Nashorn development

Ah! It’s been a while since I’ve posted the last time!

But this year was quite a DE(VOXX)ED for me! First I had a chance to speak in wonderful Romania, then beautiful Vienna, after that amazing Lugano, then the loveliest Krakow, finally at the huge Antwerp event! In between I also gave some talks in my home towns Sofia –Java2Days and St. Petersburg – Joker! Let’s not forget that I was in the dreamteam of 5 to organize and run the coolest jPrime conf!

Quite an intense year!!!

So finally this weekend I had some time just to play. Of course play with coding!

As may be some of you saw, I’m really interested in the Nashorn engine to run JavaScript on JVM. I gave once some talks about it!

But not only this bothers me! For several years I’m interested in General Purpose computations on Video Cards (GPGPU)! I even gave some introductory talks on how to use GPU and Java together.

On Devoxx in English:

https://www.youtube.com/watch?v=BjdYRtL6qjg

And on Joker in Russian will be hopefully available soon 🙂

But! What will happen if actually unite these two my passions? How to run some code on the GPU but submitted from.. JavaScript!!!

You will say just use WebCL! But, isn’t it a little bit not ready yet? And as far as I know it is not exactly a full binding to OpenCL but mainly browser oriented stuff. Please correct me if I’m wrong. I’ve even played with some experimental drafts.

What if I want to utilize the full control of our computations on GPU through JS and make it very dynamic?

Yes, yes!! Nashorn is here to help us! And yes, we have the full power of the available bindings like those provided by JOCL!

So let’s do it! The usual example with vector add will be just cool enough!

That’s the JavaScript code:

print("GPU in JS!")

//some typedefs
var String = java.lang.String;
var System = java.lang.System;
var CL = org.jocl.CL;
var Pointer = org.jocl.Pointer;
var Sizeof = org.jocl.Sizeof;
var cl_command_queue = org.jocl.cl_command_queue;
var cl_context = org.jocl.cl_context;
var cl_context_properties = org.jocl.cl_context_properties;
var cl_device_id = org.jocl.cl_device_id;
var cl_kernel = org.jocl.cl_kernel;
var cl_mem = org.jocl.cl_mem;
var cl_platform_id =  org.jocl.cl_platform_id;
var cl_program = org.jocl.cl_program;
var LongArray = Java.type("long[]");
var ByteArray = Java.type("byte[]");
var FloatArray = Java.type("float[]");
var StringArray = Java.type("java.lang.String[]");
var IntArray = Java.type("int[]");
var ClPlatformIdArray = Java.type("org.jocl.cl_platform_id[]");
var ClDeviceIdArray = Java.type("org.jocl.cl_device_id[]");
var ClMemArray = Java.type("org.jocl.cl_mem[]");

//helper function
function getString(device, paramName) {
    var size = new LongArray(1);
    CL.clGetDeviceInfo(device, paramName, 0, null, size);
    var buffer = new ByteArray(size[0]);
    CL.clGetDeviceInfo(device, paramName, buffer.length, Pointer.to(buffer), null);
    return new String(buffer, 0, buffer.length-1);
}

//this goes to GPU
var programSource =
        "__kernel void "+
        "sampleKernel(__global const float *a,"+
        "             __global const float *b,"+
        "             __global float *c)"+
        "{"+
        "    int gid = get_global_id(0);"+
        "    c[gid] = a[gid] + b[gid];"+
        "}";

var start= System.currentTimeMillis();

var n = 1024;
var srcArrayA = new FloatArray(n);
var srcArrayB = new FloatArray(n);
var dstArray = new FloatArray(n);
for (var i=0; i<n; i++){
  srcArrayA[i] = i;
  srcArrayB[i] = i;
}
var srcA = Pointer.to(srcArrayA);
var srcB = Pointer.to(srcArrayB);
var dst = Pointer.to(dstArray);


var platformIndex = 0;
var deviceType = CL.CL_DEVICE_TYPE_ALL;
var deviceIndex = 2;

CL.setExceptionsEnabled(true);

var numPlatformsArray = new IntArray(1);
CL.clGetPlatformIDs(0, null, numPlatformsArray);
var numPlatforms = numPlatformsArray[0];

var platforms = new ClPlatformIdArray(numPlatforms);
CL.clGetPlatformIDs(platforms.length, platforms, null);
var platform = platforms[platformIndex];

var contextProperties = new cl_context_properties();
contextProperties.addProperty(CL.CL_CONTEXT_PLATFORM, platform);

var numDevicesArray = new IntArray(1);
CL.clGetDeviceIDs(platform, deviceType, 0, null, numDevicesArray);
var numDevices = numDevicesArray[0];

