public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
From: Kyrill Tkachov <kyrylo.tkachov@foss.arm.com>
To: Srinath Parvathaneni <Srinath.Parvathaneni@arm.com>,
	"gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
Cc: Richard Earnshaw <Richard.Earnshaw@arm.com>
Subject: Re: [PATCH][ARM][GCC][4/1x]: MVE intrinsics with unary operand.
Date: Thu, 19 Dec 2019 18:16:00 -0000	[thread overview]
Message-ID: <c1680b0f-c2db-deaa-c6cf-04807d50fb07@foss.arm.com> (raw)
In-Reply-To: <DBBPR08MB47757EED7FD83FFC3247D4109B710@DBBPR08MB4775.eurprd08.prod.outlook.com>

Hi Srinath,

On 11/14/19 7:13 PM, Srinath Parvathaneni wrote:
> Hello,
>
> This patch supports following MVE ACLE intrinsics with unary operand.
>
> vctp16q, vctp32q, vctp64q, vctp8q, vpnot.
>
> Please refer to M-profile Vector Extension (MVE) intrinsics [1]  for 
> more details.
> [1] 
> https://developer.arm.com/architectures/instruction-sets/simd-isas/helium/mve-intrinsics
>
> There are few conflicts in defining the machine registers, resolved by 
> re-ordering
> VPR_REGNUM, APSRQ_REGNUM and APSRGE_REGNUM.
>
> Regression tested on arm-none-eabi and found no regressions.
>
> Ok for trunk?
>
> Thanks,
> Srinath.
>
> gcc/ChangeLog:
>
> 2019-11-12  Andre Vieira <andre.simoesdiasvieira@arm.com>
>             Mihail Ionescu  <mihail.ionescu@arm.com>
>             Srinath Parvathaneni <srinath.parvathaneni@arm.com>
>
>         * config/arm/arm-builtins.c (hi_UP): Define mode.
>         * config/arm/arm.h (IS_VPR_REGNUM): Move.
>         * config/arm/arm.md (VPR_REGNUM): Define before APSRQ_REGNUM.
>         (APSRQ_REGNUM): Modify.
>         (APSRGE_REGNUM): Modify.
>         * config/arm/arm_mve.h (vctp16q): Define macro.
>         (vctp32q): Likewise.
>         (vctp64q): Likewise.
>         (vctp8q): Likewise.
>         (vpnot): Likewise.
>         (__arm_vctp16q): Define intrinsic.
>         (__arm_vctp32q): Likewise.
>         (__arm_vctp64q): Likewise.
>         (__arm_vctp8q): Likewise.
>         (__arm_vpnot): Likewise.
>         * config/arm/arm_mve_builtins.def (UNOP_UNONE_UNONE): Use builtin
>         qualifier.
>         * config/arm/mve.md (mve_vctp<mode1>qhi): Define RTL pattern.
>         (mve_vpnothi): Likewise.
>
> gcc/testsuite/ChangeLog:
>
> 2019-11-12  Andre Vieira <andre.simoesdiasvieira@arm.com>
>             Mihail Ionescu  <mihail.ionescu@arm.com>
>             Srinath Parvathaneni <srinath.parvathaneni@arm.com>
>
>         * gcc.target/arm/mve/intrinsics/vctp16q.c: New test.
>         * gcc.target/arm/mve/intrinsics/vctp32q.c: Likewise.
>         * gcc.target/arm/mve/intrinsics/vctp64q.c: Likewise.
>         * gcc.target/arm/mve/intrinsics/vctp8q.c: Likewise.
>         * gcc.target/arm/mve/intrinsics/vpnot.c: Likewise.
