Finish implementing a readme entry: when inserting an i64 variable
authorChris Lattner <sabre@nondot.org>
Sun, 9 Mar 2008 05:42:06 +0000 (05:42 +0000)
committerChris Lattner <sabre@nondot.org>
Sun, 9 Mar 2008 05:42:06 +0000 (05:42 +0000)
commit67f453aae7ac55f30af9e961a21029beabaaf47b
tree7a7fd9ea19992b97cc52890188a1cdab8940c738
parent529de8a45702cd34968d79d13f95ed1e5d5fa250
Finish implementing a readme entry: when inserting an i64 variable
into a vector of zeros or undef, and when the top part is obviously
zero, we can just use movd + shuffle.  This allows us to compile
vec_set-B.ll into:

_test3:
movl $1234567, %eax
andl 4(%esp), %eax
movd %eax, %xmm0
ret

instead of:

_test3:
subl $28, %esp
movl $1234567, %eax
andl 32(%esp), %eax
movl %eax, (%esp)
movl $0, 4(%esp)
movq (%esp), %xmm0
addl $28, %esp
ret

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48090 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/X86/README-SSE.txt
lib/Target/X86/X86ISelLowering.cpp
test/CodeGen/X86/vec_set-B.ll [new file with mode: 0644]