File tensor_buffer.hpp¶
-
namespace xir
-
namespace vart
-
class TensorBuffer
- #include <tensor_buffer.hpp>
Class of TensorBuffer.
Subclassed by TensorBufferExt
Public Types
-
enum class location_t¶
Values:
-
enumerator HOST_VIRT¶
Host only data() should return a valid pair (0,Nonzero_u); data_phy() should return an invalid pair (0,0u);.
-
enumerator HOST_PHY¶
continuous physicial memory, shared among host and device.
both data () and data_phy() should return a valid pair.
-
enumerator DEVICE_0¶
only accessiable by device.
data () should return an invalid pair (0,0u); data_phy() should return a valid pair.
-
enumerator DEVICE_1¶
only accessiable by device.
-
enumerator DEVICE_2¶
only accessiable by device.
-
enumerator DEVICE_3¶
only accessiable by device.
-
enumerator DEVICE_4¶
only accessiable by device.
-
enumerator DEVICE_5¶
only accessiable by device.
-
enumerator DEVICE_6¶
only accessiable by device.
-
enumerator DEVICE_7¶
only accessiable by device.
-
enumerator HOST_VIRT¶
Public Functions
-
virtual ~TensorBuffer() = default¶
-
virtual std::pair<std::uint64_t, std::size_t> data(const std::vector<std::int32_t> idx = {}) = 0
Get the data address of the index and the size of the data available for use.
Sample code:
vart::TensorBuffer* tb; std::tie(data_addr, tensor_size) = tb->data({0,0,0,0});
- Parameters:
idx – The index of the data to be accessed, its dimension same as the tensor shape.
- Returns:
A pair of the data address of the index and the size of the data available for use in byte unit.
-
inline virtual location_t get_location() const
Get where the tensor buffer located.
Sample code:
vart::TensorBuffer* tb; switch (tb->get_location()) { case vart::TensorBuffer::location_t::HOST_VIRT: // do nothing break; case vart::TensorBuffer::location_t::HOST_PHY: // do nothing break; default: // do nothing break; }
- Returns:
the tensor buffer location, a location_t enum type value: HOST_VIRT/HOST_PHY/DEVICE_*.
-
inline virtual std::pair<uint64_t, size_t> data_phy(const std::vector<std::int32_t> idx)
Get the data physical address of the index and the size of the data available for use.
Sample code:
vart::TensorBuffer* tb; std::tie(phy_data, phy_size) = tb->data_phy({0, 0});
- Parameters:
idx – The index of the data to be accessed, its dimension same to the tensor shape.
- Returns:
A pair of the data physical address of the index and the size of the data available for use in byte unit.
-
inline virtual void sync_for_read(uint64_t offset, size_t size)
Invalid cache for reading Before read, it is no-op in case get_location() returns DEVICE_ONLY or HOST_VIRT.
Sample code:
for (auto& output : output_tensor_buffers) { output->sync_for_read(0, output->get_tensor()->get_data_size() / output->get_tensor()->get_shape()[0]); }
- Parameters:
offset – The start offset address.
size – The data size.
- Returns:
void
-
inline virtual void sync_for_write(uint64_t offset, size_t size)
Flush cache for writing after write, it is no-op in case get_location() returns DEVICE_ONLY or HOST_VIRT.
Sample code:
for (auto& input : input_tensor_buffers) { input->sync_for_write(0, input->get_tensor()->get_data_size() / input->get_tensor()->get_shape()[0]); }
- Parameters:
offset – The start offset address.
size – The data size.
- Returns:
void
-
virtual void copy_from_host(size_t batch_idx, const void *buf, size_t size, size_t offset)
copy data from source buffer.
- Parameters:
batch_idx – the batch index.
buf – source buffer start address.
size – data size to be copied.
offset – the start offset to be copied.
- Returns:
void
-
virtual void copy_to_host(size_t batch_idx, void *buf, size_t size, size_t offset)
copy data to destination buffer.
Sample code:
vart::TensorBuffer* tb_from; vart::TensorBuffer* tb_to; for (auto batch = 0u; batch < batch_size; ++batch) { std::tie(data, tensor_size) = tb_to->data({(int)batch, 0, 0, 0}); tb_from->copy_to_host(batch, reinterpret_cast<void*>(data), tensor_size, 0u); }
- Parameters:
batch_idx – the batch index.
buf – destination buffer start address.
size – data size to be copied.
offset – the start offset to be copied.
- Returns:
void
-
const xir::Tensor *get_tensor() const
Get tensor of TensorBuffer.
