From: Jonathan Wright <Jonathan.Wright@arm.com>
To: "gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
Cc: Richard Sandiford <Richard.Sandiford@arm.com>,
Kyrylo Tkachov <Kyrylo.Tkachov@arm.com>
Subject: [PATCH] aarch64: Use type-qualified builtins for USUB[LW][2] Neon intrinsics
Date: Thu, 11 Nov 2021 10:19:44 +0000 [thread overview]
Message-ID: <DB9PR08MB69591EA055BC25FA003A9ED8EB949@DB9PR08MB6959.eurprd08.prod.outlook.com> (raw)
[-- Attachment #1: Type: text/plain, Size: 1383 bytes --]
Hi,
This patch declares unsigned type-qualified builtins and uses them to
implement widening-subtract Neon intrinsics. This removes the need
for many casts in arm_neon.h.
Bootstrapped and regression tested on aarch64-none-linux-gnu - no
issues.
Ok for master?
Thanks,
Jonathan
---
gcc/ChangeLog:
2021-11-09 Jonathan Wright <jonathan.wright@arm.com>
* config/aarch64/aarch64-simd-builtins.def: Use BINOPU type
qualifiers in generator macros for usub[lw][2] builtins.
* config/aarch64/arm_neon.h (vsubl_s8): Remove unnecessary
cast.
(vsubl_s16): Likewise.
(vsubl_s32): Likewise.
(vsubl_u8): Use type-qualified builtin and remove casts.
(vsubl_u16): Likewise.
(vsubl_u32): Likewise.
(vsubl_high_s8): Remove unnecessary cast.
(vsubl_high_s16): Likewise.
(vsubl_high_s32): Likewise.
(vsubl_high_u8): Use type-qualified builtin and remove casts.
(vsubl_high_u16): Likewise.
(vsubl_high_u32): Likewise.
(vsubw_s8): Remove unnecessary casts.
(vsubw_s16): Likewise.
(vsubw_s32): Likewise.
(vsubw_u8): Use type-qualified builtin and remove casts.
(vsubw_u16): Likewise.
(vsubw_u32): Likewise.
(vsubw_high_s8): Remove unnecessary cast.
(vsubw_high_s16): Likewise.
(vsubw_high_s32): Likewise.
(vsubw_high_u8): Use type-qualified builtin and remove casts.
(vsubw_high_u16): Likewise.
(vsubw_high_u32): Likewise.
[-- Attachment #2: rb15034.patch --]
[-- Type: application/octet-stream, Size: 8871 bytes --]
diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index ccd194978f948201698aec16d74baa82c187cad4..be06a80cea379b8b78c798dbec47fb95eec68db1 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -160,21 +160,21 @@
BUILTIN_VQW (BINOP, saddl2, 0, NONE)
BUILTIN_VQW (BINOPU, uaddl2, 0, NONE)
BUILTIN_VQW (BINOP, ssubl2, 0, NONE)
- BUILTIN_VQW (BINOP, usubl2, 0, NONE)
+ BUILTIN_VQW (BINOPU, usubl2, 0, NONE)
BUILTIN_VQW (BINOP, saddw2, 0, NONE)
BUILTIN_VQW (BINOPU, uaddw2, 0, NONE)
BUILTIN_VQW (BINOP, ssubw2, 0, NONE)
- BUILTIN_VQW (BINOP, usubw2, 0, NONE)
+ BUILTIN_VQW (BINOPU, usubw2, 0, NONE)
/* Implemented by aarch64_<ANY_EXTEND:su><ADDSUB:optab>l<mode>. */
BUILTIN_VD_BHSI (BINOP, saddl, 0, NONE)
BUILTIN_VD_BHSI (BINOPU, uaddl, 0, NONE)
BUILTIN_VD_BHSI (BINOP, ssubl, 0, NONE)
- BUILTIN_VD_BHSI (BINOP, usubl, 0, NONE)
+ BUILTIN_VD_BHSI (BINOPU, usubl, 0, NONE)
/* Implemented by aarch64_<ANY_EXTEND:su><ADDSUB:optab>w<mode>. */
BUILTIN_VD_BHSI (BINOP, saddw, 0, NONE)
BUILTIN_VD_BHSI (BINOPU, uaddw, 0, NONE)
BUILTIN_VD_BHSI (BINOP, ssubw, 0, NONE)
- BUILTIN_VD_BHSI (BINOP, usubw, 0, NONE)
+ BUILTIN_VD_BHSI (BINOPU, usubw, 0, NONE)
/* Implemented by aarch64_<sur>h<addsub><mode>. */
BUILTIN_VDQ_BHSI (BINOP, shadd, 0, NONE)
BUILTIN_VDQ_BHSI (BINOP, shsub, 0, NONE)