>
>
> ###############     Attachment also inlined for ease of reply    
> ###############
>
>
> diff --git a/gcc/config/arm/arm-builtins.c b/gcc/config/arm/arm-builtins.c
> index 
> 21b213d8e1bc99a3946f15e97161e01d73832799..cd82aa159089c288607e240de02a85dcbb134a14 
> 100644
> --- a/gcc/config/arm/arm-builtins.c
> +++ b/gcc/config/arm/arm-builtins.c
> @@ -387,6 +387,7 @@ arm_set_sat_qualifiers[SIMD_MAX_BUILTIN_ARGS]
>  #define oi_UP    E_OImode
>  #define hf_UP    E_HFmode
>  #define si_UP    E_SImode
> +#define hi_UP    E_HImode
>  #define void_UP  E_VOIDmode
>
>  #define UP(X) X##_UP
> diff --git a/gcc/config/arm/arm.h b/gcc/config/arm/arm.h
> index 
> 485db72f05f16ca389227289a35c232dc982bf9d..95ec7963a57a1a5652a0a9dc30391a0ce6348242 
> 100644
> --- a/gcc/config/arm/arm.h
> +++ b/gcc/config/arm/arm.h
> @@ -955,6 +955,9 @@ extern int arm_arch_cmse;
>  #define IS_IWMMXT_GR_REGNUM(REGNUM) \
>    (((REGNUM) >= FIRST_IWMMXT_GR_REGNUM) && ((REGNUM) <= 
> LAST_IWMMXT_GR_REGNUM))
>
> +#define IS_VPR_REGNUM(REGNUM) \
> +  ((REGNUM) == VPR_REGNUM)
> +
>  /* Base register for access to local variables of the function.  */
>  #define FRAME_POINTER_REGNUM    102
>
> @@ -999,7 +1002,7 @@ extern int arm_arch_cmse;
>     && (LAST_VFP_REGNUM - (REGNUM) >= 2 * (N) - 1))
>
>  /* The number of hard registers is 16 ARM + 1 CC + 1 SFP + 1 AFP
> -   + 1 APSRQ + 1 APSRGE + 1 VPR.  */
> +   +1 VPR + 1 APSRQ + 1 APSRGE.  */
>  /* Intel Wireless MMX Technology registers add 16 + 4 more.  */
>  /* VFP (VFP3) adds 32 (64) + 1 VFPCC.  */
>  #define FIRST_PSEUDO_REGISTER   107
> @@ -1101,13 +1104,10 @@ extern int arm_regs_in_sequence[];
>    /* Registers not for general use.  */                \
>    CC_REGNUM, VFPCC_REGNUM,                     \
>    FRAME_POINTER_REGNUM, ARG_POINTER_REGNUM,    \
> -  SP_REGNUM, PC_REGNUM, APSRQ_REGNUM, APSRGE_REGNUM,   \
> -  VPR_REGNUM                                   \
> +  SP_REGNUM, PC_REGNUM, VPR_REGNUM, APSRQ_REGNUM,\
> +  APSRGE_REGNUM                                        \
>  }
>
> -#define IS_VPR_REGNUM(REGNUM) \
> -  ((REGNUM) == VPR_REGNUM)
> -
>  /* Use different register alloc ordering for Thumb.  */
>  #define ADJUST_REG_ALLOC_ORDER arm_order_regs_for_local_alloc ()
>
> diff --git a/gcc/config/arm/arm.md b/gcc/config/arm/arm.md
> index 
> 689baa0b0ff63ef90f47d2fd844cb98c9a1457a0..2a90482a873f8250a3b2b1dec141669f55e0c58b 
> 100644
> --- a/gcc/config/arm/arm.md
> +++ b/gcc/config/arm/arm.md
> @@ -39,9 +39,9 @@
>     (LAST_ARM_REGNUM  15)       ;
>     (CC_REGNUM       100)       ; Condition code pseudo register
>     (VFPCC_REGNUM    101)       ; VFP Condition code pseudo register
> -   (APSRQ_REGNUM    104)       ; Q bit pseudo register
> -   (APSRGE_REGNUM   105)       ; GE bits pseudo register
> -   (VPR_REGNUM      106)       ; Vector Predication Register - MVE 
> register.
> +   (VPR_REGNUM      104)       ; Vector Predication Register - MVE 
> register.
