Moving benchmarks implementations to common
This commit is contained in:
Roland Grinis
parent
274d1a3105
commit
d599d1132b
@ -0,0 +1,24 @@
|
||||
@file:Suppress("NOTHING_TO_INLINE")
|
||||
|
||||
package kscience.kmath.torch
|
||||
|
||||
import kotlin.time.measureTime
|
||||
|
||||
internal inline fun <T, PrimitiveArrayType, TorchTensorType : TorchTensorOverField<T>,
|
||||
TorchTensorAlgebraType : TorchTensorPartialDivisionAlgebra<T, PrimitiveArrayType, TorchTensorType>>
|
||||
TorchTensorAlgebraType.benchmarkMatMul(
|
||||
scale: Int,
|
||||
numWarmUp: Int,
|
||||
numIter: Int,
|
||||
fieldName: String,
|
||||
device: Device = Device.CPU
|
||||
): Unit {
|
||||
println("Benchmarking $scale x $scale $fieldName matrices on $device: ")
|
||||
setSeed(SEED)
|
||||
val lhs = randNormal(shape = intArrayOf(scale, scale), device = device)
|
||||
val rhs = randNormal(shape = intArrayOf(scale, scale), device = device)
|
||||
repeat(numWarmUp) { lhs dotAssign rhs }
|
||||
val measuredTime = measureTime { repeat(numIter) { lhs dotAssign rhs } }
|
||||
println(" ${measuredTime / numIter} p.o. with $numIter iterations")
|
||||
}
|
||||
|
||||
@ -0,0 +1,132 @@
|
||||
@file:Suppress("NOTHING_TO_INLINE")
|
||||
|
||||
package kscience.kmath.torch
|
||||
|
||||
import kotlin.time.measureTime
|
||||
|
||||
internal inline fun <TorchTensorType : TorchTensorOverField<Float>,
|
||||
TorchTensorAlgebraType : TorchTensorPartialDivisionAlgebra<Float, FloatArray, TorchTensorType>>
|
||||
TorchTensorAlgebraType.benchmarkRand(
|
||||
samples: Int,
|
||||
numWarmUp: Int,
|
||||
numIter: Int,
|
||||
device: Device,
|
||||
distName: String,
|
||||
initBock: TorchTensorAlgebraType.(IntArray, Device) -> TorchTensorType,
|
||||
runBlock: TorchTensorAlgebraType.(TorchTensorType) -> Unit
|
||||
): Unit{
|
||||
println("Benchmarking generation of $samples $distName samples on $device: ")
|
||||
setSeed(SEED)
|
||||
val shape = intArrayOf(samples)
|
||||
val tensor = this.initBock(shape,device)
|
||||
repeat(numWarmUp) { this.runBlock(tensor) }
|
||||
val measuredTime = measureTime { repeat(numIter) { this.runBlock(tensor) } }
|
||||
println(" ${measuredTime / numIter} p.o. with $numIter iterations")
|
||||
}
|
||||
|
||||
internal inline fun <TorchTensorType : TorchTensorOverField<Float>,
|
||||
TorchTensorAlgebraType : TorchTensorPartialDivisionAlgebra<Float, FloatArray, TorchTensorType>>
|
||||
TorchTensorAlgebraType.benchmarkRandNormal(
|
||||
samples: Int,
|
||||
numWarmUp: Int,
|
||||
numIter: Int,
|
||||
device: Device = Device.CPU): Unit{
|
||||
benchmarkRand(
|
||||
samples,
|
||||
numWarmUp,
|
||||
numIter,
|
||||
device,
|
||||
"Normal",
|
||||
{sh, dc -> randNormal(shape = sh, device = dc)},
|
||||
{ten -> ten.randNormalAssign() }
|
||||
)
|
||||
}
|
||||
|
||||
internal inline fun <TorchTensorType : TorchTensorOverField<Float>,
|
||||
TorchTensorAlgebraType : TorchTensorPartialDivisionAlgebra<Float, FloatArray, TorchTensorType>>
|
||||
TorchTensorAlgebraType.benchmarkRandUniform(
|
||||
samples: Int,
|
||||
numWarmUp: Int,
|
||||
numIter: Int,
|
||||
device: Device = Device.CPU): Unit{
|
||||
benchmarkRand(
|
||||
samples,
|
