Skip to content

Adds tests for the new Morton Code class #187

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 13 commits into
base: master
Choose a base branch
from
Open

Adds tests for the new Morton Code class #187

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
f2ea51d
Morton code tests
Fletterio Mar 23, 2025
8f4e452
Morton codes creating properly
Fletterio Mar 25, 2025
0aedfd9
All tests passing, HLSL compiles fine!
Fletterio Mar 28, 2025
ea42d5b
Rename example
Fletterio Apr 1, 2025
2ba08a4
Add tests for AddCarry and SUbBorrow intrinsics
Fletterio Apr 1, 2025
f00bbf6
Disable intrinsic tests for uSUbBorrow for the time being, start copy…
Fletterio Apr 7, 2025
b2d87c3
Added extensive tests for Morton codes
Fletterio Apr 24, 2025
c68c336
Done with tests
Fletterio Apr 28, 2025
d906bb2
Merged master
Fletterio Apr 28, 2025
f05dec4
Clarifying comment for blocker issue
Fletterio Apr 28, 2025
b13fdc7
Merge branch 'master' into mortons
Nov 19, 2025
08c898d
Reindex mortons example from 12 to 73
Nov 27, 2025
7f8dd73
Global variable of hlsl to use NBL_CONSTEXPR_INLINE_NSPC_SCOPE_VAR
Nov 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
0 XX_Mortons/CMakeLists.txt → 12_Mortons/CMakeLists.txt
View file
Open in desktop
File renamed without changes.
13 changes: 13 additions & 0 deletions 12_Mortons/app_resources/common.hlsl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
//#include "nbl/builtin/hlsl/morton.hlsl"
#include "nbl/builtin/hlsl/cpp_compat.hlsl"

NBL_CONSTEXPR uint32_t bufferSize = 256;

// Proper coverage would require writing tests for ALL possible sign, dimensions and width configurations
//using morton_t2 = nbl::hlsl::morton::code<true, 8, 2>; // Fits in an int16_t
using vector_t2 = nbl::hlsl::vector<int16_t, 3>;

struct PushConstantData
{
uint64_t deviceBufferAddress;
};
8 changes: 5 additions & 3 deletions XX_Mortons/app_resources/shader.hlsl → 12_Mortons/app_resources/shader.hlsl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,14 +3,16 @@

[[vk::push_constant]] PushConstantData pushConstants;

using namespace nbl::hlsl;

[numthreads(bufferSize, 1, 1)]
void main(uint32_t3 ID : SV_DispatchThreadID)
{
/*
LegacyBdaAccessor<unsigned_scalar_t> accessor = LegacyBdaAccessor<unsigned_scalar_t>::create(pushConstants.deviceBufferAddress);

morton::code<int32_t, 2> foo = morton::code<int32_t, 2>::create(vector<int32_t, 2>(-32768, -1));

accessor.set(0, foo.value);
//accessor.set(0, foo.value);
*/
uint32_t bar = _static_cast<uint32_t>(0xCAFEDEADDEADBEEF);
accessor.set(0, bar);
}
0 XX_Mortons/config.json.template → 12_Mortons/config.json.template
View file
Open in desktop
File renamed without changes.
21 changes: 9 additions & 12 deletions XX_Mortons/main.cpp → 12_Mortons/main.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,12 +25,6 @@ class MortonTestApp final : public application_templates::MonoDeviceApplication,
using device_base_t = application_templates::MonoDeviceApplication;
using asset_base_t = application_templates::MonoAssetManagerAndBuiltinResourceApplication;

using morton_t = nbl::hlsl::morton::code<int32_t, 3>;
using vector_t = nbl::hlsl::vector<int32_t, 3>;
using unsigned_morton_t = nbl::hlsl::morton::code<uint32_t, 3>;
using unsigned_vector_t = nbl::hlsl::vector<uint32_t, 3>;
using bool_vector_t = nbl::hlsl::vector<bool, 3>;

inline core::smart_refctd_ptr<video::IGPUShader> createShader(
const char* includeMainName)
{
Expand All @@ -52,6 +46,8 @@ class MortonTestApp final : public application_templates::MonoDeviceApplication,
if (!asset_base_t::onAppInitialized(std::move(system)))
return false;

/*

// ----------------------------------------------- CPP TESTS ----------------------------------------------------------------------

// Coordinate extraction and whole vector decode tests
Expand Down Expand Up @@ -201,7 +197,7 @@ class MortonTestApp final : public application_templates::MonoDeviceApplication,
if(!TestHLSL)
return true;


*/



Expand All @@ -213,7 +209,7 @@ class MortonTestApp final : public application_templates::MonoDeviceApplication,
auto shader = createShader("app_resources/shader.hlsl");

