Turn a series of extract_element's feeding a build_vector into a
vector_shuffle node. For this: void test(__m128 *res, __m128 *A, __m128 *B) { *res = _mm_unpacklo_ps(*A, *B); } we now produce this code: _test: movl 8(%esp), %eax movaps (%eax), %xmm0 movl 12(%esp), %eax unpcklps (%eax), %xmm0 movl 4(%esp), %eax movaps %xmm0, (%eax) ret instead of this: _test: subl $76, %esp movl 88(%esp), %eax movaps (%eax), %xmm0 movaps %xmm0, (%esp) movaps %xmm0, 32(%esp) movss 4(%esp), %xmm0 movss 32(%esp), %xmm1 unpcklps %xmm0, %xmm1 movl 84(%esp), %eax movaps (%eax), %xmm0 movaps %xmm0, 16(%esp) movaps %xmm0, 48(%esp) movss 20(%esp), %xmm0 movss 48(%esp), %xmm2 unpcklps %xmm0, %xmm2 unpcklps %xmm1, %xmm2 movl 80(%esp), %eax movaps %xmm2, (%eax) addl $76, %esp ret GCC produces this (with -fomit-frame-pointer): _test: subl $12, %esp movl 20(%esp), %eax movaps (%eax), %xmm0 movl 24(%esp), %eax unpcklps (%eax), %xmm0 movl 16(%esp), %eax movaps %xmm0, (%eax) addl $12, %esp ret llvm-svn: 27233
Loading
Please register or sign in to comment