||||
numWarmUp,
|
||||
numIter,
|
||||
device,
|
||||
"Uniform",
|
||||
{sh, dc -> randUniform(shape = sh, device = dc)},
|
||||
{ten -> ten.randUniformAssign() }
|
||||
)
|
||||
}
|
||||
|
||||
internal inline fun <TorchTensorType : TorchTensorOverField<Float>,
|
||||
TorchTensorAlgebraType : TorchTensorPartialDivisionAlgebra<Float, FloatArray, TorchTensorType>>
|
||||
TorchTensorAlgebraType.benchmarkRandIntegral(
|
||||
samples: Int,
|
||||
numWarmUp: Int,
|
||||
numIter: Int,
|
||||
device: Device = Device.CPU): Unit{
|
||||
benchmarkRand(
|
||||
samples,
|
||||
numWarmUp,
|
||||
numIter,
|
||||
device,
|
||||
"integer [0,100]",
|
||||
{sh, dc -> randIntegral(0f, 100f, shape = sh, device = dc)},
|
||||
{ten -> ten.randIntegralAssign(0f, 100f) }
|
||||
)
|
||||
}
|
||||
|
||||
internal inline fun <TorchTensorType : TorchTensorOverField<Float>,
|
||||
TorchTensorAlgebraType : TorchTensorPartialDivisionAlgebra<Float, FloatArray, TorchTensorType>>
|
||||
TorchTensorAlgebraType.benchmarkingRand1(): Unit {
|
||||
benchmarkRandNormal(10, 10, 100000)
|
||||
benchmarkRandUniform(10, 10, 100000)
|
||||
benchmarkRandIntegral(10, 10, 100000)
|
||||
if(cudaAvailable()) {
|
||||
benchmarkRandNormal(10, 10, 100000, device = Device.CUDA(0))
|
||||
benchmarkRandUniform(10, 10, 100000, device = Device.CUDA(0))
|
||||
benchmarkRandIntegral(10, 10, 100000, device = Device.CUDA(0))
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
internal inline fun <TorchTensorType : TorchTensorOverField<Float>,
|
||||
TorchTensorAlgebraType : TorchTensorPartialDivisionAlgebra<Float, FloatArray, TorchTensorType>>
|
||||
TorchTensorAlgebraType.benchmarkingRand3(): Unit {
|
||||
benchmarkRandNormal(1000, 10, 10000)
|
||||
benchmarkRandUniform(1000, 10, 10000)
|
||||
benchmarkRandIntegral(1000, 10, 10000)
|
||||
if(cudaAvailable()) {
|
||||
benchmarkRandNormal(1000, 10, 100000, device = Device.CUDA(0))
|
||||
benchmarkRandUniform(1000, 10, 100000, device = Device.CUDA(0))
|
||||
benchmarkRandIntegral(1000, 10, 100000, device = Device.CUDA(0))
|
||||
}
|
||||
}
|
||||
|
||||
internal inline fun <TorchTensorType : TorchTensorOverField<Float>,
|
||||
TorchTensorAlgebraType : TorchTensorPartialDivisionAlgebra<Float, FloatArray, TorchTensorType>>
|
||||
TorchTensorAlgebraType.benchmarkingRand5(): Unit {
|
||||
benchmarkRandNormal(100000, 5, 100)
|
||||
benchmarkRandUniform(100000, 5, 100)
|
||||
benchmarkRandIntegral(100000, 5, 100)
|
||||
if(cudaAvailable()){
|
||||
benchmarkRandNormal(100000, 10, 100000, device = Device.CUDA(0))
|
||||
benchmarkRandUniform(100000, 10, 100000, device = Device.CUDA(0))
|
||||
benchmarkRandIntegral(100000, 10, 100000, device = Device.CUDA(0))
|
||||
}
|
||||
}
|
||||
|
||||
internal inline fun <TorchTensorType : TorchTensorOverField<Float>,
|
||||
TorchTensorAlgebraType : TorchTensorPartialDivisionAlgebra<Float, FloatArray, TorchTensorType>>
|
||||
TorchTensorAlgebraType.benchmarkingRand7(): Unit {
|
||||
benchmarkRandNormal(10000000, 3, 20)
|
||||
benchmarkRandUniform(10000000, 3, 20)
|
||||
benchmarkRandIntegral(10000000, 3, 20)
|
||||
if(cudaAvailable()){
|
||||
benchmarkRandNormal(10000000, 10, 10000, device = Device.CUDA(0))