//just print out the name
var devices = new ClDeviceIdArray(numDevices);
CL.clGetDeviceIDs(platform, deviceType, numDevices, devices, null);
var device = devices[deviceIndex];

var deviceName = getString(device, CL.CL_DEVICE_NAME);
print("Device: "+deviceName);

var devices = new ClDeviceIdArray(1);
devices[0]=device;
var context = CL.clCreateContext(
  contextProperties, 1, devices,
  null, null, null);

var commandQueue =
  CL.clCreateCommandQueue(context, device, 0, null);

var memObjects = new ClMemArray(3);
memObjects[0] = CL.clCreateBuffer(context,
  CL.CL_MEM_READ_ONLY | CL.CL_MEM_COPY_HOST_PTR,
  Sizeof.cl_float * n, srcA, null);
memObjects[1] = CL.clCreateBuffer(context,
  CL.CL_MEM_READ_ONLY | CL.CL_MEM_COPY_HOST_PTR,
  Sizeof.cl_float * n, srcB, null);
memObjects[2] = CL.clCreateBuffer(context,
  CL.CL_MEM_READ_WRITE,
  Sizeof.cl_float * n, null, null);

var ps = new StringArray(1);
ps[0] = programSource;
var program = CL.clCreateProgramWithSource(context,
  1, ps, null, null);

CL.clBuildProgram(program, 0, null, null, null, null);

var kernel = CL.clCreateKernel(program, "sampleKernel", null);

CL.clSetKernelArg(kernel, 0,
  Sizeof.cl_mem, Pointer.to(memObjects[0]));
CL.clSetKernelArg(kernel, 1,
  Sizeof.cl_mem, Pointer.to(memObjects[1]));
CL.clSetKernelArg(kernel, 2,
  Sizeof.cl_mem, Pointer.to(memObjects[2]));

var global_work_size = new LongArray(1);
global_work_size[0] = n;
var local_work_size = new LongArray(1);
local_work_size[0] = 1;

// Execute the kernel
CL.clEnqueueNDRangeKernel(commandQueue, kernel, 1, null,
  global_work_size, local_work_size, 0, null, null);

CL.clEnqueueReadBuffer(commandQueue, memObjects[2], CL.CL_TRUE, 0,
  n * Sizeof.cl_float, dst, 0, null, null);

CL.clReleaseMemObject(memObjects[0]);
CL.clReleaseMemObject(memObjects[1]);
CL.clReleaseMemObject(memObjects[2]);
CL.clReleaseKernel(kernel);
CL.clReleaseProgram(program);
CL.clReleaseCommandQueue(commandQueue);
CL.clReleaseContext(context);

print("Calculated on GPU:");

for (var i=0; i<n; i++){
  print(srcArrayA[i], " + ",srcArrayB[i]," = ",dstArray[i]);
}

print("Done in: "+(System.currentTimeMillis()-start)+" ms.");

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

print("GPU in JS!")

//some typedefs

var String = java.lang.String;

var System = java.lang.System;

var CL = org.jocl.CL;

var Pointer = org.jocl.Pointer;

var Sizeof = org.jocl.Sizeof;

var cl_command_queue = org.jocl.cl_command_queue;

var cl_context = org.jocl.cl_context;

var cl_context_properties = org.jocl.cl_context_properties;

var cl_device_id = org.jocl.cl_device_id;

var cl_kernel = org.jocl.cl_kernel;

var cl_mem = org.jocl.cl_mem;

var cl_platform_id = org.jocl.cl_platform_id;

var cl_program = org.jocl.cl_program;

var LongArray = Java.type("long[]");

var ByteArray = Java.type("byte[]");

var FloatArray = Java.type("float[]");

var StringArray = Java.type("java.lang.String[]");

var IntArray = Java.type("int[]");

var ClPlatformIdArray = Java.type("org.jocl.cl_platform_id[]");

var ClDeviceIdArray = Java.type("org.jocl.cl_device_id[]");

var ClMemArray = Java.type("org.jocl.cl_mem[]");

//helper function

function getString(device, paramName) {

var size = new LongArray(1);

CL.clGetDeviceInfo(device, paramName, 0, null, size);

var buffer = new ByteArray(size[0]);

CL.clGetDeviceInfo(device, paramName, buffer.length, Pointer.to(buffer), null);

return new String(buffer, 0, buffer.length-1);

}

//this goes to GPU

var programSource =

"__kernel void "+

"sampleKernel(__global const float *a,"+

" __global const float *b,"+

" __global float *c)"+

"{"+

" int gid = get_global_id(0);"+

" c[gid] = a[gid] + b[gid];"+

"}";

var start= System.currentTimeMillis();

var n = 1024;

var srcArrayA = new FloatArray(n);

var srcArrayB = new FloatArray(n);

var dstArray = new FloatArray(n);

for (var i=0; i<n; i++){

srcArrayA[i] = i;

srcArrayB[i] = i;

}

var srcA = Pointer.to(srcArrayA);

var srcB = Pointer.to(srcArrayB);

var dst = Pointer.to(dstArray);

var platformIndex = 0;

var deviceType = CL.CL_DEVICE_TYPE_ALL;

var deviceIndex = 2;

CL.setExceptionsEnabled(true);

var numPlatformsArray = new IntArray(1);