// Create massive upload/download buffers
constexpr uint32_t DownstreamBufferSize = sizeof(unsigned_scalar_t) << 23;
constexpr uint32_t DownstreamBufferSize = sizeof(uint32_t) << 23;

m_utils = make_smart_refctd_ptr<IUtilities>(smart_refctd_ptr(m_device), smart_refctd_ptr(m_logger), DownstreamBufferSize);
if (!m_utils)
Expand All @@ -230,7 +226,7 @@ class MortonTestApp final : public application_templates::MonoDeviceApplication,

deviceLocalBufferParams.queueFamilyIndexCount = 1;
deviceLocalBufferParams.queueFamilyIndices = &queueFamilyIndex;
deviceLocalBufferParams.size = sizeof(unsigned_scalar_t) * bufferSize;
deviceLocalBufferParams.size = sizeof(uint32_t) * bufferSize;
deviceLocalBufferParams.usage = nbl::asset::IBuffer::E_USAGE_FLAGS::EUF_TRANSFER_SRC_BIT | nbl::asset::IBuffer::E_USAGE_FLAGS::EUF_TRANSFER_DST_BIT | nbl::asset::IBuffer::E_USAGE_FLAGS::EUF_SHADER_DEVICE_ADDRESS_BIT;

m_deviceLocalBuffer = m_device->createBuffer(std::move(deviceLocalBufferParams));
Expand Down Expand Up @@ -268,7 +264,7 @@ class MortonTestApp final : public application_templates::MonoDeviceApplication,

IQueue* const queue = getComputeQueue();

const uint32_t inputSize = sizeof(unsigned_scalar_t) * bufferSize;
const uint32_t inputSize = sizeof(uint32_t) * bufferSize;

// Just need a single suballocation in this example
const uint32_t AllocationCount = 1;
Expand Down Expand Up @@ -361,8 +357,9 @@ class MortonTestApp final : public application_templates::MonoDeviceApplication,
assert(dstOffset == 0 && size == outputSize);

std::cout << "Begin array GPU\n";
unsigned_scalar_t* const data = reinterpret_cast<unsigned_scalar_t*>(const_cast<void*>(bufSrc));
std::cout << std::bitset<32>(data[0]) << "\n";
uint32_t* const data = reinterpret_cast<uint32_t*>(const_cast<void*>(bufSrc));
//std::cout << std::bitset<32>(data[0]) << "\n";
std::cout << data[0] << "\n";
/*
for (auto i = 0u; i < bufferSize; i++) {
std::cout << std::bitset<32>(data[i]) << "\n";
Expand Down
0 XX_Mortons/pipeline.groovy → 12_Mortons/pipeline.groovy
View file
Open in desktop
File renamed without changes.
13 changes: 13 additions & 0 deletions 22_CppCompat/CIntrinsicsTester.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,6 +85,10 @@ class CIntrinsicsTester final : public ITester
testInput.smoothStepEdge0 = realDistributionNeg(mt);
testInput.smoothStepEdge1 = realDistributionPos(mt);
testInput.smoothStepX = realDistribution(mt);
testInput.addCarryA = std::numeric_limits<uint32_t>::max() - uintDistribution(mt);
testInput.addCarryB = uintDistribution(mt);
testInput.subBorrowA = uintDistribution(mt);
testInput.subBorrowB = uintDistribution(mt);

testInput.bitCountVec = int32_t3(intDistribution(mt), intDistribution(mt), intDistribution(mt));
testInput.clampValVec = float32_t3(realDistribution(mt), realDistribution(mt), realDistribution(mt));
Expand Down Expand Up @@ -119,6 +123,10 @@ class CIntrinsicsTester final : public ITester
testInput.refractI = float32_t3(realDistribution(mt), realDistribution(mt), realDistribution(mt));
testInput.refractN = glm::normalize(float32_t3(realDistribution(mt), realDistribution(mt), realDistribution(mt)));
testInput.refractEta = realDistribution(mt);
testInput.addCarryAVec = uint32_t3(std::numeric_limits<uint32_t>::max() - uintDistribution(mt), std::numeric_limits<uint32_t>::max() - uintDistribution(mt), std::numeric_limits<uint32_t>::max() - uintDistribution(mt));
testInput.addCarryBVec = uint32_t3(uintDistribution(mt), uintDistribution(mt), uintDistribution(mt));
testInput.subBorrowAVec = uint32_t3(uintDistribution(mt), uintDistribution(mt), uintDistribution(mt));
testInput.subBorrowBVec = uint32_t3(uintDistribution(mt), uintDistribution(mt), uintDistribution(mt));

// use std library or glm functions to determine expected test values, the output of functions from intrinsics.hlsl will be verified against these values
IntrinsicsTestValues expected;
Expand Down Expand Up @@ -188,6 +196,11 @@ class CIntrinsicsTester final : public ITester
auto inverseGlm = glm::inverse(reinterpret_cast<typename float32_t3x3::Base const&>(testInput.inverse));
expected.inverse = reinterpret_cast<float32_t3x3&>(inverseGlm);

expected.addCarry.result = glm::uaddCarry(testInput.addCarryA, testInput.addCarryB, expected.addCarry.carry);
expected.subBorrow.result = glm::usubBorrow(testInput.subBorrowA, testInput.subBorrowB, expected.subBorrow.borrow);
expected.addCarryVec.result = glm::uaddCarry(testInput.addCarryAVec, testInput.addCarryBVec, expected.addCarryVec.carry);
expected.subBorrowVec.result = glm::usubBorrow(testInput.subBorrowAVec, testInput.subBorrowBVec, expected.subBorrowVec.borrow);

performCpuTests(testInput, expected);
performGpuTests(testInput, expected);
}
Expand Down
Loading