mirrors-yuzu-emu/unicorn
1
0
Fork 0
mirror of https://github.com/yuzu-emu/unicorn synced 2024-11-25 17:55:28 +00:00
Code Issues Projects Releases Packages Wiki Activity
unicorn/qemu/target/arm/helper-a64.h

76 lines
4.1 KiB
C
Raw Normal View History

import
2015-08-21 07:04:50 +00:00
/*
* AArch64 specific helper definitions
*
* Copyright (c) 2013 Alexander Graf <agraf@suse.de>
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
DEF_HELPER_FLAGS_2(udiv64, TCG_CALL_NO_RWG_SE, i64, i64, i64)
DEF_HELPER_FLAGS_2(sdiv64, TCG_CALL_NO_RWG_SE, s64, s64, s64)
DEF_HELPER_FLAGS_1(rbit64, TCG_CALL_NO_RWG_SE, i64, i64)
DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, ptr)
DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, ptr)
DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, ptr)
DEF_HELPER_3(vfp_cmped_a64, i64, f64, f64, ptr)
DEF_HELPER_FLAGS_5(simd_tbl, TCG_CALL_NO_RWG_SE, i64, env, i64, i64, i32, i32)
DEF_HELPER_FLAGS_3(vfp_mulxs, TCG_CALL_NO_RWG, f32, f32, f32, ptr)
DEF_HELPER_FLAGS_3(vfp_mulxd, TCG_CALL_NO_RWG, f64, f64, f64, ptr)
DEF_HELPER_FLAGS_3(neon_ceq_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
DEF_HELPER_FLAGS_3(neon_cge_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
DEF_HELPER_FLAGS_3(neon_cgt_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
arm/translate-a64: add FP16 FR[ECP/SQRT]S to simd_three_reg_same_fp16 As some of the constants here will also be needed elsewhere (specifically for the upcoming SVE support) we move them out to softfloat.h. Backports commit 026e2d6ef74000afb9049f46add4b94f594c8fb3 from qemu
2018-03-08 20:44:29 +00:00
DEF_HELPER_FLAGS_3(recpsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
import
2015-08-21 07:04:50 +00:00
DEF_HELPER_FLAGS_3(recpsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr)
DEF_HELPER_FLAGS_3(recpsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr)
arm/translate-a64: add FP16 FR[ECP/SQRT]S to simd_three_reg_same_fp16 As some of the constants here will also be needed elsewhere (specifically for the upcoming SVE support) we move them out to softfloat.h. Backports commit 026e2d6ef74000afb9049f46add4b94f594c8fb3 from qemu
2018-03-08 20:44:29 +00:00
DEF_HELPER_FLAGS_3(rsqrtsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
import
2015-08-21 07:04:50 +00:00
DEF_HELPER_FLAGS_3(rsqrtsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr)
DEF_HELPER_FLAGS_3(rsqrtsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr)
DEF_HELPER_FLAGS_1(neon_addlp_s8, TCG_CALL_NO_RWG_SE, i64, i64)
DEF_HELPER_FLAGS_1(neon_addlp_u8, TCG_CALL_NO_RWG_SE, i64, i64)
DEF_HELPER_FLAGS_1(neon_addlp_s16, TCG_CALL_NO_RWG_SE, i64, i64)
DEF_HELPER_FLAGS_1(neon_addlp_u16, TCG_CALL_NO_RWG_SE, i64, i64)
DEF_HELPER_FLAGS_2(frecpx_f64, TCG_CALL_NO_RWG, f64, f64, ptr)
DEF_HELPER_FLAGS_2(frecpx_f32, TCG_CALL_NO_RWG, f32, f32, ptr)
DEF_HELPER_FLAGS_2(fcvtx_f64_to_f32, TCG_CALL_NO_RWG, f32, f64, env)
DEF_HELPER_FLAGS_3(crc32_64, TCG_CALL_NO_RWG_SE, i64, i64, i64, i32)
DEF_HELPER_FLAGS_3(crc32c_64, TCG_CALL_NO_RWG_SE, i64, i64, i64, i32)