|
||||
benchmarkRandUniform(10000000, 10, 10000, device = Device.CUDA(0))
|
||||
benchmarkRandIntegral(10000000, 10, 10000, device = Device.CUDA(0))
|
||||
}
|
||||
}
|
||||
@ -1,20 +0,0 @@
|
||||
package kscience.kmath.torch
|
||||
|
||||
import kotlin.test.Test
|
||||
|
||||
class BenchmarkMatMultGPU {
|
||||
@Test
|
||||
fun benchmarkMatMultFloat20() =
|
||||
benchmarkingMatMultFloat(20, 10, 100000,
|
||||
device = Device.CUDA(0))
|
||||
|
||||
@Test
|
||||
fun benchmarkMatMultFloat200() =
|
||||
benchmarkingMatMultFloat(200, 10, 10000,
|
||||
device = Device.CUDA(0))
|
||||
|
||||
@Test
|
||||
fun benchmarkMatMultFloat2000() =
|
||||
benchmarkingMatMultFloat(2000, 10, 1000,
|
||||
device = Device.CUDA(0))
|
||||
}
|
||||
@ -1,64 +0,0 @@
|
||||
package kscience.kmath.torch
|
||||
|
||||
import kotlin.test.Test
|
||||
|
||||
class BenchmarkRandomGeneratorsGPU {
|
||||
@Test
|
||||
fun benchmarkRandNormal1() =
|
||||
benchmarkingRandNormal(10, 10, 100000,
|
||||
device = Device.CUDA(0))
|
||||
@Test
|
||||
fun benchmarkRandUniform1() =
|
||||
benchmarkingRandUniform(10, 10, 100000,
|
||||
device = Device.CUDA(0))
|
||||
|
||||
@Test
|
||||
fun benchmarkRandIntegral1() =
|
||||
benchmarkingRandIntegral(10, 10, 100000,
|
||||
device = Device.CUDA(0))
|
||||
|
||||
@Test
|
||||
fun benchmarkRandNormal3() =
|
||||
benchmarkingRandNormal(1000, 10, 100000,
|
||||
device = Device.CUDA(0))
|
||||
|
||||
@Test
|
||||
fun benchmarkRandUniform3() =
|
||||
benchmarkingRandUniform(1000, 10, 100000,
|
||||
device = Device.CUDA(0))
|
||||
|
||||
@Test
|
||||
fun benchmarkRandIntegral3() =
|
||||
benchmarkingRandIntegral(1000, 10, 100000,
|
||||
device = Device.CUDA(0))
|
||||
|
||||
@Test
|
||||
fun benchmarkRandNormal5() =
|
||||
benchmarkingRandNormal(100000, 10, 100000,
|
||||
device = Device.CUDA(0))
|
||||
|
||||
@Test
|
||||
fun benchmarkRandUniform5() =
|
||||
benchmarkingRandUniform(100000, 10, 100000,
|
||||
device = Device.CUDA(0))
|
||||
|
||||
@Test
|
||||
fun benchmarkRandIntegral5() =
|
||||
benchmarkingRandIntegral(100000, 10, 100000,
|
||||
device = Device.CUDA(0))
|
||||
|
||||
@Test
|
||||
fun benchmarkRandNormal7() =
|
||||
benchmarkingRandNormal(10000000, 10, 10000,
|
||||
device = Device.CUDA(0))
|
||||
|
||||
@Test
|
||||
fun benchmarkRandUniform7() =
|
||||
benchmarkingRandUniform(10000000, 10, 10000,
|
||||
device = Device.CUDA(0))
|
||||
|
||||
@Test
|
||||
fun benchmarkRandIntegral7() =
|
||||
benchmarkingRandIntegral(10000000, 10, 10000,
|
||||
device = Device.CUDA(0))
|
||||
}
|
||||
@ -0,0 +1,27 @@
|
||||
package kscience.kmath.torch
|
||||
|
||||
import kotlin.test.Test
|
||||
|
||||
internal class BenchmarkMatMul {
|
||||
|
||||
@Test
|
||||
fun benchmarkMatMulDouble() = TorchTensorRealAlgebra {
|
||||
benchmarkMatMul(20, 10, 100000, "Real")
|
||||
benchmarkMatMul(200, 10, 10000, "Real")
|
||||
benchmarkMatMul(2000, 3, 20, "Real")
|
||||
}
|
||||
|
||||
@Test
|
||||
fun benchmarkMatMulFloat() = TorchTensorFloatAlgebra {
|
||||
benchmarkMatMul(20, 10, 100000, "Float")
|
||||
benchmarkMatMul(200, 10, 10000, "Float")
|
||||
benchmarkMatMul(2000, 3, 20, "Float")
|
||||
