diff options
author | Alexey Samsonov <samsonov@google.com> | 2014-02-14 09:20:33 +0000 |
---|---|---|
committer | Alexey Samsonov <samsonov@google.com> | 2014-02-14 09:20:33 +0000 |
commit | 53aa4fda49f94920139300227786ac47c393f1ce (patch) | |
tree | 6d022d04ee279fe1afd89668f346e28a9e3e1559 /lib/builtins/i386/lshrdi3.S | |
parent | 6d999e478fecb10dc43f20b85385d25cc239db0a (diff) |
Move original compiler-rt functions (libgcc replacement) to lib/builtins directory
git-svn-id: https://llvm.org/svn/llvm-project/compiler-rt/trunk@201393 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/builtins/i386/lshrdi3.S')
-rw-r--r-- | lib/builtins/i386/lshrdi3.S | 59 |
1 files changed, 59 insertions, 0 deletions
diff --git a/lib/builtins/i386/lshrdi3.S b/lib/builtins/i386/lshrdi3.S new file mode 100644 index 000000000..dcfc33169 --- /dev/null +++ b/lib/builtins/i386/lshrdi3.S @@ -0,0 +1,59 @@ +// This file is dual licensed under the MIT and the University of Illinois Open +// Source Licenses. See LICENSE.TXT for details. + +#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__ + +.text +.align 4 +DEFINE_COMPILERRT_FUNCTION(__lshrdi3) + 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 + psrlq %xmm2, %xmm0 // shift input by count + movd %xmm0, %eax + psrlq $32, %xmm0 + movd %xmm0, %edx + ret +END_COMPILERRT_FUNCTION(__lshrdi3) + +#else // Use GPRs instead of SSE2 instructions, if they aren't available. + +.text +.align 4 +DEFINE_COMPILERRT_FUNCTION(__lshrdi3) + 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 + ret + +1: movl %edx, %eax // Move high to low + xorl %edx, %edx // clear high + shrl %cl, %eax // shift low by count - 32 + ret +END_COMPILERRT_FUNCTION(__lshrdi3) + +#endif // __SSE2__ +#endif // __i386__ |