llvm/compiler-rt/lib/builtins/i386/ashldi3.S
Chandler Carruth 57b08b0944 Update more file headers across all of the LLVM projects in the monorepo
to reflect the new license. These used slightly different spellings that
defeated my regular expressions.

We understand that people may be surprised that we're moving the header
entirely to discuss the new license. We checked this carefully with the
Foundation's lawyer and we believe this is the correct approach.

Essentially, all code in the project is now made available by the LLVM
project under our new license, so you will see that the license headers
include that license only. Some of our contributors have contributed
code under our old license, and accordingly, we have retained a copy of
our old license notice in the top-level files in each project and
repository.

llvm-svn: 351648
2019-01-19 10:56:40 +00:00

63 lines
1.8 KiB
ArmAsm

// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#include "../assembly.h"
// di_int __ashldi3(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__
.text
.balign 4
DEFINE_COMPILERRT_FUNCTION(__ashldi3)
movd 12(%esp), %xmm2 // Load count
#ifndef TRUST_CALLERS_USE_64_BIT_STORES
movd 4(%esp), %xmm0
movd 8(%esp), %xmm1
punpckldq %xmm1, %xmm0 // Load input
#else
movq 4(%esp), %xmm0 // Load input
#endif
psllq %xmm2, %xmm0 // shift input by count
movd %xmm0, %eax
psrlq $32, %xmm0
movd %xmm0, %edx
ret
END_COMPILERRT_FUNCTION(__ashldi3)
#else // Use GPRs instead of SSE2 instructions, if they aren't available.
.text
.balign 4
DEFINE_COMPILERRT_FUNCTION(__ashldi3)
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
shldl %cl, %eax, %edx // left shift high by count
shll %cl, %eax // left shift low by count
ret
1: movl %eax, %edx // Move low to high
xorl %eax, %eax // clear low
shll %cl, %edx // shift high by count - 32
ret
END_COMPILERRT_FUNCTION(__ashldi3)
#endif // __SSE2__
#endif // __i386__
NO_EXEC_STACK_DIRECTIVE