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index a3d742f25a896f8e736a5fb01535d372cd4b20db..58b3dddb2c4ebf856de0e9cf0399e42d322beff9 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -1765,180 +1765,168 @@ __extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubl_s8 (int8x8_t __a, int8x8_t __b)
{
- return (int16x8_t) __builtin_aarch64_ssublv8qi (__a, __b);
+ return __builtin_aarch64_ssublv8qi (__a, __b);
}
__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubl_s16 (int16x4_t __a, int16x4_t __b)
{
- return (int32x4_t) __builtin_aarch64_ssublv4hi (__a, __b);
+ return __builtin_aarch64_ssublv4hi (__a, __b);
}
__extension__ extern __inline int64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubl_s32 (int32x2_t __a, int32x2_t __b)
{
- return (int64x2_t) __builtin_aarch64_ssublv2si (__a, __b);
+ return __builtin_aarch64_ssublv2si (__a, __b);
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubl_u8 (uint8x8_t __a, uint8x8_t __b)
{
- return (uint16x8_t) __builtin_aarch64_usublv8qi ((int8x8_t) __a,
- (int8x8_t) __b);
+ return __builtin_aarch64_usublv8qi_uuu (__a, __b);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubl_u16 (uint16x4_t __a, uint16x4_t __b)
{
- return (uint32x4_t) __builtin_aarch64_usublv4hi ((int16x4_t) __a,
- (int16x4_t) __b);
+ return __builtin_aarch64_usublv4hi_uuu (__a, __b);
}
__extension__ extern __inline uint64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubl_u32 (uint32x2_t __a, uint32x2_t __b)
{
- return (uint64x2_t) __builtin_aarch64_usublv2si ((int32x2_t) __a,
- (int32x2_t) __b);
+ return __builtin_aarch64_usublv2si_uuu (__a, __b);
}
__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubl_high_s8 (int8x16_t __a, int8x16_t __b)
{
- return (int16x8_t) __builtin_aarch64_ssubl2v16qi (__a, __b);
+ return __builtin_aarch64_ssubl2v16qi (__a, __b);
}
__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubl_high_s16 (int16x8_t __a, int16x8_t __b)
{
- return (int32x4_t) __builtin_aarch64_ssubl2v8hi (__a, __b);
+ return __builtin_aarch64_ssubl2v8hi (__a, __b);
}
__extension__ extern __inline int64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubl_high_s32 (int32x4_t __a, int32x4_t __b)
{
- return (int64x2_t) __builtin_aarch64_ssubl2v4si (__a, __b);
+ return __builtin_aarch64_ssubl2v4si (__a, __b);
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubl_high_u8 (uint8x16_t __a, uint8x16_t __b)
{
- return (uint16x8_t) __builtin_aarch64_usubl2v16qi ((int8x16_t) __a,
- (int8x16_t) __b);
+ return __builtin_aarch64_usubl2v16qi_uuu (__a, __b);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubl_high_u16 (uint16x8_t __a, uint16x8_t __b)
{
- return (uint32x4_t) __builtin_aarch64_usubl2v8hi ((int16x8_t) __a,
- (int16x8_t) __b);
+ return __builtin_aarch64_usubl2v8hi_uuu (__a, __b);
}
__extension__ extern __inline uint64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubl_high_u32 (uint32x4_t __a, uint32x4_t __b)
{
- return (uint64x2_t) __builtin_aarch64_usubl2v4si ((int32x4_t) __a,
- (int32x4_t) __b);
+ return __builtin_aarch64_usubl2v4si_uuu (__a, __b);
}
__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubw_s8 (int16x8_t __a, int8x8_t __b)
{
- return (int16x8_t) __builtin_aarch64_ssubwv8qi (__a, __b);
+ return __builtin_aarch64_ssubwv8qi (__a, __b);
