Vector Operations

Overview

The VecOps API provides efficient vector operations such as addition, subtraction, and multiplication.

Example

Vector addition

package main

import (
    "github.com/ingonyama-zk/icicle/wrappers/golang/core"
    cr "github.com/ingonyama-zk/icicle/wrappers/golang/cuda_runtime"
)

func main() {
    testSize := 1 << 12
    a := GenerateScalars(testSize)
    b := GenerateScalars(testSize)
    out := make(core.HostSlice[ScalarField], testSize)
    cfg := core.DefaultVecOpsConfig()

    // Perform vector addition
    err := VecOp(a, b, out, cfg, core.Add)
    if err != cr.CudaSuccess {
        panic("Vector addition failed")
    }
}

Vector Subtraction

package main

import (
    "github.com/ingonyama-zk/icicle/wrappers/golang/core"
    cr "github.com/ingonyama-zk/icicle/wrappers/golang/cuda_runtime"
)

func main() {
    testSize := 1 << 12
    a := GenerateScalars(testSize)
    b := GenerateScalars(testSize)
    out := make(core.HostSlice[ScalarField], testSize)
    cfg := core.DefaultVecOpsConfig()

    // Perform vector subtraction
    err := VecOp(a, b, out, cfg, core.Sub)
    if err != cr.CudaSuccess {
        panic("Vector subtraction failed")
    }
}

Vector Multiplication

package main

import (
    "github.com/ingonyama-zk/icicle/wrappers/golang/core"
    cr "github.com/ingonyama-zk/icicle/wrappers/golang/cuda_runtime"
)

func main() {
    testSize := 1 << 12
    a := GenerateScalars(testSize)
    b := GenerateScalars(testSize)
    out := make(core.HostSlice[ScalarField], testSize)
    cfg := core.DefaultVecOpsConfig()

    // Perform vector multiplication
    err := VecOp(a, b, out, cfg, core.Mul)
    if err != cr.CudaSuccess {
        panic("Vector multiplication failed")
    }
}

VecOps Method

func VecOp(a, b, out core.HostOrDeviceSlice, config core.VecOpsConfig, op core.VecOps) (ret cr.CudaError)

Parameters

• a: The first input vector.
• b: The second input vector.
• out: The output vector where the result of the operation will be stored.
• config: A VecOpsConfig object containing various configuration options for the vector operations.
• op: The operation to perform, specified as one of the constants (Sub, Add, Mul) from the VecOps type.

Return Value

• CudaError: Returns a CUDA error code indicating the success or failure of the vector operation.

VecOpsConfig

The VecOpsConfig structure holds configuration parameters for the vector operations, allowing customization of its behavior.

type VecOpsConfig struct {
    Ctx cr.DeviceContext
    isAOnDevice bool
    isBOnDevice bool
    isResultOnDevice bool
    IsResultMontgomeryForm bool
    IsAsync bool
}

Fields

• Ctx: Device context containing details like device ID and stream ID.
• isAOnDevice: Indicates if vector a is located on the device.
• isBOnDevice: Indicates if vector b is located on the device.
• isResultOnDevice: Specifies where the result vector should be stored (device or host memory).
• IsResultMontgomeryForm: Determines if the result vector should be in Montgomery form.
• IsAsync: Controls whether the vector operation runs asynchronously.

Default Configuration

Use DefaultVecOpsConfig to obtain a default configuration, customizable as needed.

func DefaultVecOpsConfig() VecOpsConfig