mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-02-06 06:33:24 +00:00
ba05f728b5
movd always clear the top 96 bits and movss does so when it's loading the
value from memory.
The net result is codegen for 4-wide shuffles is much improved. It is near
optimal if one or more elements is a zero. e.g.
__m128i test(int a, int b) {
return _mm_set_epi32(0, 0, b, a);
}
compiles to
_test:
movd 8(%esp), %xmm1
movd 4(%esp), %xmm0
punpckldq %xmm1, %xmm0
ret
compare to gcc:
_test:
subl $12, %esp
movd 20(%esp), %xmm0
movd 16(%esp), %xmm1
punpckldq %xmm0, %xmm1
movq %xmm1, %xmm0
movhps LC0, %xmm0
addl $12, %esp
ret
or icc:
_test:
movd 4(%esp), %xmm0 #5.10
movd 8(%esp), %xmm3 #5.10
xorl %eax, %eax #5.10
movd %eax, %xmm1 #5.10
punpckldq %xmm1, %xmm0 #5.10
movd %eax, %xmm2 #5.10
punpckldq %xmm2, %xmm3 #5.10
punpckldq %xmm3, %xmm0 #5.10
ret #5.10
There are still room for improvement, for example the FP variant of the above example:
__m128 test(float a, float b) {
return _mm_set_ps(0.0, 0.0, b, a);
}
_test:
movss 8(%esp), %xmm1
movss 4(%esp), %xmm0
unpcklps %xmm1, %xmm0
xorps %xmm1, %xmm1
movlhps %xmm1, %xmm0
ret
The xorps and movlhps are unnecessary. This will require post legalizer optimization to handle.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27939 91177308-0d34-0410-b5e6-96231b3b80d8