On Tue, Aug 24, 2021 at 09:57:52AM +0800, Hongtao Liu wrote:
> Trying 5 -> 7:
> 5: r85:V4SF=[`*.LC0']
> REG_EQUAL const_vector
> 7: r84:V4SF=vec_select(vec_concat(r85:V4SF,r85:V4SF),parallel)
> REG_DEAD r85:V4SF
> REG_EQUAL const_vector
> Failed to match this instruction:
> (set (reg:V4SF 84)
> (const_vector:V4SF [
> (const_double:SF 3.0e+0 [0x0.cp+2])
> (const_double:SF 2.0e+0 [0x0.8p+2])
> (const_double:SF 4.0e+0 [0x0.8p+3])
> (const_double:SF 1.0e+0 [0x0.8p+1])
> ]))
>
> (insn 5 2 7 2 (set (reg:V4SF 85)
> (mem/u/c:V4SF (symbol_ref/u:DI ("*.LC0") [flags 0x2]) [0 S16
> A128]))
> "/export/users/liuhongt/install/git_trunk_master_native/lib/gcc/x86_64-pc-linux-gnu/12.0.0/include/xmmintrin.h":746:19
> 1600 {movv4sf_internal}
> (expr_list:REG_EQUAL (const_vector:V4SF [
> (const_double:SF 4.0e+0 [0x0.8p+3])
> (const_double:SF 3.0e+0 [0x0.cp+2])
> (const_double:SF 2.0e+0 [0x0.8p+2])
> (const_double:SF 1.0e+0 [0x0.8p+1])
> ])
> (nil)))
> (insn 7 5 11 2 (set (reg:V4SF 84)
> (vec_select:V4SF (vec_concat:V8SF (reg:V4SF 85)
> (reg:V4SF 85))
> (parallel [
> (const_int 1 [0x1])
> (const_int 2 [0x2])
> (const_int 4 [0x4])
> (const_int 7 [0x7])
> ])))
> "/export/users/liuhongt/install/git_trunk_master_native/lib/gcc/x86_64-pc-linux-gnu/12.0.0/include/xmmintrin.h":746:19
> 3015 {sse_shufps_v4sf}
> (expr_list:REG_DEAD (reg:V4SF 85)
> (expr_list:REG_EQUAL (const_vector:V4SF [
> (const_double:SF 3.0e+0 [0x0.cp+2])
> (const_double:SF 2.0e+0 [0x0.8p+2])
> (const_double:SF 4.0e+0 [0x0.8p+3])
> (const_double:SF 1.0e+0 [0x0.8p+1])
> ])
> (nil))))
>
> I think pass_combine should be extended to force illegitimate constant
> to constant pool and recog load insn again, It looks like a general
> optimization that better not do it in the backend.
Patches welcome. You should do this like change_zero_ext is done, and
perhaps make sure you do not introduce new is_just_move insns that can
make 2->2 combinations do the wrong thing.
Also somehow make this not take exponential time? It looks like this
should onle be done in cases where change_zero_ext is not, and the
reverse, so this will work fine with a little attention to detail.
gl;hf,
Segher
