
Trv64p5x (variant): Trv64p5 with DSP extensions |
Features on top of Trv64p5:
|
Trv32p3sdx (variant): Trv32p3c with skeleton for custom data path extensions |
Features on top of Trv32p3c:
|
Back to example models overview
DLX (base model): 32-bit microcontroller (Hennessy & Patterson DLX)
|
|
FLX (variant): DLX with HW floating point unit |
Features on top of DLX base model:
|
TLX (variant): DLX with reduced register file and exposed shallower pipeline |
Features different from DLX base model:
|
ILX (variant): DLX with multi-threading support, exposed pipeline |
Features different from DLX base model:
|
PLX (variant): DLX with multi-threading support, protected pipeline |
Features different from DLX base model:
|
VLX (variant): DLX with SIMD vector extensions |
Features on top of DLX base model:
|
BLX (variant): DLX with simple branch predictor |
Features on top of DLX base model:
|
Back to example models overview
16/32-bit DSP with single MAC unit, dual load-store units with post-modify addressing, and 3-way instruction-level parallelism in 16/32-bit variable-length instructions |
|
Back to example models overview
Tvec1 (base model): Scalar microcontroller with additional SIMD vector data path |
|
Tvec2 (variant): Tvec1 with vector predication |
Features on top of Tvec1:
|
Tvec3 (variant): Tvec2 with vector-based vector addressing |
Features on top of Tvec2:
|
Tvec4 (variant): Tvec2 with scalar-based vector addressing |
Features on top of Tvec2:
|
Tvec5 (variant): Tvec4 support for multiple vector types on shared vector ALU |
Features on top of Tvec4:
|
Back to example models overview
Tvliw1 (base model): 32-bit microprocessor with 4-slot VLIW instruction level parallelism |
|
Tvliw2 (variant): Tvliw1 with variable-length instruction level parallelism |
Features on top of Tvliw1:
|
Tvliw3 (variant): Tvliw2 with additional 2-cycle program fetch pipeline |
Features on top of Tvliw2:
|
Back to example models overview
Tutorial model used in basic processor modeling hands-on laboratory |
|
Back to example models overview
Workshop model: Matrix multiplication on a RISC-V scalar core (Trv32p5x) with SIMD vector and ILP extensions. |
Features on top of/different from Trv32p5x:
|
Back to example models overview
Historic educational model used in manuals |
|
Back to example models overview
Video accelerator for motion estimation |
|
Back to example models overview
Accelerator for Gaussian image filtering |
|
Back to example models overview
SIMD vector processor for communication kernels, supporting complex-type operations |
|
Back to example models overview
Scalar accelerator for block matrix inversion |
|
Back to example models overview
Scalar FFT accelerator (minimal core optimized for FFT application kernel, without support for C built-in types or arbitrary C code) |
|
Back to example models overview
Accelerator for 5G New Radio MMSE equalization using Cholesky decomposition, with FLX processor as scalar base | Features on top of FLX:
|
Accelerator for SHA256 hashing by extension of a RISC-V scalar core |
|
Back to example models overview
Accelerator for the Kyber key encapsulation mechanism (post-quantum cryptography) by extension of a RISC-V scalar core (Trv32p5x) |
Features on top of Trv32p5x:
|
Back to example models overview
AI accelerator for MobileNet Convolutional Neural Network, with Trv32p3 RISC-V processor (RV32IM ISA) as scalar base | Features on top of Trv32p3:
|
Back to example models overview
Accelerator for medium-throughput CNN applications, based on RISC-V scalar core (Trv32p5x) | Features on top of Trv32p5x:
|
Back to example models overview