- Returns:
A pointer to the tensor.
-
virtual std::string to_string() const
for fancy log messages
Public Static Functions
-
static std::string to_string(location_t value)
for TensorBuffer location message
-
static void copy_tensor_buffer(vart::TensorBuffer *tb_from, vart::TensorBuffer *tb_to)
copy TensorBuffer from one to another.
Sample code:
vart::TensorBuffer* tb_from; vart::TensorBuffer* tb_to; vart::TensorBuffer::copy_tensor_buffer(tb_from.get(), tb_to.get());
- Parameters:
tb_from – the source TensorBuffer.
tb_to – the destination TensorBuffer.
- Returns:
void
-
static std::unique_ptr<TensorBuffer> create_unowned_device_tensor_buffer(const xir::Tensor *tensor, uint64_t batch_addr[], size_t addr_arrsize)
create unowned device tensor buffer with device physical addresses for a tensor.
There are some limitations on the arguments:
The addr_arrsize must NOT be greater than the tensor batch.
The tensor must have attribute ddr_addr whose value must be 0.
Sample code:
auto runner = vart::RunnerExt::create_runner(subgraph, attrs); auto input_tensors = runner->get_input_tensors(); auto output_tensors = runner->get_output_tensors(); std::vector<vart::TensorBuffer*> input_tensor_buffers; std::vector<vart::TensorBuffer*> output_tensor_buffers; uint64_t in_batch_addr[1]; uint64_t out_batch_addr[1]; in_batch_addr[0] = DEVICE_PHY_ADDRESS_IN; out_batch_addr[0] = DEVICE_PHY_ADDRESS_OUT; auto input_tb = vart::TensorBuffer::create_unowned_device_tensor_buffer( input_tensors[0], in_batch_addr, 1); auto output_tb = vart::TensorBuffer::create_unowned_device_tensor_buffer( output_tensors[0], out_batch_addr, 1); input_tensor_buffers.emplace_back(input_tb.get()); output_tensor_buffers.emplace_back(output_tb.get()); auto v = runner->execute_async(input_tensor_buffers, output_tensor_buffers);
- Parameters:
tensor – XIR tensor pointer
batch_addr – Array which contains device physical address for each batch
addr_arrsize – The array size of batch_addr
- Returns:
Unique pointer of created tensor buffer.
-
enum class location_t¶
-
class TensorBufferExt : public TensorBuffer
Public Types
-
enum class location_t¶
Values:
-
enumerator HOST_VIRT¶
Host only data() should return a valid pair (0,Nonzero_u); data_phy() should return an invalid pair (0,0u);.
-
enumerator HOST_PHY¶
continuous physicial memory, shared among host and device.
both data () and data_phy() should return a valid pair.
-
enumerator DEVICE_0¶
only accessiable by device.
data () should return an invalid pair (0,0u); data_phy() should return a valid pair.
-
enumerator DEVICE_1¶
only accessiable by device.
-
enumerator DEVICE_2¶
only accessiable by device.
-
enumerator DEVICE_3¶
only accessiable by device.
-
enumerator DEVICE_4¶
only accessiable by device.
-
enumerator DEVICE_5¶
only accessiable by device.
-
enumerator DEVICE_6¶
only accessiable by device.
-
enumerator DEVICE_7¶
only accessiable by device.
-
enumerator HOST_VIRT¶
Public Functions
-
virtual std::string to_string() const
for fancy log messages
-
virtual std::pair<std::uint64_t, std::size_t> data(const std::vector<std::int32_t> idx = {}) = 0
Get the data address of the index and the size of the data available for use.
Sample code:
vart::TensorBuffer* tb; std::tie(data_addr, tensor_size) = tb->data({0,0,0,0});
- Parameters:
idx – The index of the data to be accessed, its dimension same as the tensor shape.
- Returns:
A pair of the data address of the index and the size of the data available for use in byte unit.
-
inline virtual location_t get_location() const
Get where the tensor buffer located.
Sample code:
vart::TensorBuffer* tb; switch (tb->get_location()) { case vart::TensorBuffer::location_t::HOST_VIRT: // do nothing break; case vart::TensorBuffer::location_t::HOST_PHY: // do nothing break; default: // do nothing break; }
- Returns:
the tensor buffer location, a location_t enum type value: HOST_VIRT/HOST_PHY/DEVICE_*.
-
inline virtual std::pair<uint64_t, size_t> data_phy(const std::vector<std::int32_t> idx)
Get the data physical address of the index and the size of the data available for use.
