Commit Graph
13 Commits
Author SHA1 Message Date
Thomas Schlichter 300346c43a nrLDPC_coding_t2: replace global q_bufs by struct data_buffers on stack 2025-05-20 07:57:23 +00:00
Thomas Schlichter 48e78ff4b0 nrLDPC_coding_t2: fix q_bufs memory leak 2025-05-20 07:57:23 +00:00
Thomas Schlichter ac9a8f017b nrLDPC_coding_t2 fix: make sure to free allocated mbufs
The DPDK driver may directly provide the internal HW mbuf in the dequeued structure.
So don't try to free the mbufs from that dequeued structure, but the ones we allocated.
2025-05-20 07:57:21 +00:00
Thomas Schlichter 1612ba33a8 nrLDPC_coding_t2: remove unused soft_outputs, harq_inputs and harq_outputs elements 2025-05-20 07:56:26 +00:00
Thomas Schlichter d8b3bfd17b nrLDPC_coding_t2: use nb_segments_decoding() and nb_segments_encoding() to calculate num_segments 2025-05-20 07:56:24 +00:00
Thomas Schlichter 084bbb0363 nrLDPC_coding_t2: also support newer DPDK versions 2025-05-20 07:54:12 +00:00
Romain Beurdouche 360f341394 feat(nrLDPC_coding_t2): Shift encoder output with 64 bits shift
Use 64 bits shift to shift the output segment of the encoding operations to their offset in the coding library output buffer.
2025-05-13 14:08:33 +00:00
Jaroslava Fiedlerova b31dd728cb T2: Use 8b packed output of the T2 encoder
- modify retrieve_ldpc_enc_op() to store encoded results in a packed format
- add timing measurements for T2 encoder
- add simde implementation for bit reversal
  - Introduce new bit reversal implementation using simde_mm_gf2p8affine_epi64_epi8
    instruction, based on https://wunkolo.github.io/post/2020/11/gf2p8affineqb-bit-reversal/.
    This implementation requires GFNI and AVX512VL support on the target machine.
2025-05-13 14:08:33 +00:00
Romain Beurdouche 1b31ac417b fix(nrLDPC_coding_interface): Move the encoding output to the TB
Since this branch aims to bring all the encoded segments packed and contiguous,
it doesn't make anymore sense to have one output array per segment.
Therefore this commit moves the output array to the TB instead of the segment and adapts its size.

TODO: Adapt the size of f where it is relevant.
2025-05-13 14:08:33 +00:00
Romain Beurdouche 0d3008c244 fix(nrLDPC_coding_t2): HARQ combined offset
The offset provided for each code block in the HARQ combined input and output buffer shall not be above 512.
A modulus was performed on the offset of the TB in the buffer to avoid this situation.
But the offset of the code block was added afterward so that the total offset was sometimes going above 512.
This commit performs the modulus after adding the code block offset.
2025-01-17 10:55:03 +00:00
Robert Schmidt 0aeba914a0 Cleanup in CMakeLists.txt
- Remove all variables (like OPENAIR1), they serve no purpose and make
  unnecessarily long lines
- Remove linking to T, it does not seem to be necessary
- Avoid intermediate variables to keep sources, and declare libraries
  directly, making for shorter code
2024-12-16 08:40:54 +01:00
Romain Beurdouche 23bfce8d91 feat(nrLDPC_coding_interface): Move LDPC and Turdo coding libraries cmake lists in sub directories 2024-12-16 08:40:54 +01:00
Romain Beurdouche c6bdde1244 feat(nrLDPC_coding_interface): Add ldpc_slot_t2 coding library 2024-12-16 08:40:54 +01:00