CL.clGetPlatformIDs(0, null, numPlatformsArray);

var numPlatforms = numPlatformsArray[0];

var platforms = new ClPlatformIdArray(numPlatforms);

CL.clGetPlatformIDs(platforms.length, platforms, null);

var platform = platforms[platformIndex];

var contextProperties = new cl_context_properties();

contextProperties.addProperty(CL.CL_CONTEXT_PLATFORM, platform);

var numDevicesArray = new IntArray(1);

CL.clGetDeviceIDs(platform, deviceType, 0, null, numDevicesArray);

var numDevices = numDevicesArray[0];

//just print out the name

var devices = new ClDeviceIdArray(numDevices);

CL.clGetDeviceIDs(platform, deviceType, numDevices, devices, null);

var device = devices[deviceIndex];

var deviceName = getString(device, CL.CL_DEVICE_NAME);

print("Device: "+deviceName);

var devices = new ClDeviceIdArray(1);

devices[0]=device;

var context = CL.clCreateContext(

contextProperties, 1, devices,

null, null, null);

var commandQueue =

CL.clCreateCommandQueue(context, device, 0, null);

var memObjects = new ClMemArray(3);

memObjects[0] = CL.clCreateBuffer(context,

CL.CL_MEM_READ_ONLY | CL.CL_MEM_COPY_HOST_PTR,

Sizeof.cl_float * n, srcA, null);

memObjects[1] = CL.clCreateBuffer(context,

CL.CL_MEM_READ_ONLY | CL.CL_MEM_COPY_HOST_PTR,

Sizeof.cl_float * n, srcB, null);

memObjects[2] = CL.clCreateBuffer(context,

CL.CL_MEM_READ_WRITE,

Sizeof.cl_float * n, null, null);

var ps = new StringArray(1);

ps[0] = programSource;

var program = CL.clCreateProgramWithSource(context,

1, ps, null, null);

CL.clBuildProgram(program, 0, null, null, null, null);

var kernel = CL.clCreateKernel(program, "sampleKernel", null);

CL.clSetKernelArg(kernel, 0,

Sizeof.cl_mem, Pointer.to(memObjects[0]));

CL.clSetKernelArg(kernel, 1,

Sizeof.cl_mem, Pointer.to(memObjects[1]));

CL.clSetKernelArg(kernel, 2,

Sizeof.cl_mem, Pointer.to(memObjects[2]));

var global_work_size = new LongArray(1);

global_work_size[0] = n;

var local_work_size = new LongArray(1);

local_work_size[0] = 1;

// Execute the kernel

CL.clEnqueueNDRangeKernel(commandQueue, kernel, 1, null,

global_work_size, local_work_size, 0, null, null);

CL.clEnqueueReadBuffer(commandQueue, memObjects[2], CL.CL_TRUE, 0,

n * Sizeof.cl_float, dst, 0, null, null);

CL.clReleaseMemObject(memObjects[0]);

CL.clReleaseMemObject(memObjects[1]);

CL.clReleaseMemObject(memObjects[2]);

CL.clReleaseKernel(kernel);

CL.clReleaseProgram(program);

CL.clReleaseCommandQueue(commandQueue);

CL.clReleaseContext(context);

print("Calculated on GPU:");

for (var i=0; i<n; i++){

print(srcArrayA[i], " + ",srcArrayB[i]," = ",dstArray[i]);

}

print("Done in: "+(System.currentTimeMillis()-start)+" ms.");

I just put it all in jscl.js file.

As you in the beginning I’ve added some type definition shortcuts just to make code look more readable.

To run it in the console I just put:

jjs -cp ./lib/JOCL-0.1.9.jar -scripting jscl.js

1	jjs -cp ./lib/JOCL-0.1.9.jar -scripting jscl.js

JJS is available by default if you have minimum Java 8 installed.

The JOCL jar you can just get from their site.

And what we have (on my Mac):

GPU in JS!
Device: GeForce GT 650M
Calculated on GPU:
0 + 0 = 0
1 + 1 = 2
2 + 2 = 4
....
1019 + 1019 = 2038
1020 + 1020 = 2040
1021 + 1021 = 2042
1022 + 1022 = 2044
1023 + 1023 = 2046
Done in: 704 ms.

GPU in JS!

Device: GeForce GT 650M

Calculated on GPU:

0 + 0 = 0

1 + 1 = 2

2 + 2 = 4

....

1019 + 1019 = 2038

1020 + 1020 = 2040

1021 + 1021 = 2042

1022 + 1022 = 2044

1023 + 1023 = 2046

Done in: 704 ms.

Isn’t this lovely!!

Funny fact that is that because of the memory latency it about 700 ms no matter if I make 1k computations or 100m of them 🙂

Still, this may be good example of how Java/JVM can be a kind of a technology glue. Having in mind that there are more than 40 languages running on JVM, all of them can benefit from the de facto standard libraries already available for Java.

This is so much cool!! Have Fun!