}
__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubw_s16 (int32x4_t __a, int16x4_t __b)
{
- return (int32x4_t) __builtin_aarch64_ssubwv4hi (__a, __b);
+ return __builtin_aarch64_ssubwv4hi (__a, __b);
}
__extension__ extern __inline int64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubw_s32 (int64x2_t __a, int32x2_t __b)
{
- return (int64x2_t) __builtin_aarch64_ssubwv2si (__a, __b);
+ return __builtin_aarch64_ssubwv2si (__a, __b);
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubw_u8 (uint16x8_t __a, uint8x8_t __b)
{
- return (uint16x8_t) __builtin_aarch64_usubwv8qi ((int16x8_t) __a,
- (int8x8_t) __b);
+ return __builtin_aarch64_usubwv8qi_uuu (__a, __b);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubw_u16 (uint32x4_t __a, uint16x4_t __b)
{
- return (uint32x4_t) __builtin_aarch64_usubwv4hi ((int32x4_t) __a,
- (int16x4_t) __b);
+ return __builtin_aarch64_usubwv4hi_uuu (__a, __b);
}
__extension__ extern __inline uint64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubw_u32 (uint64x2_t __a, uint32x2_t __b)
{
- return (uint64x2_t) __builtin_aarch64_usubwv2si ((int64x2_t) __a,
- (int32x2_t) __b);
+ return __builtin_aarch64_usubwv2si_uuu (__a, __b);
}
__extension__ extern __inline int16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubw_high_s8 (int16x8_t __a, int8x16_t __b)
{
- return (int16x8_t) __builtin_aarch64_ssubw2v16qi (__a, __b);
+ return __builtin_aarch64_ssubw2v16qi (__a, __b);
}
__extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubw_high_s16 (int32x4_t __a, int16x8_t __b)
{
- return (int32x4_t) __builtin_aarch64_ssubw2v8hi (__a, __b);
+ return __builtin_aarch64_ssubw2v8hi (__a, __b);
}
__extension__ extern __inline int64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubw_high_s32 (int64x2_t __a, int32x4_t __b)
{
- return (int64x2_t) __builtin_aarch64_ssubw2v4si (__a, __b);
+ return __builtin_aarch64_ssubw2v4si (__a, __b);
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubw_high_u8 (uint16x8_t __a, uint8x16_t __b)
{
- return (uint16x8_t) __builtin_aarch64_usubw2v16qi ((int16x8_t) __a,
- (int8x16_t) __b);
+ return __builtin_aarch64_usubw2v16qi_uuu (__a, __b);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubw_high_u16 (uint32x4_t __a, uint16x8_t __b)
{
- return (uint32x4_t) __builtin_aarch64_usubw2v8hi ((int32x4_t) __a,
- (int16x8_t) __b);
+ return __builtin_aarch64_usubw2v8hi_uuu (__a, __b);
}
__extension__ extern __inline uint64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vsubw_high_u32 (uint64x2_t __a, uint32x4_t __b)
{
- return (uint64x2_t) __builtin_aarch64_usubw2v4si ((int64x2_t) __a,
- (int32x4_t) __b);
+ return __builtin_aarch64_usubw2v4si_uuu (__a, __b);
}
__extension__ extern __inline int8x8_t
next reply other threads:[~2021-11-11 10:20 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-11 10:19 Jonathan Wright [this message]
2021-11-11 10:26 ` Richard Sandiford
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=DB9PR08MB69591EA055BC25FA003A9ED8EB949@DB9PR08MB6959.eurprd08.prod.outlook.com \
--to=jonathan.wright@arm.com \
--cc=Kyrylo.Tkachov@arm.com \
--cc=Richard.Sandiford@arm.com \
--cc=gcc-patches@gcc.gnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).