Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

more logging

Browse Source
This commit is contained in:
Hendrik Groove 2024-10-20 20:53:50 +02:00
parent 4a10135006
commit c964dd62b4
1 changed files with 14 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
src/common/device_helpers.hip.h
View File

@ -441,12 +441,11 @@ struct XGBCachingDeviceAllocatorImpl : XGBBaseDeviceAllocator<T> {
std::make_unique<hipcub::CachingDeviceAllocator>(2, 9, 29)};
return *allocator;
}
pointer allocate(size_t n) { // NOLINT
pointer allocate(size_t n) {
pointer thrust_ptr;
if (use_cub_allocator_) {
T* raw_ptr{nullptr};
auto errc = GetGlobalCachingAllocator().DeviceAllocate(reinterpret_cast<void **>(&raw_ptr),
n * sizeof(T));
auto errc = GetGlobalCachingAllocator().DeviceAllocate(reinterpret_cast<void **>(&raw_ptr), n * sizeof(T));
if (errc != hipSuccess) {
ThrowOOMError("Caching allocator", n * sizeof(T));
}
@ -459,10 +458,14 @@ struct XGBCachingDeviceAllocatorImpl : XGBBaseDeviceAllocator<T> {
ThrowOOMError(e.what(), n * sizeof(T));
}
}
std::cerr << "XGBCachingDeviceAllocatorImpl: Allocated " << n * sizeof(T)
<< " bytes at " << thrust_ptr.get() << std::endl;
GlobalMemoryLogger().RegisterAllocation(thrust_ptr.get(), n * sizeof(T));
return thrust_ptr;
}
void deallocate(pointer ptr, size_t n) { // NOLINT
void deallocate(pointer ptr, size_t n) {
std::cerr << "XGBCachingDeviceAllocatorImpl: Deallocating " << n * sizeof(T)
<< " bytes at " << ptr.get() << std::endl;
GlobalMemoryLogger().RegisterDeallocation(ptr.get(), n * sizeof(T));
if (use_cub_allocator_) {
GetGlobalCachingAllocator().DeviceFree(ptr.get());
@ -574,6 +577,8 @@ xgboost::common::Span<T> LazyResize(xgboost::Context const *ctx,
template <typename T>
void CopyDeviceSpanToVector(std::vector<T> *dst, xgboost::common::Span<T> src) {
CHECK_EQ(dst->size(), src.size());
std::cerr << "CopyDeviceSpanToVector: Copying " << src.size() * sizeof(T)
<< " bytes from device to host" << std::endl;
dh::safe_cuda(hipMemcpyAsync(dst->data(), src.data(), dst->size() * sizeof(T),
hipMemcpyDeviceToHost));
}
@ -601,8 +606,9 @@ void CopyToD(HContainer const &h, DContainer *d) {
d->resize(h.size());
using HVT = std::remove_cv_t<typename HContainer::value_type>;
using DVT = std::remove_cv_t<typename DContainer::value_type>;
static_assert(std::is_same<HVT, DVT>::value,
"Host and device containers must have same value type.");
static_assert(std::is_same<HVT, DVT>::value, "Host and device containers must have same value type.");
std::cerr << "CopyToD: Copying " << h.size() * sizeof(HVT)
<< " bytes from host to device" << std::endl;
dh::safe_cuda(hipMemcpyAsync(d->data().get(), h.data(), h.size() * sizeof(HVT),
hipMemcpyHostToDevice));
}