From patchwork Tue Oct 21 13:03:11 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Christophe Lyon X-Patchwork-Id: 39129 Return-Path: X-Original-To: linaro@patches.linaro.org Delivered-To: linaro@patches.linaro.org Received: from mail-la0-f70.google.com (mail-la0-f70.google.com [209.85.215.70]) by ip-10-151-82-157.ec2.internal (Postfix) with ESMTPS id 09D6E202DB for ; Tue, 21 Oct 2014 13:09:17 +0000 (UTC) Received: by mail-la0-f70.google.com with SMTP id ge10sf792760lab.9 for ; Tue, 21 Oct 2014 06:09:16 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:mime-version:delivered-to:mailing-list :precedence:list-id:list-unsubscribe:list-archive:list-post :list-help:sender:delivered-to:from:to:subject:date:message-id :in-reply-to:references:x-original-sender :x-original-authentication-results; bh=gEr/zySh5CUy61BIU2oV9jZmLAHG0PJeBNGHzkWV/Ok=; b=ga4r1PGS7O0fYoj7AeBGNsQNiUfdKqOEQqIhl7AdVh+upR+n8V3QQakXtsIrvFofsV 97YWVSeedPuUKYH2J3jedfZel6na6qyHVGVMIZm/vuMaRG6XKvcaCrAlBe7F/e+UyL55 5JJkJQizDYgA604cPzoRahJNSc9bhEMnkLNblqfsF82nhRIro4W1xWCp/jx0vtgANAhc zm1RDG/auVqmmYiEXc01ui6GnSe3/r1mCkxNBgvbu8nsPQW/QFQlGcjC5MagyPxjZgSG nagwfT6eTDZmjiaqYNbQ7V8GjeaDtRE+4+zHpzgcbJi9Po0omWENO8NUkWRrcB4g7doa hsUA== X-Gm-Message-State: ALoCoQk9I7NkClVvn++tyrF5jceMfx2CXLfcrV8Ktkp0ojqlP6sSA5nB/zoEYzZuu2ZIAnTsmKm6 X-Received: by 10.194.206.10 with SMTP id lk10mr558541wjc.3.1413896955914; Tue, 21 Oct 2014 06:09:15 -0700 (PDT) MIME-Version: 1.0 X-BeenThere: patchwork-forward@linaro.org Received: by 10.152.204.44 with SMTP id kv12ls55238lac.44.gmail; Tue, 21 Oct 2014 06:09:15 -0700 (PDT) X-Received: by 10.152.5.129 with SMTP id s1mr15469545las.59.1413896955688; Tue, 21 Oct 2014 06:09:15 -0700 (PDT) Received: from mail-la0-x229.google.com (mail-la0-x229.google.com. [2a00:1450:4010:c03::229]) by mx.google.com with ESMTPS id u2si18814537laa.120.2014.10.21.06.09.15 for (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Tue, 21 Oct 2014 06:09:15 -0700 (PDT) Received-SPF: pass (google.com: domain of patch+caf_=patchwork-forward=linaro.org@linaro.org designates 2a00:1450:4010:c03::229 as permitted sender) client-ip=2a00:1450:4010:c03::229; Received: by mail-la0-f41.google.com with SMTP id pn19so1015418lab.0 for ; Tue, 21 Oct 2014 06:09:15 -0700 (PDT) X-Received: by 10.152.29.8 with SMTP id f8mr34691963lah.56.1413896955403; Tue, 21 Oct 2014 06:09:15 -0700 (PDT) X-Forwarded-To: patchwork-forward@linaro.org X-Forwarded-For: patch@linaro.org patchwork-forward@linaro.org Delivered-To: patch@linaro.org Received: by 10.112.84.229 with SMTP id c5csp493506lbz; Tue, 21 Oct 2014 06:09:14 -0700 (PDT) X-Received: by 10.70.92.134 with SMTP id cm6mr2356581pdb.167.1413896953587; Tue, 21 Oct 2014 06:09:13 -0700 (PDT) Received: from sourceware.org (server1.sourceware.org. [209.132.180.131]) by mx.google.com with ESMTPS id ku4si11132436pab.87.2014.10.21.06.09.12 for (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Tue, 21 Oct 2014 06:09:13 -0700 (PDT) Received-SPF: pass (google.com: domain of gcc-patches-return-381280-patch=linaro.org@gcc.gnu.org designates 209.132.180.131 as permitted sender) client-ip=209.132.180.131; Received: (qmail 27965 invoked by alias); 21 Oct 2014 13:03:37 -0000 Mailing-List: list patchwork-forward@linaro.org; contact patchwork-forward+owners@linaro.org Precedence: list 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 27737 invoked by uid 89); 21 Oct 2014 13:03:35 -0000 X-Virus-Found: No X-Spam-SWARE-Status: No, score=-2.6 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_LOW, SPF_PASS autolearn=ham