mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-02-19 06:31:18 +00:00
1596373671
The current patch optimizes frequently used shuffle patterns and gives these instruction sequence reduction.
Before:
vshufps $-35, %xmm1, %xmm0, %xmm2 ## xmm2 = xmm0[1,3],xmm1[1,3]
vpermilps $-40, %xmm2, %xmm2 ## xmm2 = xmm2[0,2,1,3]
vextractf128 $1, %ymm1, %xmm1
vextractf128 $1, %ymm0, %xmm0
vshufps $-35, %xmm1, %xmm0, %xmm0 ## xmm0 = xmm0[1,3],xmm1[1,3]
vpermilps $-40, %xmm0, %xmm0 ## xmm0 = xmm0[0,2,1,3]
vinsertf128 $1, %xmm0, %ymm2, %ymm0
After:
vshufps $13, %ymm0, %ymm1, %ymm1 ## ymm1 = ymm1[1,3],ymm0[0,0],ymm1[5,7],ymm0[4,4]
vshufps $13, %ymm0, %ymm0, %ymm0 ## ymm0 = ymm0[1,3,0,0,5,7,4,4]
vunpcklps %ymm1, %ymm0, %ymm0 ## ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159188 91177308-0d34-0410-b5e6-96231b3b80d8