> +   (APSRQ_REGNUM    105)       ; Q bit pseudo register
> +   (APSRGE_REGNUM   106)       ; GE bits pseudo register
>    ]
>  )
>  ;; 3rd operand to select_dominance_cc_mode
> diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
> index 
> 1d357180ba9ddb26347b55cde625903bdb09eef6..c8d9b6471634725cea9bab3f9fa145810b506938 
> 100644
> --- a/gcc/config/arm/arm_mve.h
> +++ b/gcc/config/arm/arm_mve.h
> @@ -192,6 +192,11 @@ typedef struct { uint8x16_t val[4]; } uint8x16x4_t;
>  #define vcvtmq_u32_f32(__a) __arm_vcvtmq_u32_f32(__a)
>  #define vcvtaq_u16_f16(__a) __arm_vcvtaq_u16_f16(__a)
>  #define vcvtaq_u32_f32(__a) __arm_vcvtaq_u32_f32(__a)
> +#define vctp16q(__a) __arm_vctp16q(__a)
> +#define vctp32q(__a) __arm_vctp32q(__a)
> +#define vctp64q(__a) __arm_vctp64q(__a)
> +#define vctp8q(__a) __arm_vctp8q(__a)
> +#define vpnot(__a) __arm_vpnot(__a)
>  #endif
>
>  __extension__ extern __inline void
> @@ -703,6 +708,41 @@ __arm_vaddlvq_u32 (uint32x4_t __a)
>    return __builtin_mve_vaddlvq_uv4si (__a);
>  }
>
> +__extension__ extern __inline int64_t
> +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> +__arm_vctp16q (uint32_t __a)
> +{
> +  return __builtin_mve_vctp16qhi (__a);
> +}
> +
> +__extension__ extern __inline mve_pred16_t
> +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> +__arm_vctp32q (uint32_t __a)
> +{
> +  return __builtin_mve_vctp32qhi (__a);
> +}
> +
> +__extension__ extern __inline mve_pred16_t
> +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> +__arm_vctp64q (uint32_t __a)
> +{
> +  return __builtin_mve_vctp64qhi (__a);
> +}
> +
> +__extension__ extern __inline mve_pred16_t
> +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> +__arm_vctp8q (uint32_t __a)
> +{
> +  return __builtin_mve_vctp8qhi (__a);
> +}
> +
> +__extension__ extern __inline mve_pred16_t
> +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> +__arm_vpnot (mve_pred16_t __a)
> +{
> +  return __builtin_mve_vpnothi (__a);
> +}


Hmm, the spec says that this should generate:

VMSR P0,Rp
VPNOT
VMRS Rt,P0

but __builtin_mve_vpnothi will generate just a VPNOT... what's up with that?

Thanks,

Kyrill


> +
>  #if (__ARM_FEATURE_MVE & 2) /* MVE Floating point.  */
>
>  __extension__ extern __inline void
> diff --git a/gcc/config/arm/arm_mve_builtins.def 
> b/gcc/config/arm/arm_mve_builtins.def
> index 
> aafcc2a4bede4e2f9f7845e60f30d4482b7f10bc..816b6dfca7fb221275212ca5f06fc6f679860a38 
> 100644
> --- a/gcc/config/arm/arm_mve_builtins.def
> +++ b/gcc/config/arm/arm_mve_builtins.def
> @@ -1,5 +1,5 @@
>  /*  MVE builtin definitions for Arm.
> -    Copyright  (C) 2019 Free Software Foundation, Inc.
> +    Copyright (C) 2019 Free Software Foundation, Inc.
>      Contributed by Arm.
>
>      This file is part of GCC.
> @@ -71,3 +71,8 @@ VAR2 (UNOP_UNONE_NONE, vcvtaq_u, v8hi, v4si)
>  VAR2 (UNOP_UNONE_IMM, vmvnq_n_u, v8hi, v4si)
>  VAR1 (UNOP_UNONE_UNONE, vrev16q_u, v16qi)
>  VAR1 (UNOP_UNONE_UNONE, vaddlvq_u, v4si)
> +VAR1 (UNOP_UNONE_UNONE, vctp16q, hi)
> +VAR1 (UNOP_UNONE_UNONE, vctp32q, hi)
> +VAR1 (UNOP_UNONE_UNONE, vctp64q, hi)
> +VAR1 (UNOP_UNONE_UNONE, vctp8q, hi)
> +VAR1 (UNOP_UNONE_UNONE, vpnot, hi)
> diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
> index 
> 9ad53e5655b01c26143a5f46c675658a450e0adf..ee2263e04309e8274ec76ae4478afb7cfba59f8f 
> 100644
> --- a/gcc/config/arm/mve.md
> +++ b/gcc/config/arm/mve.md
> @@ -36,7 +36,7 @@
>                           VREV32Q_U VREV32Q_S VMOVLTQ_U VMOVLTQ_S 
> VMOVLBQ_S
>                           VMOVLBQ_U VCVTQ_FROM_F_S VCVTQ_FROM_F_U VCVTPQ_S
>                           VCVTPQ_U VCVTNQ_S VCVTNQ_U VCVTMQ_S VCVTMQ_U
