mirror of
https://sourceware.org/git/glibc.git
synced 2025-12-24 17:51:17 +03:00
1fa5773eb1
Compiler inlines trunc and truncf with SSE4.1. But older versions of GCC doesn't inline them with -Os: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=121861 Don't use asm statement for trunc and truncf if compiler can inline them with -Os. It removes one register move with GCC 16: __modff_sse41: __modff_sse41: .LFB23: .LFB23: .cfi_startproc .cfi_startproc endbr64 endbr64 subq $24, %rsp subq $24, %rsp .cfi_def_cfa_offset 32 .cfi_def_cfa_offset 32 movq %fs:40, %rax movq %fs:40, %rax movq %rax, 8(%rsp) movq %rax, 8(%rsp) xorl %eax, %eax xorl %eax, %eax movd %xmm0, %eax movd %xmm0, %eax addl %eax, %eax addl %eax, %eax cmpl $-16777216, %eax cmpl $-16777216, %eax je .L7 je .L7 > movaps %xmm0, %xmm3 movaps %xmm0, %xmm4 movaps %xmm0, %xmm4 movss .LC0(%rip), %xmm2 | movss .LC0(%rip), %xmm1 movaps %xmm2, %xmm3 | movaps %xmm1, %xmm2 andps %xmm0, %xmm2 | roundss $11, %xmm3, %xmm3 roundss $11, %xmm0, %xmm1 | subss %xmm3, %xmm4 subss %xmm1, %xmm4 | andps %xmm0, %xmm1 andnps %xmm4, %xmm3 | andnps %xmm4, %xmm2 orps %xmm3, %xmm2 | orps %xmm2, %xmm1 .L3: .L3: movss %xmm1, (%rdi) | movss %xmm3, (%rdi) movq 8(%rsp), %rax movq 8(%rsp), %rax subq %fs:40, %rax subq %fs:40, %rax jne .L8 jne .L8 movaps %xmm2, %xmm0 | movaps %xmm1, %xmm0 addq $24, %rsp addq $24, %rsp .cfi_remember_state .cfi_remember_state .cfi_def_cfa_offset 8 .cfi_def_cfa_offset 8 ret ret Signed-off-by: H.J. Lu <hjl.tools@gmail.com> Reviewed-by: Uros Bizjak <ubizjak@gmail.com>