[Bug tree-optimization/97081] wrong code for rotate vectorization (x86 target)

[igor at tachyum dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97081

--- Comment #1 from Igor Shevlyakov  ---
vect_recog_rotate_pattern()

seems to be the culprit

[Bug tree-optimization/97081] New: wrong code for rotate vectorization (x86 target)

[igor at tachyum dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97081

Bug ID: 97081
   Summary: wrong code for rotate vectorization (x86 target)
   Product: gcc
   Version: 10.2.0
Status: UNCONFIRMED
  Severity: normal
  Priority: P3
 Component: tree-optimization
  Assignee: unassigned at gcc dot gnu.org
  Reporter: igor at tachyum dot com
  Target Milestone: ---

Created attachment 49231
  --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=49231=edit
testcase

incorrectly calculates left shift amount when breaking (a r>> sh) into (a <<
sh_l) | (a >> sh_r)

shr is calculated as (-sh & 31) while should be (-sh & 63)


.file   "t.c"
.text
.p2align 4
.globl  exec_VRORudi_i
.type   exec_VRORudi_i, @function
exec_VRORudi_i:
.LFB0:
.cfi_startproc
endbr64
andl$63, %edx
movdqu  (%rsi), %xmm1
movl%edx, %eax
movd%edx, %xmm0
negl%eax
movdqa  %xmm1, %xmm3
movl%eax, %ecx
psrlq   %xmm0, %xmm3
andl$31, %ecx
movq%rcx, %xmm2
psllq   %xmm2, %xmm1
por %xmm3, %xmm1
movups  %xmm1, (%rdi)
movdqu  16(%rsi), %xmm1
movdqa  %xmm1, %xmm3
psrlq   %xmm0, %xmm1
psllq   %xmm2, %xmm3
por %xmm3, %xmm1
movups  %xmm1, 16(%rdi)
ret
.cfi_endproc