blob: 896633e85d35ddc1f62d84d77e152e675f2bbc4e [file] [log] [blame]
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#include "../assembly.h"
// di_int __lshrdi3(di_int input, int count);
// This routine has some extra memory traffic, loading the 64-bit input via two
// 32-bit loads, then immediately storing it back to the stack via a single 64-bit
// store. This is to avoid a write-small, read-large stall.
// However, if callers of this routine can be safely assumed to store the argument
// via a 64-bt store, this is unnecessary memory traffic, and should be avoided.
// It can be turned off by defining the TRUST_CALLERS_USE_64_BIT_STORES macro.
#ifdef __i386__
#ifdef __SSE2__
.balign 4
movd 12(%esp), %xmm2 // Load count
movd 4(%esp), %xmm0
movd 8(%esp), %xmm1
punpckldq %xmm1, %xmm0 // Load input
movq 4(%esp), %xmm0 // Load input
psrlq %xmm2, %xmm0 // shift input by count
movd %xmm0, %eax
psrlq $32, %xmm0
movd %xmm0, %edx
#else // Use GPRs instead of SSE2 instructions, if they aren't available.
.balign 4
movl 12(%esp), %ecx // Load count
movl 8(%esp), %edx // Load high
movl 4(%esp), %eax // Load low
testl $0x20, %ecx // If count >= 32
jnz 1f // goto 1
shrdl %cl, %edx, %eax // right shift low by count
shrl %cl, %edx // right shift high by count
1: movl %edx, %eax // Move high to low
xorl %edx, %edx // clear high
shrl %cl, %eax // shift low by count - 32
#endif // __SSE2__
#endif // __i386__