[PATCH v11 3/6] ptr_compress: add pointer compression library
Konstantin Ananyev
konstantin.ananyev at huawei.com
Thu Jun 6 15:22:39 CEST 2024
> +/**
> + * Compress pointers into 32-bit offsets from base pointer.
> + *
> + * @note It is programmer's responsibility to ensure the resulting offsets fit
> + * into 32 bits. Alignment of the structures pointed to by the pointers allows
> + * us to drop bits from the offsets. This is controlled by the bit_shift
> + * parameter. This means that if structures are aligned by 8 bytes they must be
> + * within 32GB of the base pointer. If there is no such alignment guarantee they
> + * must be within 4GB.
> + *
> + * @param ptr_base
> + * A pointer used to calculate offsets of pointers in src_table.
> + * @param src_table
> + * A pointer to an array of pointers.
> + * @param dest_table
> + * A pointer to an array of compressed pointers returned by this function.
> + * @param n
> + * The number of objects to compress, must be strictly positive.
> + * @param bit_shift
> + * Byte alignment of memory pointed to by the pointers allows for
> + * bits to be dropped from the offset and hence widen the memory region that
> + * can be covered. This controls how many bits are right shifted.
> + **/
> +static __rte_always_inline void
> +rte_ptr_compress_32_shift(void *ptr_base, void **src_table,
> + uint32_t *dest_table, size_t n, uint8_t bit_shift)
Probably: void * const *src_table
And on decompress: const uint32_t *src_table
> +{
> + size_t i = 0;
> +#if defined RTE_HAS_SVE_ACLE && !defined RTE_ARCH_ARMv8_AARCH32
> + svuint64_t v_ptr_table;
> + do {
> + svbool_t pg = svwhilelt_b64(i, n);
> + v_ptr_table = svld1_u64(pg, (uint64_t *)src_table + i);
> + v_ptr_table = svsub_x(pg, v_ptr_table, (uint64_t)ptr_base);
> + v_ptr_table = svlsr_x(pg, v_ptr_table, bit_shift);
> + svst1w(pg, &dest_table[i], v_ptr_table);
> + i += svcntd();
> + } while (i < n);
> +#elif defined __ARM_NEON && !defined RTE_ARCH_ARMv8_AARCH32
> + uint64_t ptr_diff;
> + uint64x2_t v_ptr_table;
> + /* right shift is done by left shifting by negative int */
> + int64x2_t v_shift = vdupq_n_s64(-bit_shift);
> + uint64x2_t v_ptr_base = vdupq_n_u64((uint64_t)ptr_base);
> + const size_t n_even = n & ~0x1;
> + for (; i < n_even; i += 2) {
> + v_ptr_table = vld1q_u64((const uint64_t *)src_table + i);
> + v_ptr_table = vsubq_u64(v_ptr_table, v_ptr_base);
> + v_ptr_table = vshlq_u64(v_ptr_table, v_shift);
> + vst1_u32(dest_table + i, vqmovn_u64(v_ptr_table));
> + }
> + /* process leftover single item in case of odd number of n */
> + if (unlikely(n & 0x1)) {
> + ptr_diff = RTE_PTR_DIFF(src_table[i], ptr_base);
> + dest_table[i] = (uint32_t) (ptr_diff >> bit_shift);
> + }
> +#else
> + uintptr_t ptr_diff;
> + for (; i < n; i++) {
> + ptr_diff = RTE_PTR_DIFF(src_table[i], ptr_base);
> + ptr_diff = ptr_diff >> bit_shift;
> + RTE_ASSERT(ptr_diff <= UINT32_MAX);
> + dest_table[i] = (uint32_t) ptr_diff;
> + }
> +#endif
> +}
> +
More information about the dev
mailing list