Skip to content
Commit 4ca9cbb1 authored by Chris Lattner's avatar Chris Lattner
Browse files

Eliminate useless insertelement instructions. This implements

Transforms/InstCombine/vec_insertelt.ll and fixes PR1286.

We now compile the code from that bug into:

_foo:
        movl 4(%esp), %eax
        movdqa (%eax), %xmm0
        movl 8(%esp), %ecx
        psllw (%ecx), %xmm0
        movdqa %xmm0, (%eax)
        ret

instead of:

_foo:
        subl $4, %esp
        movl %ebp, (%esp)
        movl %esp, %ebp
        movl 12(%ebp), %eax
        movdqa (%eax), %xmm0
        #IMPLICIT_DEF %eax
        pinsrw $2, %eax, %xmm0
        xorl %ecx, %ecx
        pinsrw $3, %ecx, %xmm0
        pinsrw $4, %eax, %xmm0
        pinsrw $5, %ecx, %xmm0
        pinsrw $6, %eax, %xmm0
        pinsrw $7, %ecx, %xmm0
        movl 8(%ebp), %eax
        movdqa (%eax), %xmm1
        psllw %xmm0, %xmm1
        movdqa %xmm1, (%eax)
        movl %ebp, %esp
        popl %ebp
        ret

woo :)

llvm-svn: 35788
parent 418bf4eb
Loading
Loading
Loading
Loading
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment