[PATCH v2 13/37] baseband/acc10x: limit cases for HARQ pruning

[Maxime Coquelin]

On 8/20/22 04:31, Hernan Vargas wrote:
> Add flag ACC101_HARQ_PRUNING_OPTIMIZATION to limit cases when HARQ
> pruning is valid.
> 
> Signed-off-by: Hernan Vargas <hernan.vargas at intel.com>
> ---
>   drivers/baseband/acc100/rte_acc100_pmd.c | 52 +++++++++++++++++++-----
>   1 file changed, 41 insertions(+), 11 deletions(-)
> 
> diff --git a/drivers/baseband/acc100/rte_acc100_pmd.c b/drivers/baseband/acc100/rte_acc100_pmd.c
> index 81bae4d695..e47f7d68c2 100644
> --- a/drivers/baseband/acc100/rte_acc100_pmd.c
> +++ b/drivers/baseband/acc100/rte_acc100_pmd.c
> @@ -1370,17 +1370,23 @@ acc100_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
>   	harq_index = hq_index(op->ldpc_dec.harq_combined_output.offset);
>   #ifdef ACC100_EXT_MEM
>   	/* Limit cases when HARQ pruning is valid */
> +#ifdef ACC100_HARQ_PRUNING_OPTIMIZATION
>   	harq_prun = ((op->ldpc_dec.harq_combined_output.offset %
> -			ACC100_HARQ_OFFSET) == 0) &&
> -			(op->ldpc_dec.harq_combined_output.offset <= UINT16_MAX
> -			* ACC100_HARQ_OFFSET);
> +			ACC100_HARQ_OFFSET) == 0);
> +#endif

Optimizations should not be put under #ifdefs, it will become a testing
hell otherwise. CI will have to run as many builds as there are possible 
combinations, which is not sustainable.

Even if not part of this patch, the "#ifdef ACC100_EXT_MEM" should also
be removed.

>   #endif
>   	if (fcw->hcin_en > 0) {
>   		harq_in_length = op->ldpc_dec.harq_combined_input.length;
>   		if (fcw->hcin_decomp_mode > 0)
>   			harq_in_length = harq_in_length * 8 / 6;
> -		harq_in_length = RTE_ALIGN(harq_in_length, 64);
> -		if ((harq_layout[harq_index].offset > 0) & harq_prun) {
> +		harq_in_length = RTE_MIN(harq_in_length, op->ldpc_dec.n_cb
> +				- op->ldpc_dec.n_filler);
> +		/* Alignment on next 64B - Already enforced from HC output */
> +		harq_in_length = RTE_ALIGN_FLOOR(harq_in_length, 64);
> +		/* Stronger alignment requirement when in decompression mode */
> +		if (fcw->hcin_decomp_mode > 0)
> +			harq_in_length = RTE_ALIGN_FLOOR(harq_in_length, 256);
> +		if ((harq_layout[harq_index].offset > 0) && harq_prun) {
>   			rte_bbdev_log_debug("HARQ IN offset unexpected for now\n");
>   			fcw->hcin_size0 = harq_layout[harq_index].size0;
>   			fcw->hcin_offset = harq_layout[harq_index].offset;
> @@ -1455,6 +1461,7 @@ acc101_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
>   	uint16_t harq_out_length, harq_in_length, ncb_p, k0_p, parity_offset;
>   	uint32_t harq_index;
>   	uint32_t l;
> +	bool harq_prun = false;
>   
>   	fcw->qm = op->ldpc_dec.q_m;
>   	fcw->nfiller = op->ldpc_dec.n_filler;
> @@ -1500,6 +1507,13 @@ acc101_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
>   	fcw->llr_pack_mode = check_bit(op->ldpc_dec.op_flags,
>   			RTE_BBDEV_LDPC_LLR_COMPRESSION);
>   	harq_index = hq_index(op->ldpc_dec.harq_combined_output.offset);
> +	#ifdef ACC100_EXT_MEM
> +	/* Limit cases when HARQ pruning is valid */
> +#ifdef ACC101_HARQ_PRUNING_OPTIMIZATION
> +	harq_prun = ((op->ldpc_dec.harq_combined_output.offset %
> +			ACC101_HARQ_OFFSET) == 0);
> +#endif
> +#endif
>   	if (fcw->hcin_en > 0) {
>   		harq_in_length = op->ldpc_dec.harq_combined_input.length;
>   		if (fcw->hcin_decomp_mode > 0)
> @@ -1508,9 +1522,17 @@ acc101_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
>   				- op->ldpc_dec.n_filler);
>   		/* Alignment on next 64B - Already enforced from HC output */
>   		harq_in_length = RTE_ALIGN_FLOOR(harq_in_length, 64);
> -		fcw->hcin_size0 = harq_in_length;
> -		fcw->hcin_offset = 0;
> -		fcw->hcin_size1 = 0;
> +		if ((harq_layout[harq_index].offset > 0) && harq_prun) {
> +			rte_bbdev_log_debug("HARQ IN offset unexpected for now\n");
> +			fcw->hcin_size0 = harq_layout[harq_index].size0;
> +			fcw->hcin_offset = harq_layout[harq_index].offset;
> +			fcw->hcin_size1 = harq_in_length -
> +					harq_layout[harq_index].offset;
> +		} else {
> +			fcw->hcin_size0 = harq_in_length;
> +			fcw->hcin_offset = 0;
> +			fcw->hcin_size1 = 0;
> +		}
>   	} else {
>   		fcw->hcin_size0 = 0;
>   		fcw->hcin_offset = 0;
> @@ -1551,9 +1573,17 @@ acc101_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
>   		harq_out_length = RTE_MIN(harq_out_length, ncb_p);
>   		/* Alignment on next 64B */
>   		harq_out_length = RTE_ALIGN_CEIL(harq_out_length, 64);
> -		fcw->hcout_size0 = harq_out_length;
> -		fcw->hcout_size1 = 0;
> -		fcw->hcout_offset = 0;
> +		if ((k0_p > fcw->hcin_size0 + ACC100_HARQ_OFFSET_THRESHOLD) &&
> +				harq_prun) {
> +			fcw->hcout_size0 = (uint16_t) fcw->hcin_size0;
> +			fcw->hcout_offset = k0_p & 0xFFC0;
> +			fcw->hcout_size1 = harq_out_length - fcw->hcout_offset;
> +		} else {
> +			fcw->hcout_size0 = harq_out_length;
> +			fcw->hcout_size1 = 0;
> +			fcw->hcout_offset = 0;
> +		}
> +
>   		harq_layout[harq_index].offset = fcw->hcout_offset;
>   		harq_layout[harq_index].size0 = fcw->hcout_size0;
>   	} else {