> -                        VADDLVQ_U])
> +                        VADDLVQ_U VCTP8Q VCTP16Q VCTP32Q VCTP64Q VPNOT])
>
>  (define_mode_attr MVE_CNVT [(V8HI "V8HF") (V4SI "V4SF")
>                              (V8HF "V8HI") (V4SF "V4SI")])
> @@ -54,6 +54,9 @@
>                         (VCLZQ_U "u") (VCLZQ_S "s") (VREV32Q_U "u")
>                         (VREV32Q_S "s") (VADDLVQ_U "u") (VADDLVQ_S "s")])
>
> +(define_int_attr mode1 [(VCTP8Q "8") (VCTP16Q "16") (VCTP32Q "32")
> +                       (VCTP64Q "64")])
> +
>  (define_int_iterator VCVTQ_TO_F [VCVTQ_TO_F_S VCVTQ_TO_F_U])
>  (define_int_iterator VMVNQ_N [VMVNQ_N_U VMVNQ_N_S])
>  (define_int_iterator VREV64Q [VREV64Q_S VREV64Q_U])
> @@ -71,6 +74,7 @@
>  (define_int_iterator VCVTNQ [VCVTNQ_S VCVTNQ_U])
>  (define_int_iterator VCVTMQ [VCVTMQ_S VCVTMQ_U])
>  (define_int_iterator VADDLVQ [VADDLVQ_U VADDLVQ_S])
> +(define_int_iterator VCTPQ [VCTP8Q VCTP16Q VCTP32Q VCTP64Q])
>
>  (define_insn "*mve_mov<mode>"
>    [(set (match_operand:MVE_types 0 "s_register_operand" "=w,w,r,w,w,r,w")
> @@ -648,3 +652,31 @@
>    "vaddlv.<supf>32 %Q0, %R0, %q1"
>    [(set_attr "type" "mve_move")
>  ])
> +
> +;;
> +;; [vctp8q vctp16q vctp32q vctp64q])
> +;;
> +(define_insn "mve_vctp<mode1>qhi"
> +  [
> +   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
> +       (unspec:HI [(match_operand:SI 1 "s_register_operand" "r")]
> +       VCTPQ))
> +  ]
> +  "TARGET_HAVE_MVE"
> +  "vctp.<mode1> %1"
> +  [(set_attr "type" "mve_move")
> +])
> +
> +;;
> +;; [vpnot])
> +;;
> +(define_insn "mve_vpnothi"
> +  [
> +   (set (match_operand:HI 0 "s_register_operand" "=r")
> +       (unspec:HI [(match_operand:HI 1 "vpr_register_operand" "Up")]
> +        VPNOT))
> +  ]
> +  "TARGET_HAVE_MVE"
> +  "vpnot"
> +  [(set_attr "type" "mve_move")
> +])
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vctp16q.c 
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vctp16q.c
> new file mode 100644
> index 
> 0000000000000000000000000000000000000000..0530d23d6cb6283f19f9122bb85c22714eb71843
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vctp16q.c
> @@ -0,0 +1,21 @@
> +/* { dg-do compile  } */
> +/* { dg-additional-options "-march=armv8.1-m.main+mve 
> -mfloat-abi=hard -O2"  }  */
> +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} 
> } */
> +
> +#include "arm_mve.h"
> +
> +mve_pred16_t
> +foo (uint32_t a)
> +{
> +  return vctp16q (a);
> +}
> +
> +/* { dg-final { scan-assembler "vctp.16"  }  } */
> +
> +mve_pred16_t
> +foo1 (uint32_t a)
> +{
> +  return vctp16q (a);
> +}
> +
> +/* { dg-final { scan-assembler "vctp.16"  }  } */
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vctp32q.c 
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vctp32q.c
> new file mode 100644
> index 
> 0000000000000000000000000000000000000000..6e59362345a7b4e77028262c69bee42d230a6f38
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vctp32q.c
> @@ -0,0 +1,21 @@
> +/* { dg-do compile  } */
> +/* { dg-additional-options "-march=armv8.1-m.main+mve 
> -mfloat-abi=hard -O2"  }  */
> +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} 
> } */
> +
> +#include "arm_mve.h"
> +
> +mve_pred16_t
> +foo (uint32_t a)
> +{
> +  return vctp32q (a);
> +}
> +
> +/* { dg-final { scan-assembler "vctp.32"  }  } */
> +
> +mve_pred16_t
> +foo1 (uint32_t a)
> +{
> +  return vctp32q (a);
> +}
> +
> +/* { dg-final { scan-assembler "vctp.32"  }  } */
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vctp64q.c 
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vctp64q.c
> new file mode 100644
> index 
