This patch optimizes the emulation of unit-stride load/store RVV instructions when the data being loaded/stored per iteration amounts to 64 bytes or more. The optimization consists of calling __builtin_memcpy on chunks of data of 128 and 256 bytes between the memory address of the simulated vector register and the destination memory address and vice versa. This is done only if we have direct access to the RAM of the host machine.
Signed-off-by: Paolo Savini <paolo.sav...@embecosm.com> --- target/riscv/vector_helper.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 4b444c6bc5..7674972784 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -486,7 +486,22 @@ vext_group_ldst_host(CPURISCVState *env, void *vd, uint32_t byte_end, } fn = fns[is_load][group_size]; - fn(vd, byte_offset, host + byte_offset); + + if (byte_offset + 32 < byte_end) { + group_size = MO_256; + if (is_load) + __builtin_memcpy((uint8_t *)(vd + byte_offset), (uint8_t *)(host + byte_offset), 32); + else + __builtin_memcpy((uint8_t *)(host + byte_offset), (uint8_t *)(vd + byte_offset), 32); + } else if (byte_offset + 16 < byte_end) { + group_size = MO_128; + if (is_load) + __builtin_memcpy((uint8_t *)(vd + byte_offset), (uint8_t *)(host + byte_offset), 16); + else + __builtin_memcpy((uint8_t *)(host + byte_offset), (uint8_t *)(vd + byte_offset), 16); + } else { + fn(vd, byte_offset, host + byte_offset); + } return 1 << group_size; } -- 2.17.1