if (cudaAvailable()) {
|
||||
benchmarkMatMul(20, 10, 100000, "Float", Device.CUDA(0))
|
||||
benchmarkMatMul(200, 10, 10000, "Float", Device.CUDA(0))
|
||||
benchmarkMatMul(2000, 10, 1000, "Float", Device.CUDA(0))
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
@ -1,66 +0,0 @@
|
||||
package kscience.kmath.torch
|
||||
|
||||
import kotlin.test.Test
|
||||
import kotlin.time.measureTime
|
||||
|
||||
internal fun benchmarkingMatMultDouble(
|
||||
scale: Int,
|
||||
numWarmUp: Int,
|
||||
numIter: Int,
|
||||
device: Device = Device.CPU
|
||||
): Unit {
|
||||
TorchTensorRealAlgebra {
|
||||
println("Benchmarking $scale x $scale matrices over Double's on $device: ")
|
||||
setSeed(SEED)
|
||||
val lhs = randNormal(shape = intArrayOf(scale, scale), device = device)
|
||||
val rhs = randNormal(shape = intArrayOf(scale, scale), device = device)
|
||||
repeat(numWarmUp) { lhs dotAssign rhs }
|
||||
val measuredTime = measureTime { repeat(numIter) { lhs dotAssign rhs } }
|
||||
println(" ${measuredTime / numIter} p.o. with $numIter iterations")
|
||||
}
|
||||
}
|
||||
|
||||
internal fun benchmarkingMatMultFloat(
|
||||
scale: Int,
|
||||
numWarmUp: Int,
|
||||
numIter: Int,
|
||||
device: Device = Device.CPU
|
||||
): Unit {
|
||||
TorchTensorFloatAlgebra {
|
||||
println("Benchmarking $scale x $scale matrices over Float's on $device: ")
|
||||
setSeed(SEED)
|
||||
val lhs = randNormal(shape = intArrayOf(scale, scale), device = device)
|
||||
val rhs = randNormal(shape = intArrayOf(scale, scale), device = device)
|
||||
repeat(numWarmUp) { lhs dotAssign rhs }
|
||||
val measuredTime = measureTime { repeat(numIter) { lhs dotAssign rhs } }
|
||||
println(" ${measuredTime / numIter} p.o. with $numIter iterations")
|
||||
}
|
||||
}
|
||||
|
||||
internal class BenchmarkMatMult {
|
||||
|
||||
@Test
|
||||
fun benchmarkMatMultDouble20() =
|
||||
benchmarkingMatMultDouble(20, 10, 100000)
|
||||
|
||||
@Test
|
||||
fun benchmarkMatMultFloat20() =
|
||||
benchmarkingMatMultFloat(20, 10, 100000)
|
||||
|
||||
@Test
|
||||
fun benchmarkMatMultDouble200() =
|
||||
benchmarkingMatMultDouble(200, 10, 10000)
|
||||
|
||||
@Test
|
||||
fun benchmarkMatMultFloat200() =
|
||||
benchmarkingMatMultFloat(200, 10, 10000)
|
||||
|
||||
@Test
|
||||
fun benchmarkMatMultDouble2000() =
|
||||
benchmarkingMatMultDouble(2000, 3, 20)
|
||||
|
||||
@Test
|
||||
fun benchmarkMatMultFloat2000() =
|
||||
benchmarkingMatMultFloat(2000, 3, 20)
|
||||
|
||||
}
|
||||
@ -1,107 +1,28 @@
|
||||
package kscience.kmath.torch
|
||||
|
||||
import kotlin.test.Test
|
||||
import kotlin.time.measureTime
|
||||
|
||||
internal fun benchmarkingRandNormal(
|
||||
samples: Int,
|
||||
numWarmUp: Int,
|
||||
numIter: Int,
|
||||
device: Device = Device.CPU): Unit
|
||||
{
|
||||
TorchTensorFloatAlgebra{
|
||||
println("Benchmarking generation of $samples Normal samples on $device: ")
|
||||
setSeed(SEED)
|
||||
val shape = intArrayOf(samples)
|
||||
val tensor = randNormal(shape = shape, device = device)
|
||||
repeat(numWarmUp) { tensor.randNormalAssign() }
|
||||
val measuredTime = measureTime { repeat(numIter) { tensor.randNormalAssign() } }
|
||||
