Function srotm

Applies a modified Givens plane rotation H to vectors x and y: x = H[0][0]*x + H[0][1]*y y = H[1][0]*x + H[1][1]*y

import { init, cleanup } from "wgblas";
import { srotm } from "wgblas/srotm";
import { randomFloat32Array } from "wgblas/random";

const device = await init();

const n = 10;
const x = randomFloat32Array(n, -10, 10);
const y = randomFloat32Array(n, -10, 10);

// flag = -1: full 2x2 matrix H
// H = [ h11  h12 ]  =  [ 0.6  0.8 ]
//     [ h21  h22 ]     [-0.8  0.6 ]
const param = new Float32Array([-1, 0.6, -0.8, 0.8, 0.6]);

console.log("x (before):", x);
console.log("y (before):", y);

const { x: xOut, y: yOut } = await srotm(device, n, x, 1, y, 1, param);

console.log("x (after): ", xOut);
console.log("y (after): ", yOut);

if (typeof process !== "undefined") cleanup();
Copy

Applies a modified Givens plane rotation H to vectors x and y: x = H[0][0]*x + H[0][1]*y y = H[1][0]*x + H[1][1]*y

import { init, cleanup } from "wgblas";
import { srotm } from "wgblas/srotm";
import { saxpy } from "wgblas/saxpy";
import { GpuVector } from "wgblas/classes/GpuVector";
import { randomFloat32Array } from "wgblas/random";

const device = await init();

const n = 10;
const xCpu = randomFloat32Array(n, -10, 10);
const yCpu = randomFloat32Array(n, -10, 10);

const xGpu = GpuVector.from(xCpu);
const yGpu = GpuVector.from(yCpu);

console.log("x (cpu):   ", xCpu);
console.log("y (cpu):   ", yCpu);

// flag = 0: unit diagonal — H = [ 1    h12 ]
//                                [ h21   1  ]
const param = new Float32Array([0, 1, -0.5, 0.5, 1]);

// shift y by adding 2*x on GPU, then apply modified rotation
await saxpy(device, n, 2.0, xGpu, 1, yGpu, 1);
await srotm(device, n, xGpu, 1, yGpu, 1, param);

console.log("x (after): ", await xGpu.read());
console.log("y (after): ", await yGpu.read());

xGpu.destroy();
yGpu.destroy();

if (typeof process !== "undefined") cleanup();
Copy