search for: mem_2

...2 ## xmm2 = xmm4[3],xmm2[1,2,3] > > Note that the second version does the shuffle in-place, in xmm2. > > > Some are blends (har har) of those two: > vpermilps $-0x6d, %xmm_mem_1, %xmm6 ## xmm6 = xmm_mem_1[3,0,1,2] > vpermilps $-0x6d, -0xXX(%rax), %xmm1 ## xmm1 = mem_2[3,0,1,2] > vblendps $0x1, %xmm1, %xmm6, %xmm0 ## xmm0 = xmm1[0],xmm6[1,2,3] > becomes: > vmovaps -0xXX(%rax), %xmm0 ## %xmm0 = mem_2[0,1,2,3] > vpermilps $-0x6d, %xmm0, %xmm1 ## xmm1 = xmm0[3,0,1,2] > vshufps $0x3, %xmm_mem_1, %xmm0, %xmm0 ## xmm0...

...; Note that the second version does the shuffle in-place, in xmm2. >>> >>> >>> Some are blends (har har) of those two: >>> vpermilps $-0x6d, %xmm_mem_1, %xmm6 ## xmm6 = xmm_mem_1[3,0,1,2] >>> vpermilps $-0x6d, -0xXX(%rax), %xmm1 ## xmm1 = mem_2[3,0,1,2] >>> vblendps $0x1, %xmm1, %xmm6, %xmm0 ## xmm0 = xmm1[0],xmm6[1,2,3] >>> becomes: >>> vmovaps -0xXX(%rax), %xmm0 ## %xmm0 = mem_2[0,1,2,3] >>> vpermilps $-0x6d, %xmm0, %xmm1 ## xmm1 = xmm0[3,0,1,2] >>> vshufps...

...,3] >> >> Note that the second version does the shuffle in-place, in xmm2. >> >> >> Some are blends (har har) of those two: >> vpermilps $-0x6d, %xmm_mem_1, %xmm6 ## xmm6 = xmm_mem_1[3,0,1,2] >> vpermilps $-0x6d, -0xXX(%rax), %xmm1 ## xmm1 = mem_2[3,0,1,2] >> vblendps $0x1, %xmm1, %xmm6, %xmm0 ## xmm0 = xmm1[0],xmm6[1,2,3] >> becomes: >> vmovaps -0xXX(%rax), %xmm0 ## %xmm0 = mem_2[0,1,2,3] >> vpermilps $-0x6d, %xmm0, %xmm1 ## xmm1 = xmm0[3,0,1,2] >> vshufps $0x3, %xmm_mem_1,...

...nd version does the shuffle in-place, in xmm2. >>>> >>>> >>>> Some are blends (har har) of those two: >>>> vpermilps $-0x6d, %xmm_mem_1, %xmm6 ## xmm6 = xmm_mem_1[3,0,1,2] >>>> vpermilps $-0x6d, -0xXX(%rax), %xmm1 ## xmm1 = mem_2[3,0,1,2] >>>> vblendps $0x1, %xmm1, %xmm6, %xmm0 ## xmm0 = >>>> xmm1[0],xmm6[1,2,3] >>>> becomes: >>>> vmovaps -0xXX(%rax), %xmm0 ## %xmm0 = mem_2[0,1,2,3] >>>> vpermilps $-0x6d, %xmm0, %xmm1 ## xmm1 = xmm0[3,0,1...

Greetings LLVM hackers and x86 vector shufflers! I would like to flip on another chunk of the new vector shuffling, specifically the logic to mark ~all shuffles as "legal". This can be tested today with the flag "-x86-experimental-vector-shuffle-legality". I would essentially like to make this the default (by removing the "false" path). Doing this will allow me to

Thanks a lot for answering. Before I get into it, please note that everything below bears the big capture "Thanks for trying to help me at all". 1) Yeah, those examples - quite hard to satisfy everyone's needs ;-) While the one side complained that my past examples regarding this issue were not informative enough, others didn't like the more elaborated version (as seems to be