println(" ${measuredTime / numIter} p.o. with $numIter iterations")
|
||||
}
|
||||
}
|
||||
internal fun benchmarkingRandUniform(
|
||||
samples: Int,
|
||||
numWarmUp: Int,
|
||||
numIter: Int,
|
||||
device: Device = Device.CPU): Unit
|
||||
{
|
||||
TorchTensorFloatAlgebra{
|
||||
println("Benchmarking generation of $samples Uniform samples on $device: ")
|
||||
setSeed(SEED)
|
||||
val shape = intArrayOf(samples)
|
||||
val tensor = randUniform(shape = shape, device = device)
|
||||
repeat(numWarmUp) { tensor.randUniformAssign() }
|
||||
val measuredTime = measureTime { repeat(numIter) { tensor.randUniformAssign() } }
|
||||
println(" ${measuredTime / numIter} p.o. with $numIter iterations")
|
||||
}
|
||||
}
|
||||
|
||||
internal fun benchmarkingRandIntegral(
|
||||
samples: Int,
|
||||
numWarmUp: Int,
|
||||
numIter: Int,
|
||||
device: Device = Device.CPU): Unit
|
||||
{
|
||||
TorchTensorIntAlgebra {
|
||||
println("Benchmarking generation of $samples integer [0,100] samples on $device: ")
|
||||
setSeed(SEED)
|
||||
val shape = intArrayOf(samples)
|
||||
val tensor = randIntegral(0,100, shape = shape, device = device)
|
||||
repeat(numWarmUp) { tensor.randIntegralAssign(0,100) }
|
||||
val measuredTime = measureTime { repeat(numIter) { tensor.randIntegralAssign(0,100) } }
|
||||
println(" ${measuredTime / numIter} p.o. with $numIter iterations")
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
internal class BenchmarkRandomGenerators {
|
||||
|
||||
@Test
|
||||
fun benchmarkRandNormal1() =
|
||||
benchmarkingRandNormal(10, 10, 100000)
|
||||
fun benchmarkRand1() = TorchTensorFloatAlgebra{
|
||||
benchmarkingRand1()
|
||||
}
|
||||
|
||||
@Test
|
||||
fun benchmarkRandUniform1() =
|
||||
benchmarkingRandUniform(10, 10, 100000)
|
||||
fun benchmarkRand3() = TorchTensorFloatAlgebra{
|
||||
benchmarkingRand3()
|
||||
}
|
||||
|
||||
@Test
|
||||
fun benchmarkRandIntegral1() =
|
||||
benchmarkingRandIntegral(10, 10, 100000)
|
||||
fun benchmarkRand5() = TorchTensorFloatAlgebra{
|
||||
benchmarkingRand5()
|
||||
}
|
||||
|
||||
@Test
|
||||
fun benchmarkRandNormal3() =
|
||||
benchmarkingRandNormal(1000, 10, 10000)
|
||||
|
||||
@Test
|
||||
fun benchmarkRandUniform3() =
|
||||
benchmarkingRandUniform(1000, 10, 10000)
|
||||
|
||||
@Test
|
||||
fun benchmarkRandIntegral3() =
|
||||
benchmarkingRandIntegral(1000, 10, 10000)
|
||||
|
||||
@Test
|
||||
fun benchmarkRandNormal5() =
|
||||
benchmarkingRandNormal(100000, 5, 100)
|
||||
|
||||
@Test
|
||||
fun benchmarkRandUniform5() =
|
||||
benchmarkingRandUniform(100000, 5, 100)
|
||||
|
||||
@Test
|
||||
fun benchmarkRandIntegral5() =
|
||||
benchmarkingRandIntegral(100000, 5, 100)
|
||||
|
||||
@Test
|
||||
fun benchmarkRandNormal7() =
|
||||
benchmarkingRandNormal(10000000, 3, 20)
|
||||
|
||||
@Test
|
||||
fun benchmarkRandUniform7() =
|
||||
benchmarkingRandUniform(10000000, 3, 20)
|
||||
|
||||
@Test
|
||||
fun benchmarkRandIntegral7() =
|
||||
benchmarkingRandIntegral(10000000, 3, 20)
|
||||
fun benchmarkRand7() = TorchTensorFloatAlgebra{
|
||||
benchmarkingRand7()
|
||||
}
|
||||
|
||||
}
|
||||
Loading…
Reference in New Issue
Block a user