> 0000000000000000000000000000000000000000..9a9224ef88de71012373b0f0cebedbade045fccd
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vctp64q.c
> @@ -0,0 +1,21 @@
> +/* { dg-do compile  } */
> +/* { dg-additional-options "-march=armv8.1-m.main+mve 
> -mfloat-abi=hard -O2"  }  */
> +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} 
> } */
> +
> +#include "arm_mve.h"
> +
> +mve_pred16_t
> +foo (uint32_t a)
> +{
> +  return vctp64q (a);
> +}
> +
> +/* { dg-final { scan-assembler "vctp.64"  }  } */
> +
> +mve_pred16_t
> +foo1 (uint32_t a)
> +{
> +  return vctp64q (a);
> +}
> +
> +/* { dg-final { scan-assembler "vctp.64"  }  } */
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vctp8q.c 
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vctp8q.c
> new file mode 100644
> index 
> 0000000000000000000000000000000000000000..3118d9b60a2eb8c72eb1273445a0b3370b603402
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vctp8q.c
> @@ -0,0 +1,21 @@
> +/* { dg-do compile  } */
> +/* { dg-additional-options "-march=armv8.1-m.main+mve 
> -mfloat-abi=hard -O2"  }  */
> +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} 
> } */
> +
> +#include "arm_mve.h"
> +
> +mve_pred16_t
> +foo (uint32_t a)
> +{
> +  return vctp8q (a);
> +}
> +
> +/* { dg-final { scan-assembler "vctp.8"  }  } */
> +
> +mve_pred16_t
> +foo1 (uint32_t a)
> +{
> +  return vctp8q (a);
> +}
> +
> +/* { dg-final { scan-assembler "vctp.8"  }  } */
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vpnot.c 
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vpnot.c
> new file mode 100644
> index 
> 0000000000000000000000000000000000000000..9422d342b9d8bf024c2a95877c61e8dd0bd4ffb1
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vpnot.c
> @@ -0,0 +1,21 @@
> +/* { dg-do compile  } */
> +/* { dg-additional-options "-march=armv8.1-m.main+mve 
> -mfloat-abi=hard -O2"  }  */
> +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} 
> } */
> +
> +#include "arm_mve.h"
> +
> +mve_pred16_t
> +foo (mve_pred16_t a)
> +{
> +  return vpnot (a);
> +}
> +
> +/* { dg-final { scan-assembler "vpnot"  }  } */
> +
> +mve_pred16_t
> +foo1 (mve_pred16_t a)
> +{
> +  return vpnot (a);
> +}
> +
> +/* { dg-final { scan-assembler "vpnot"  }  } */
>

  reply	other threads:[~2019-12-19 18:05 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-14 19:34 [PATCH][ARM][GCC][0/x]: Support for MVE ACLE intrinsics Srinath Parvathaneni
2019-11-14 19:13 ` [PATCH][ARM][GCC][4/x]: MVE ACLE vector interleaving store intrinsics Srinath Parvathaneni
2019-12-19 17:39   ` Kyrill Tkachov
2019-11-14 19:13 ` [PATCH][ARM][GCC][2/2x]: MVE intrinsics with binary operands Srinath Parvathaneni
2019-11-14 19:13 ` [PATCH][ARM][GCC][3/x]: MVE ACLE intrinsics framework patch Srinath Parvathaneni
2019-12-19 17:50   ` Kyrill Tkachov
2019-11-14 19:13 ` [PATCH][ARM][GCC][2/x]: " Srinath Parvathaneni
2019-12-19 17:24   ` Kyrill Tkachov
2019-11-14 19:13 ` [PATCH][ARM][GCC][2/1x]: MVE intrinsics with unary operand Srinath Parvathaneni
2019-12-19 18:05   ` Kyrill Tkachov
2019-11-14 19:13 ` [PATCH][ARM][GCC][3/3x]: MVE intrinsics with ternary operands Srinath Parvathaneni
2019-11-14 19:13 ` [PATCH][ARM][GCC][5/2x]: MVE intrinsics with binary operands Srinath Parvathaneni
2019-11-14 19:13 ` [PATCH][ARM][GCC][3/1x]: MVE intrinsics with unary operand Srinath Parvathaneni
2019-11-14 19:13 ` [PATCH][ARM][GCC][3/2x]: MVE intrinsics with binary operands Srinath Parvathaneni
2019-11-14 19:13 ` [PATCH][ARM][GCC][3/4x]: MVE intrinsics with quaternary operands Srinath Parvathaneni
2019-11-14 19:14 ` [PATCH][ARM][GCC][1/4x]: " Srinath Parvathaneni