target-arm: emulate aarch64's LL/SC using cmpxchg helpers Emulating LL/SC with cmpxchg is not correct, since it can suffer from the ABA problem. Portable parallel code, however, is written assuming only cmpxchg--and not LL/SC--is available. This means that in practice emulating LL/SC with cmpxchg is a viable alternative. The appended emulates LL/SC pairs in aarch64 with cmpxchg helpers. This works in both user and system mode. In usermode, it avoids pausing all other CPUs to perform the LL/SC pair. The subsequent performance and scalability improvement is significant, as the plots below show. They plot the throughput of atomic_add-bench compiled for ARM and executed on a 64-core x86 machine. Hi-res plots: http://imgur.com/a/JVc8Y atomic_add-bench: 1000000 ops/thread, [0,1] range 18 ++---------+----------+---------+----------+----------+----------+---++ +cmpxchg +-E--+ + + + + + | 16 ++master +-H--+ ++ || | 14 ++ ++ | | | 12 ++| ++ | | | 10 ++++ ++ 8 ++E ++ |+++ | 6 ++ | ++ | | | 4 ++ | ++ | | | 2 +H++E+--- ++ + | +E++----+E+---+--+E+----++E+------+E+------+E++----+E+---+--+E| 0 ++H-H----H-+-----H----+---------+----------+----------+----------+---++ 0 10 20 30 40 50 60 Number of threads atomic_add-bench: 1000000 ops/thread, [0,2] range 18 ++---------+----------+---------+----------+----------+----------+---++ +cmpxchg +-E--+ + + + + + | 16 ++master +-H--+ ++ | | | 14 ++E ++ | | | 12 ++| ++ |+++ | 10 ++ | ++ 8 ++ | ++ | | | 6 ++ | ++ | | | 4 ++ | ++ | +E+--- | 2 +H+ +E+-----+++ +++ +++ ---+E+-----+E+------+++ +++ + +E+---+--+E+----++E+------+E+--- ++++ +++ + +E| 0 ++H-H----H-+-----H----+---------+----------+----------+----------+---++ 0 10 20 30 40 50 60 Number of threads atomic_add-bench: 1000000 ops/thread, [0,128] range 70 ++---------+----------+---------+----------+----------+----------+---++ +cmpxchg +-E--+ + + + + + | 60 ++master +-H--+ +++ ---+E+-----+E+------+E+ | +E+------E-------+E+--- | | --- +++ | 50 ++ +++--- ++ | -+E+ | 40 ++ +++---- ++ | E- | | --| | 30 ++ -- +++ ++ | +E+ | 20 ++E+ ++ |E+ | | | 10 ++ ++ + + + + + + + | 0 +HH-H----H-+-----H----+---------+----------+----------+----------+---++ 0 10 20 30 40 50 60 Number of threads atomic_add-bench: 1000000 ops/thread, [0,1024] range 160 ++---------+---------+----------+---------+----------+----------+---++ +cmpxchg +-E--+ + + + + + | 140 ++master +-H--+ +++ +++ | -+E+-----+E+-------E| 120 ++ +++ ---- +++ | +++ ----E-- | 100 ++ --E--- +++ ++ | +++ ---- +++ | 80 ++ --E-- ++ | ---- +++ | | -+E+ | 60 ++ ---- +++ ++ | +E+- | 40 ++ -- ++ | +E+ | 20 +EE+ ++ +++ + + + + + + | 0 +HH-H---H--+-----H---+----------+---------+----------+----------+---++ 0 10 20 30 40 50 60 Number of threads Backports commit 1dd089d0eec060dcd8478735114d98421d414805 from qemu
2018-02-28 05:13:19 +00:00
DEF_HELPER_FLAGS_4(paired_cmpxchg64_le, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
DEF_HELPER_FLAGS_4(paired_cmpxchg64_be, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
arm/translate-a64: implement half-precision F(MIN|MAX)(V|NMV) This implements the half-precision variants of the across vector reduction operations. This involves a re-factor of the reduction code which more closely matches the ARM ARM order (and handles 8 element reductions). Backports commit 807cdd504283c11addcd7ea95ba594bbddc86fe4 from qemu
