maki/openairinterface5g
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/ldpc_encoder_ZC384_optimization' into integration_2025_w36 (!3614)

Browse Source 
Ldpc encoder zc384 optimization

This is a modification for the ldpc encoder which improves performance for
high-throughput cases. It contains a newly-generated file for innermost part of
the parity bit generation which, for AVX512, uses the mm512_permutex2var_epi8
instruction and for 128-bit (aarch64) the mm_alignr_epi8 (vextq_s8) in the
computation corresponding to each non-zero bit of the H matrix. This allows for
removing a very large memcpy and reduces the memory demand for the parity matrix
computation. For the moment this is limited to largest case in BG1, namely
Zc=384. This is the only format used when the number of segments after codeblock
segmentation is large (>8). This improves the timing required for ldpc parity
bits generation by more than a factor 2 with AVX512. This significantly reduces
the total time to generate the DLSCH/PDSCH.

See the merge request description for numbers.
This commit is contained in:
Jaroslava Fiedlerova
2025-09-02 11:06:20 +02:00
parent 9d2960eab8 0e09c7c347
commit 774c390bbe
5 changed files with 545 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
openair1/PHY/CODING/nrLDPC_encoder/ldpc384_alignr_byte_128.c
+153
View File
File diff suppressed because one or more lines are too long
openair1/PHY/CODING/nrLDPC_encoder/ldpc384_simd512_alignr_byte.c
+151
View File
File diff suppressed because one or more lines are too long
openair1/PHY/CODING/nrLDPC_encoder/ldpc384_simd512_permutex_byte.c
+218
View File
File diff suppressed because one or more lines are too long
openair1/PHY/CODING/nrLDPC_encoder/ldpc_encode_parity_check.c
+22 -3
View File
@@ -36,13 +36,27 @@
#include "assertions.h"
#include "common/utils/LOG/log.h"
#define USE_PERMUTEX
#ifdef __aarch64__
#define USE_ALIGNR
#endif
#ifdef __AVX512F__
#if defined(__AVX512VBMI__) && defined(USE_PERMUTEX)
// For AVX512 machines, use an AVX512 version of the encoder for Zc=384 only for now. This is used almost exclusively for
// high-throughput cases. The version with "permutex2var" instruction uses less memory (i.e. 1/64th of the memory to store the
// input), but uses more reads instead of creating 64 shifts of the input with memcpy
#include "ldpc384_simd512_permutex_byte.c"
#else
#include "ldpc384_simd512_byte.c"
#endif
#else
#include "ldpc384_byte.c"
#endif
#ifdef USE_ALIGNR
#include "ldpc384_alignr_byte_128.c"
#else
#include "ldpc384_byte_128.c"
#endif
#include "ldpc352_byte.c"
#include "ldpc352_byte_128.c"
#include "ldpc320_byte.c"
@@ -96,8 +110,13 @@ static void encode_parity_check_part_optim(uint8_t *cc, uint8_t *d, short BG,sho
memcpy(&c[2 * i1 * Zc], &cc[i1 * Zc], Zc * sizeof(unsigned char));
memcpy(&c[(2 * i1 + 1) * Zc], &cc[i1 * Zc], Zc * sizeof(unsigned char));
}
for (int i1 = 1; i1 < simd_size; i1++) {
memcpy(&c[(2 * ncols * Zc * i1)], &c[i1], (2 * ncols * Zc * sizeof(unsigned char)) - i1);
#if (defined(USE_PERMUTEX) && defined(__AVX512VBMI__)) || defined(USE_ALIGNR)
if (Zc < 384 || BG == 2)
#endif
{
for (int i1 = 1; i1 < simd_size; i1++) {
memcpy(&c[(2 * ncols * Zc * i1)], &c[i1], (2 * ncols * Zc * sizeof(unsigned char)) - i1);
}
}
if (BG == 1) {
switch (Zc) {
openair1/SIMULATION/NR_PHY/dlsim.c
+1
View File
@@ -1032,6 +1032,7 @@ printf("%d\n", slot);
reset_meas(&gNB->dlsch_rate_matching_stats);
reset_meas(&gNB->dlsch_segmentation_stats);
reset_meas(&gNB->dlsch_modulation_stats);
reset_meas(&gNB->dlsch_precoding_stats);
reset_meas(&gNB->dlsch_encoding_stats);
reset_meas(&gNB->dci_generation_stats);
reset_meas(&gNB->tinput);