Sample code:
vart::TensorBuffer* tb; std::tie(phy_data, phy_size) = tb->data_phy({0, 0});
- Parameters:
idx – The index of the data to be accessed, its dimension same to the tensor shape.
- Returns:
A pair of the data physical address of the index and the size of the data available for use in byte unit.
-
inline virtual void sync_for_read(uint64_t offset, size_t size)
Invalid cache for reading Before read, it is no-op in case get_location() returns DEVICE_ONLY or HOST_VIRT.
Sample code:
for (auto& output : output_tensor_buffers) { output->sync_for_read(0, output->get_tensor()->get_data_size() / output->get_tensor()->get_shape()[0]); }
- Parameters:
offset – The start offset address.
size – The data size.
- Returns:
void
-
inline virtual void sync_for_write(uint64_t offset, size_t size)
Flush cache for writing after write, it is no-op in case get_location() returns DEVICE_ONLY or HOST_VIRT.
Sample code:
for (auto& input : input_tensor_buffers) { input->sync_for_write(0, input->get_tensor()->get_data_size() / input->get_tensor()->get_shape()[0]); }
- Parameters:
offset – The start offset address.
size – The data size.
- Returns:
void
-
virtual void copy_from_host(size_t batch_idx, const void *buf, size_t size, size_t offset)
copy data from source buffer.
- Parameters:
batch_idx – the batch index.
buf – source buffer start address.
size – data size to be copied.
offset – the start offset to be copied.
- Returns:
void
-
virtual void copy_to_host(size_t batch_idx, void *buf, size_t size, size_t offset)
copy data to destination buffer.
Sample code:
vart::TensorBuffer* tb_from; vart::TensorBuffer* tb_to; for (auto batch = 0u; batch < batch_size; ++batch) { std::tie(data, tensor_size) = tb_to->data({(int)batch, 0, 0, 0}); tb_from->copy_to_host(batch, reinterpret_cast<void*>(data), tensor_size, 0u); }
- Parameters:
batch_idx – the batch index.
buf – destination buffer start address.
size – data size to be copied.
offset – the start offset to be copied.
- Returns:
void
-
const xir::Tensor *get_tensor() const
Get tensor of TensorBuffer.
- Returns:
A pointer to the tensor.
Public Static Functions
-
static std::string to_string(location_t value)
for TensorBuffer location message
-
static void copy_tensor_buffer(vart::TensorBuffer *tb_from, vart::TensorBuffer *tb_to)
copy TensorBuffer from one to another.
Sample code:
vart::TensorBuffer* tb_from; vart::TensorBuffer* tb_to; vart::TensorBuffer::copy_tensor_buffer(tb_from.get(), tb_to.get());
- Parameters:
tb_from – the source TensorBuffer.
tb_to – the destination TensorBuffer.
- Returns:
void
-
static std::unique_ptr<TensorBuffer> create_unowned_device_tensor_buffer(const xir::Tensor *tensor, uint64_t batch_addr[], size_t addr_arrsize)
create unowned device tensor buffer with device physical addresses for a tensor.
There are some limitations on the arguments:
The addr_arrsize must NOT be greater than the tensor batch.
The tensor must have attribute ddr_addr whose value must be 0.
Sample code:
auto runner = vart::RunnerExt::create_runner(subgraph, attrs); auto input_tensors = runner->get_input_tensors(); auto output_tensors = runner->get_output_tensors(); std::vector<vart::TensorBuffer*> input_tensor_buffers; std::vector<vart::TensorBuffer*> output_tensor_buffers; uint64_t in_batch_addr[1]; uint64_t out_batch_addr[1]; in_batch_addr[0] = DEVICE_PHY_ADDRESS_IN; out_batch_addr[0] = DEVICE_PHY_ADDRESS_OUT; auto input_tb = vart::TensorBuffer::create_unowned_device_tensor_buffer( input_tensors[0], in_batch_addr, 1); auto output_tb = vart::TensorBuffer::create_unowned_device_tensor_buffer( output_tensors[0], out_batch_addr, 1); input_tensor_buffers.emplace_back(input_tb.get()); output_tensor_buffers.emplace_back(output_tb.get()); auto v = runner->execute_async(input_tensor_buffers, output_tensor_buffers);
- Parameters:
tensor – XIR tensor pointer
batch_addr – Array which contains device physical address for each batch
addr_arrsize – The array size of batch_addr
- Returns:
Unique pointer of created tensor buffer.
-
enum class location_t¶
-
struct XclBo¶
-
class TensorBuffer