2018-03-08 17:49:26 +00:00
DEF_HELPER_FLAGS_3(advsimd_maxh, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
DEF_HELPER_FLAGS_3(advsimd_minh, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
DEF_HELPER_FLAGS_3(advsimd_maxnumh, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
DEF_HELPER_FLAGS_3(advsimd_minnumh, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
arm/translate-a64: add FP16 FADD/FABD/FSUB/FMUL/FDIV to simd_three_reg_same_fp16 The fprintf is only there for debugging as the skeleton is added to, it will be removed once the skeleton is complete. Backports commit 372087348d561e7f4051d7b32609bda417092ddf from qemu
2018-03-08 17:54:44 +00:00
DEF_HELPER_3(advsimd_addh, f16, f16, f16, ptr)
DEF_HELPER_3(advsimd_subh, f16, f16, f16, ptr)
DEF_HELPER_3(advsimd_mulh, f16, f16, f16, ptr)
DEF_HELPER_3(advsimd_divh, f16, f16, f16, ptr)
arm/translate-a64: add FP16 F[A]C[EQ/GE/GT] to simd_three_reg_same_fp16 These use the generic float16_compare functionality which in turn uses the common float_compare code from the softfloat re-factor. Backports commit d32adeae1a71a8e71374fa48d3d6ab0ad4c23e94 from qemu
2018-03-08 17:59:06 +00:00
DEF_HELPER_3(advsimd_ceq_f16, i32, f16, f16, ptr)
DEF_HELPER_3(advsimd_cge_f16, i32, f16, f16, ptr)
DEF_HELPER_3(advsimd_cgt_f16, i32, f16, f16, ptr)
DEF_HELPER_3(advsimd_acge_f16, i32, f16, f16, ptr)
DEF_HELPER_3(advsimd_acgt_f16, i32, f16, f16, ptr)
arm/translate-a64: add FP16 FMULA/X/S to simd_three_reg_same_fp16 Backports commit 2deb992b767d28035fac3b374c7730494ff0b43d from qemu Also backports the fp16 changes introduced in commit f566c0474a9b9bbd9ed248607e4007e24d3358c0
2018-03-08 20:36:50 +00:00
DEF_HELPER_3(advsimd_mulxh, f16, f16, f16, ptr)
DEF_HELPER_4(advsimd_muladdh, f16, f16, f16, f16, ptr)
arm/translate-a64: add FP16 x2 ops for simd_indexed A bunch of the vectorised bitwise operations just operate on larger chunks at a time. We can do the same for the new half-precision operations by introducing some TWOHALFOP helpers which work on each half of a pair of half-precision operations at once. Hopefully all this hoop jumping will get simpler once we have generically vectorised helpers here. Backports commit 6089030c7322d8f96b54fb9904e53b0f464bb8fe from qemu
2018-03-08 23:06:25 +00:00
DEF_HELPER_3(advsimd_add2h, i32, i32, i32, ptr)
DEF_HELPER_3(advsimd_sub2h, i32, i32, i32, ptr)
DEF_HELPER_3(advsimd_mul2h, i32, i32, i32, ptr)
DEF_HELPER_3(advsimd_div2h, i32, i32, i32, ptr)
DEF_HELPER_3(advsimd_max2h, i32, i32, i32, ptr)
DEF_HELPER_3(advsimd_min2h, i32, i32, i32, ptr)
DEF_HELPER_3(advsimd_maxnum2h, i32, i32, i32, ptr)
DEF_HELPER_3(advsimd_minnum2h, i32, i32, i32, ptr)
DEF_HELPER_3(advsimd_mulx2h, i32, i32, i32, ptr)
DEF_HELPER_4(advsimd_muladd2h, i32, i32, i32, i32, ptr)
arm/translate-a64: add FP16 FPRINTx to simd_two_reg_misc_fp16 This adds the full range of half-precision floating point to integral instructions. Backports commit 6109aea2d954891027acba64a13f1f1c7463cfac from qemu
2018-03-08 23:20:37 +00:00
DEF_HELPER_2(advsimd_rinth_exact, f16, f16, ptr)
DEF_HELPER_2(advsimd_rinth, f16, f16, ptr)
Reference in a new issue Copy permalink