From patchwork Tue Jul 7 12:34:57 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alan Lawrence X-Patchwork-Id: 492170 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from sourceware.org (server1.sourceware.org [209.132.180.131]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 660531402C2 for ; Tue, 7 Jul 2015 22:35:19 +1000 (AEST) Authentication-Results: ozlabs.org; dkim=pass (1024-bit key; unprotected) header.d=gcc.gnu.org header.i=@gcc.gnu.org header.b=V949PcvV; dkim-atps=neutral DomainKey-Signature: a=rsa-sha1; c=nofws; d=gcc.gnu.org; h=list-id :list-unsubscribe:list-archive:list-post:list-help:sender :message-id:date:from:mime-version:to:subject:in-reply-to :content-type; q=dns; s=default; b=YUPInxU/9S0Hs3NkxSNkFfB1qjvM7 Hn3J+EzCs9uYtMZz4eiF2JJ0tRwijvT1t5Jb2L9/25YhiNQ21k+QDJKySsFKS8og /lbWGk/lquqP87vah7KdgOqbMsuNWVOWIWMlttNOzKFzvgglnPEMe/Z7Ykltthk+ fPeh4M9YIxuRe8= DKIM-Signature: v=1; a=rsa-sha1; c=relaxed; d=gcc.gnu.org; h=list-id :list-unsubscribe:list-archive:list-post:list-help:sender :message-id:date:from:mime-version:to:subject:in-reply-to :content-type; s=default; bh=9b2sYpEQtuvY7+egPxlN9ShpluQ=; b=V94 9PcvVmxBuPuciOu3w7hrFOxavkKQbaUErzmOjomda32v6nXmvjXBV/Tsgvn0gxnD EmM3KpRlSrP4DAtt8mqzwdrxH+ocVTdGv+EJHx7d9bS8Q1bbPoX1kpA/bJzUSV2n VAK0BBKRHMFoZkt7ZsY5bLNr8C1W1ZSLUmrxS46I= Received: (qmail 91788 invoked by alias); 7 Jul 2015 12:35:10 -0000 Mailing-List: contact gcc-patches-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Id: List-Unsubscribe: List-Archive: List-Post: List-Help: Sender: gcc-patches-owner@gcc.gnu.org Delivered-To: mailing list gcc-patches@gcc.gnu.org Received: (qmail 91301 invoked by uid 89); 7 Jul 2015 12:35:10 -0000 Authentication-Results: sourceware.org; auth=none X-Virus-Found: No X-Spam-SWARE-Status: No, score=-1.7 required=5.0 tests=AWL, BAYES_00, SPF_PASS autolearn=ham version=3.3.2 X-HELO: eu-smtp-delivery-143.mimecast.com Received: from eu-smtp-delivery-143.mimecast.com (HELO eu-smtp-delivery-143.mimecast.com) (207.82.80.143) by sourceware.org (qpsmtpd/0.93/v0.84-503-g423c35a) with ESMTP; Tue, 07 Jul 2015 12:35:03 +0000 Received: from cam-owa1.Emea.Arm.com (fw-tnat.cambridge.arm.com [217.140.96.140]) by eu-smtp-1.mimecast.com with ESMTP id uk-mta-36-HPonAKVpSvy23tuR0dFvvA-1 Received: from [10.2.207.65] ([10.1.2.79]) by cam-owa1.Emea.Arm.com with Microsoft SMTPSVC(6.0.3790.3959); Tue, 7 Jul 2015 13:34:57 +0100 Message-ID: <559BC771.8010703@arm.com> Date: Tue, 07 Jul 2015 13:34:57 +0100 From: Alan Lawrence User-Agent: Thunderbird 2.0.0.24 (X11/20101213) MIME-Version: 1.0 To: "gcc-patches@gcc.gnu.org" Subject: [PATCH 5/16][ARM] Add float16x8_t intrinsics In-Reply-To: <559BC6EC.3000907@arm.com> X-MC-Unique: HPonAKVpSvy23tuR0dFvvA-1 X-IsSubscribed: yes As per https://gcc.gnu.org/ml/gcc-patches/2015-04/msg01337.html commit 336eb16d3061131fe8d28fad4a473d00768bfe5c Author: Alan Lawrence Date: Tue Dec 9 15:06:38 2014 +0000 ARM float16x8_t intrinsics (v2 - fix v[sg]etq_lane_f16, add vreinterpretq_p16_f16, no vdup_n/lane/vmov_n) diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h index a958f63..db73c70 100644 --- a/gcc/config/arm/arm_neon.h +++ b/gcc/config/arm/arm_neon.h @@ -5282,6 +5282,15 @@ vgetq_lane_s32 (int32x4_t __a, const int __b) return (int32_t)__builtin_neon_vget_lanev4si (__a, __b); } +#define vgetq_lane_f16(__v, __idx) \ + __extension__ \ + ({ \ + float16x8_t __vec = (__v); \ + __builtin_arm_lane_check (8, __idx); \ + float16_t __res = __vec[__idx]; \ + __res; \ + }) + __extension__ static __inline float32_t __attribute__ ((__always_inline__)) vgetq_lane_f32 (float32x4_t __a, const int __b) { @@ -5424,6 +5433,16 @@ vsetq_lane_s32 (int32_t __a, int32x4_t __b, const int __c) return (int32x4_t)__builtin_neon_vset_lanev4si ((__builtin_neon_si) __a, __b, __c); } +#define vsetq_lane_f16(__e, __v, __idx) \ + __extension__ \ + ({ \ + float16_t __elem = (__e); \ + float16x8_t __vec = (__v); \ + __builtin_arm_lane_check (8, __idx); \ + __vec[__idx] = __elem; \ + __vec; \ + }) + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vsetq_lane_f32 (float32_t __a, float32x4_t __b, const int __c) { @@ -8907,6 +8926,12 @@ vld1q_lane_s32 (const int32_t * __a, int32x4_t __b, const int __c) return (int32x4_t)__builtin_neon_vld1_lanev4si ((const __builtin_neon_si *) __a, __b, __c); } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vld1q_lane_f16 (const float16_t * __a, float16x8_t __b, const int __c) +{ + return vsetq_lane_f16 (*__a, __b, __c); +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vld1q_lane_f32 (const float32_t * __a, float32x4_t __b, const int __c) { @@ -9062,6 +9087,13 @@ vld1q_dup_s32 (const int32_t * __a) return (int32x4_t)__builtin_neon_vld1_dupv4si ((const __builtin_neon_si *) __a); } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vld1q_dup_f16 (const float16_t * __a) +{ + float16_t __f = *__a; + return (float16x8_t) { __f, __f, __f, __f, __f, __f, __f, __f }; +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vld1q_dup_f32 (const float32_t * __a) { @@ -12856,6 +12888,12 @@ vreinterpretq_p8_p16 (poly16x8_t __a) } __extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_f16 (float16x8_t __a) +{ + return (poly8x16_t) __a; +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) vreinterpretq_p8_f32 (float32x4_t __a) { return (poly8x16_t)__builtin_neon_vreinterpretv16qiv4sf (__a); @@ -12932,6 +12970,12 @@ vreinterpretq_p16_p8 (poly8x16_t __a) } __extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_f16 (float16x8_t __a) +{ + return (poly16x8_t) __a; +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) vreinterpretq_p16_f32 (float32x4_t __a) { return (poly16x8_t)__builtin_neon_vreinterpretv8hiv4sf (__a); @@ -13001,6 +13045,88 @@ vreinterpretq_p16_u32 (uint32x4_t __a) return (poly16x8_t)__builtin_neon_vreinterpretv8hiv4si ((int32x4_t) __a); } +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_p8 (poly8x16_t __a) +{ + return (float16x8_t) __a; +} + +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_p16 (poly16x8_t __a) +{ + return (float16x8_t) __a; +} + +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_f32 (float32x4_t __a) +{ + return (float16x8_t) __a; +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_p64 (poly64x2_t __a) +{ + return (float16x8_t) __a; +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_p128 (poly128_t __a) +{ + return (float16x8_t) __a; +} + +#endif +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_s64 (int64x2_t __a) +{ + return (float16x8_t) __a; +} + +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_u64 (uint64x2_t __a) +{ + return (float16x8_t) __a; +} + +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_s8 (int8x16_t __a) +{ + return (float16x8_t) __a; +} + +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_s16 (int16x8_t __a) +{ + return (float16x8_t) __a; +} + +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_s32 (int32x4_t __a) +{ + return (float16x8_t) __a; +} + +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_u8 (uint8x16_t __a) +{ + return (float16x8_t) __a; +} + +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_u16 (uint16x8_t __a) +{ + return (float16x8_t) __a; +} + +__extension__ static __inline float16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_f16_u32 (uint32x4_t __a) +{ + return (float16x8_t) __a; +} + __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vreinterpretq_f32_p8 (poly8x16_t __a) { @@ -13013,6 +13139,12 @@ vreinterpretq_f32_p16 (poly16x8_t __a) return (float32x4_t)__builtin_neon_vreinterpretv4sfv8hi ((int16x8_t) __a); } +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_f16 (float16x8_t __a) +{ + return (float32x4_t) __a; +} + #ifdef __ARM_FEATURE_CRYPTO __extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) vreinterpretq_f32_p64 (poly64x2_t __a) @@ -13095,6 +13227,14 @@ vreinterpretq_p64_p16 (poly16x8_t __a) #endif #ifdef __ARM_FEATURE_CRYPTO __extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_f16 (float16x8_t __a) +{ + return (poly64x2_t) __a; +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) vreinterpretq_p64_f32 (float32x4_t __a) { return (poly64x2_t)__builtin_neon_vreinterpretv2div4sf (__a); @@ -13191,6 +13331,14 @@ vreinterpretq_p128_p16 (poly16x8_t __a) #endif #ifdef __ARM_FEATURE_CRYPTO __extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_f16 (float16x8_t __a) +{ + return (poly128_t) __a; +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) vreinterpretq_p128_f32 (float32x4_t __a) { return (poly128_t)__builtin_neon_vreinterprettiv4sf (__a); @@ -13282,6 +13430,12 @@ vreinterpretq_s64_p16 (poly16x8_t __a) } __extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_f16 (float16x8_t __a) +{ + return (int64x2_t) __a; +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) vreinterpretq_s64_f32 (float32x4_t __a) { return (int64x2_t)__builtin_neon_vreinterpretv2div4sf (__a); @@ -13358,6 +13512,12 @@ vreinterpretq_u64_p16 (poly16x8_t __a) } __extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_f16 (float16x8_t __a) +{ + return (uint64x2_t) __a; +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) vreinterpretq_u64_f32 (float32x4_t __a) { return (uint64x2_t)__builtin_neon_vreinterpretv2div4sf (__a); @@ -13434,6 +13594,12 @@ vreinterpretq_s8_p16 (poly16x8_t __a) } __extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_f16 (float16x8_t __a) +{ + return (int8x16_t) __a; +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) vreinterpretq_s8_f32 (float32x4_t __a) { return (int8x16_t)__builtin_neon_vreinterpretv16qiv4sf (__a); @@ -13510,6 +13676,12 @@ vreinterpretq_s16_p16 (poly16x8_t __a) } __extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_f16 (float16x8_t __a) +{ + return (int16x8_t) __a; +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) vreinterpretq_s16_f32 (float32x4_t __a) { return (int16x8_t)__builtin_neon_vreinterpretv8hiv4sf (__a); @@ -13586,6 +13758,12 @@ vreinterpretq_s32_p16 (poly16x8_t __a) } __extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_f16 (float16x8_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv8hi ((int16x8_t) __a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) vreinterpretq_s32_f32 (float32x4_t __a) { return (int32x4_t)__builtin_neon_vreinterpretv4siv4sf (__a); @@ -13662,6 +13840,12 @@ vreinterpretq_u8_p16 (poly16x8_t __a) } __extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_f16 (float16x8_t __a) +{ + return (uint8x16_t) __a; +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) vreinterpretq_u8_f32 (float32x4_t __a) { return (uint8x16_t)__builtin_neon_vreinterpretv16qiv4sf (__a); @@ -13738,6 +13922,12 @@ vreinterpretq_u16_p16 (poly16x8_t __a) } __extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_f16 (float16x8_t __a) +{ + return (uint16x8_t) __a; +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) vreinterpretq_u16_f32 (float32x4_t __a) { return (uint16x8_t)__builtin_neon_vreinterpretv8hiv4sf (__a); @@ -13814,6 +14004,12 @@ vreinterpretq_u32_p16 (poly16x8_t __a) } __extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_f16 (float16x8_t __a) +{ + return (uint32x4_t) __a; +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) vreinterpretq_u32_f32 (float32x4_t __a) { return (uint32x4_t)__builtin_neon_vreinterpretv4siv4sf (__a);