llvm-project/compiler-rt/lib/builtins/arm/aeabi_cfcmp.S

145 lines
3.2 KiB
ArmAsm

//===-- aeabi_cfcmp.S - EABI cfcmp* implementation ------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "../assembly.h"
#if __BYTE_ORDER__ != __ORDER_LITTLE_ENDIAN__
#error big endian support not implemented
#endif
#define APSR_Z (1 << 30)
#define APSR_C (1 << 29)
// void __aeabi_cfcmpeq(float a, float b) {
// if (isnan(a) || isnan(b)) {
// Z = 0; C = 1;
// } else {
// __aeabi_cfcmple(a, b);
// }
// }
.syntax unified
.p2align 2
DEFINE_COMPILERRT_FUNCTION(__aeabi_cfcmpeq)
push {r0-r3, lr}
bl __aeabi_cfcmpeq_check_nan
cmp r0, #1
#if defined(USE_THUMB_1)
beq 1f
// NaN has been ruled out, so __aeabi_cfcmple can't trap
mov r0, sp
ldm r0, {r0-r3}
bl __aeabi_cfcmple
pop {r0-r3, pc}
1:
// Z = 0, C = 1
movs r0, #0xF
lsls r0, r0, #31
pop {r0-r3, pc}
#else
pop {r0-r3, lr}
// NaN has been ruled out, so __aeabi_cfcmple can't trap
// Use "it ne" + unconditional branch to guarantee a supported relocation if
// __aeabi_cfcmple is in a different section for some builds.
IT(ne)
bne __aeabi_cfcmple
#if defined(USE_THUMB_2)
mov ip, #APSR_C
msr APSR_nzcvq, ip
#else
msr CPSR_f, #APSR_C
#endif
JMP(lr)
#endif
END_COMPILERRT_FUNCTION(__aeabi_cfcmpeq)
// void __aeabi_cfcmple(float a, float b) {
// if (__aeabi_fcmplt(a, b)) {
// Z = 0; C = 0;
// } else if (__aeabi_fcmpeq(a, b)) {
// Z = 1; C = 1;
// } else {
// Z = 0; C = 1;
// }
// }
.syntax unified
.p2align 2
DEFINE_COMPILERRT_FUNCTION(__aeabi_cfcmple)
// Per the RTABI, this function must preserve r0-r11.
// Save lr in the same instruction for compactness
push {r0-r3, lr}
bl __aeabi_fcmplt
cmp r0, #1
#if defined(USE_THUMB_1)
bne 1f
// Z = 0, C = 0
movs r0, #1
lsls r0, r0, #1
pop {r0-r3, pc}
1:
mov r0, sp
ldm r0, {r0-r3}
bl __aeabi_fcmpeq
cmp r0, #1
bne 2f
// Z = 1, C = 1
movs r0, #2
lsls r0, r0, #31
pop {r0-r3, pc}
2:
// Z = 0, C = 1
movs r0, #0xF
lsls r0, r0, #31
pop {r0-r3, pc}
#else
ITT(eq)
moveq ip, #0
beq 1f
ldm sp, {r0-r3}
bl __aeabi_fcmpeq
cmp r0, #1
ITE(eq)
moveq ip, #(APSR_C | APSR_Z)
movne ip, #(APSR_C)
1:
#if defined(__ARM_ARCH_7M__) || defined(__ARM_ARCH_7EM__)
msr APSR_nzcvq, ip
#else
msr CPSR_f, ip
#endif
pop {r0-r3}
POP_PC()
#endif
END_COMPILERRT_FUNCTION(__aeabi_cfcmple)
// int __aeabi_cfrcmple(float a, float b) {
// return __aeabi_cfcmple(b, a);
// }
.syntax unified
.p2align 2
DEFINE_COMPILERRT_FUNCTION(__aeabi_cfrcmple)
// Swap r0 and r1
mov ip, r0
mov r0, r1
mov r1, ip
b __aeabi_cfcmple
END_COMPILERRT_FUNCTION(__aeabi_cfrcmple)
NO_EXEC_STACK_DIRECTIVE