2019-11-14 19:14 ` [PATCH][ARM][GCC][1/2x]: MVE intrinsics with binary operands Srinath Parvathaneni
2019-12-19 19:10   ` Kyrill Tkachov
2019-11-14 19:15 ` [PATCH][ARM][GCC][2/4x]: MVE intrinsics with quaternary operands Srinath Parvathaneni
2019-11-14 19:15 ` [PATCH][ARM][GCC][7/5x]: MVE store intrinsics which stores byte,half word or word to memory Srinath Parvathaneni
2019-11-14 19:15 ` [PATCH][ARM][GCC][4/2x]: MVE intrinsics with binary operands Srinath Parvathaneni
2019-11-14 19:15 ` [PATCH][ARM][GCC][4/5x]: MVE load intrinsics with zero(_z) suffix Srinath Parvathaneni
2019-11-14 19:15 ` [PATCH][ARM][GCC][2/5x]: MVE load intrinsics Srinath Parvathaneni
2019-11-14 19:15 ` [PATCH][ARM][GCC][8/5x]: Remaining MVE store intrinsics which stores an half word, word and double word to memory Srinath Parvathaneni
2019-11-14 19:15 ` [PATCH][ARM][GCC][1/5x]: MVE store intrinsics Srinath Parvathaneni
2019-11-14 19:15 ` [PATCH][ARM][GCC][3/5x]: MVE store intrinsics with predicated suffix Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][7x]: MVE vreinterpretq and vuninitializedq intrinsics Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][14x]: MVE ACLE whole vector left shift with carry intrinsics Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][5/5x]: MVE ACLE load intrinsics which load a byte, halfword, or word from memory Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][13x]: MVE ACLE scalar shift intrinsics Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][2/8x]: MVE ACLE gather load and scatter store intrinsics with writeback Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][1/x]: MVE ACLE intrinsics framework patch Srinath Parvathaneni
2019-12-18 17:18   ` Kyrill Tkachov
2019-11-14 19:16 ` [PATCH][ARM][GCC][1/1x]: Patch to support MVE ACLE intrinsics with unary operand Srinath Parvathaneni
2019-12-19 17:57   ` Kyrill Tkachov
2019-11-14 19:16 ` [PATCH][ARM][GCC][12x]: MVE ACLE intrinsics to set and get vector lane Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][6/5x]: Remaining MVE load intrinsics which loads half word and word or double word from memory Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][4/1x]: MVE intrinsics with unary operand Srinath Parvathaneni
2019-12-19 18:16   ` Kyrill Tkachov [this message]
2019-11-14 19:16 ` [PATCH][ARM][GCC][1/8x]: MVE ACLE vidup, vddup, viwdup and vdwdup intrinsics with writeback Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][10x]: MVE ACLE intrinsics "add with carry across beats" and "beat-wise substract" Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][6x]:MVE ACLE vaddq intrinsics using arithmetic plus operator Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][9x]: MVE ACLE predicated intrinsics with (dont-care) variant Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][2/3x]: MVE intrinsics with ternary operands Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][11x]: MVE ACLE vector interleaving store and deinterleaving load intrinsics and also aliases to vstr and vldr intrinsics Srinath Parvathaneni
2019-11-14 19:16 ` [PATCH][ARM][GCC][4/4x]: MVE intrinsics with quaternary operands Srinath Parvathaneni
2019-11-14 19:27 ` [PATCH][ARM][GCC][1/3x]: MVE intrinsics with ternary operands Srinath Parvathaneni
2019-12-12 16:09 ` [PATCH][ARM][GCC][0/x]: Support for MVE ACLE intrinsics Kyrill Tkachov

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=c1680b0f-c2db-deaa-c6cf-04807d50fb07@foss.arm.com \
    --to=kyrylo.tkachov@foss.arm.com \
    --cc=Richard.Earnshaw@arm.com \
    --cc=Srinath.Parvathaneni@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).