summaryrefslogtreecommitdiff
path: root/gcc/config/aarch64/arm_neon.h
Commit message (Expand)AuthorAgeFilesLines
* [AArch64] Add __extension__ and __always_inline__ to crypto intrinsicsKyrylo Tkachov2015-05-221-16/+18
* [AArch64] Idiomatic 64x1 comparisons in arm_neon.hAlan Lawrence2015-05-081-18/+18
* arm_neon.h (vdup_n_f32): Remove forward declaration.Alan Lawrence2015-04-171-2/+0
* [AArch64 Intrinsics] Replace temporary assembler for vst1_laneAlan Lawrence2015-04-141-268/+150
* Fix bug 64893: ICE with vget_lane_u32 with C++ front-endAndrew Pinski2015-02-111-1/+1
* [AArch64] Use target builtin instead of __builtin_sqrt for vsqrt_f64Kyrylo Tkachov2015-02-041-1/+1
* aarch64-simd.md (aarch64_<maxmin_uns>p<mode>): New pattern.Felix Yang2015-01-191-484/+284
* [AArch64] Error out of arm_neon.h if nofp/nosimdKyrylo Tkachov2015-01-141-0/+6
* Update copyright years.Jakub Jelinek2015-01-051-1/+1
* [AArch64]Remove be_checked_get_lane, check bounds with __builtin_aarch64_im_l...Alan Lawrence2014-12-091-266/+177
* [AArch64] Fix ICE on non-constant indices to __builtin_aarch64_im_lane_boundsiAlan Lawrence2014-12-091-33/+34
* [AArch64]Fix ICE at -O0 on vld1_lane intrinsicsAlan Lawrence2014-12-091-184/+187
* arm_neon.h (vrecpe_u32, [...]): Rewrite using builtin functions.Felix Yang2014-12-081-516/+307
* aarch64-simd.md (clrsb<mode>2, [...]): New patterns.Felix Yang2014-12-071-132/+76
* [AArch64] Implement vsqrt_f64 intrinsicKyrylo Tkachov2014-11-211-0/+6
* [AArch64]Replace temporary assembler for vld1_dupAlan Lawrence2014-11-181-264/+148
* [AArch64] Extend aarch64_simd_vec_set pattern, replace asm for vld1_laneAlan Lawrence2014-11-171-313/+149
* aarch64-builtins.c (TYPES_CREATE): Remove.Alan Lawrence2014-11-171-3/+3
* [AArch64] Restructure arm_neon.h vector types.Tejas Belagod2014-11-051-54/+30
* [AArch64] Use new reduc_[us](min|max)_scal optabs, inc. for builtinsAlan Lawrence2014-10-271-68/+36
* [AArch64] Use new reduc_plus_scal optabs, inc. for __builtinsAlan Lawrence2014-10-271-36/+18
* [PATCH 2/2] [AARCH64,NEON] Convert arm_neon.h to use new builtins for vld[234...Charles Baylis2014-10-241-125/+281
* re PR target/63173 (performance problem with simd intrinsics vld2_dup_* on aa...Felix Yang2014-10-241-120/+866
* [AArch64] Wire up vqdmullh_laneq_s16 and vqdmullh_laneq_s32James Greenhalgh2014-09-301-2/+14
* [AArch64] Use __aarch64_vget_lane* macros for getting the lane in some lane m...Kyrylo Tkachov2014-09-241-4/+4
* [AArch64] Simplify vreinterpret for float64x1_t using casts.Alan Lawrence2014-09-111-20/+20
* [AArch64] Replace temporary inline assembler for vset_laneAlan Lawrence2014-09-111-312/+168
* [AArch64] Cheap fix for argument types of vmull_high_lane_{us}{16,32}James Greenhalgh2014-09-111-4/+4
* [PATCH AArch64] Rename [u]int32x1_t to [u]int32_t (resp 16x1, 8x1) in arm_neon.hAlan Lawrence2014-09-051-223/+217
* [PATCH AArch64 2/2] Replace temporary inline assembler for vget_highAlan Lawrence2014-09-051-132/+79
* [PATCH AArch64 2/2] Remove vector compare/tst __builtinsAlan Lawrence2014-09-051-279/+160
* [PATCH AArch64] Add a builtin for rbit(q?)_p8; add intrinsics and tests.Alan Lawrence2014-09-051-44/+38
* [AArch64] Fix types for vqdmlals_lane_s32 and vqdmlsls_lane_s32 intrinsics.Kyrylo Tkachov2014-08-051-7/+6
* [AArch64] Implement some saturating math NEON intrinsics.Kyrylo Tkachov2014-08-051-0/+48
* [AArch64] Implement some vmul*_lane*_f* intrinsics in arm_neon.h.Kyrylo Tkachov2014-08-051-26/+42
* [AArch64] arm_neon.h - add vpaddd_f64, vpaddd_s64, vpaddd_u64 intrinsicsJames Greenhalgh2014-07-311-56/+59
* [AArch64] Implement vbsl_f64 arm_neon.h intrinsic.Kyrylo Tkachov2014-07-221-0/+7
* [AArch64] Implement vfma_f64, vmla_f64, vfms_f64, vmls_f64 intrinsics.Kyrylo Tkachov2014-07-171-0/+28
* [AArch64] Fix argument types for some high_lane* intrinsics implemented in as...Kyrylo Tkachov2014-07-171-8/+8
* [AArch64] Implement some vca*_f[32,64] intrinsics.Kyrylo Tkachov2014-07-011-0/+48
* PR/60825 Make {int,uint}64x1_t in arm_neon.h a proper vector typeAlan Lawrence2014-06-231-226/+240
* PR/60825 Make float64x1_t in arm_neon.h a proper vector typeAlan Lawrence2014-06-231-79/+90
* [AArch64] Fix some saturating math NEON intrinsics types.Kyrylo Tkachov2014-06-201-28/+22
* [AArch64] Remove from arm_neon.h functions not in the specAlan Lawrence2014-06-121-315/+0
* [PATCH AArch64 2/2] Correct signedness of builtins, remove casts from arm_neon.hAlan Lawrence2014-06-031-51/+51
* [PATCH AArch64 1/2] Correct signedness of builtins, remove casts from arm_neon.hAlan Lawrence2014-06-031-187/+136
* Recognize shuffle patterns for REV instructions on AArch64, rewrite intrinsics.Alan Lawrence2014-06-031-396/+228
* Detect EXT patterns to vec_perm_const, use for EXT intrinsicsAlan Lawrence2014-05-291-312/+286
* arm_neon.h (vqdmulh_n_s16): Change the last operand's constraint.Guozhi Wei2014-05-211-2/+2
* Reimplement AArch64 TRN intrinsics with __builtin_shuffle.Alan Lawrence2014-05-071-462/+432