version=3.3.2 X-HELO: mail-wg0-f43.google.com Received: from mail-wg0-f43.google.com (HELO mail-wg0-f43.google.com) (74.125.82.43) by sourceware.org (qpsmtpd/0.93/v0.84-503-g423c35a) with (AES128-SHA encrypted) ESMTPS; Tue, 21 Oct 2014 13:03:31 +0000 Received: by mail-wg0-f43.google.com with SMTP id m15so1307215wgh.2 for ; Tue, 21 Oct 2014 06:03:28 -0700 (PDT) X-Received: by 10.194.91.176 with SMTP id cf16mr35977820wjb.60.1413896608588; Tue, 21 Oct 2014 06:03:28 -0700 (PDT) Received: from babel.clyon.hd.free.fr (vig38-2-82-225-222-175.fbx.proxad.net. [82.225.222.175]) by mx.google.com with ESMTPSA id ce1sm15348183wjc.2.2014.10.21.06.03.27 for (version=TLSv1.2 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Tue, 21 Oct 2014 06:03:27 -0700 (PDT) From: Christophe Lyon To: gcc-patches@gcc.gnu.org Subject: [Patch ARM-AArch64/testsuite v3 19/21] Add vld2_lane, vld3_lane and vld4_lane tests. Date: Tue, 21 Oct 2014 15:03:11 +0200 Message-Id: <1413896593-26607-20-git-send-email-christophe.lyon@linaro.org> In-Reply-To: <1413896593-26607-1-git-send-email-christophe.lyon@linaro.org> References: <1413896593-26607-1-git-send-email-christophe.lyon@linaro.org> X-IsSubscribed: yes X-Original-Sender: christophe.lyon@linaro.org X-Original-Authentication-Results: mx.google.com; spf=pass (google.com: domain of patch+caf_=patchwork-forward=linaro.org@linaro.org designates 2a00:1450:4010:c03::229 as permitted sender) smtp.mail=patch+caf_=patchwork-forward=linaro.org@linaro.org; dkim=pass header.i=@gcc.gnu.org X-Google-Group-Id: 836684582541 2014-10-21 Christophe Lyon * gcc.target/aarch64/advsimd-intrinsics/vldX_lane.c: New file. diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vldX_lane.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vldX_lane.c new file mode 100644 index 0000000..1991033 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vldX_lane.c @@ -0,0 +1,610 @@ +#include +#include "arm-neon-ref.h" +#include "compute-ref-data.h" + +/* Expected results. */ + +/* vld2/chunk 0. */ +VECT_VAR_DECL(expected_vld2_0,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld2_0,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld2_0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 }; +VECT_VAR_DECL(expected_vld2_0,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld2_0,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld2_0,uint,16,4) [] = { 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld2_0,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld2_0,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld2_0,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld2_0,poly,16,4) [] = { 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld2_0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 }; +VECT_VAR_DECL(expected_vld2_0,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld2_0,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld2_0,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld2_0,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld2_0,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld2_0,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld2_0,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld2_0,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld2_0,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld2_0,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld2_0,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; + +/* vld2/chunk 1. */ +VECT_VAR_DECL(expected_vld2_1,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xf0, 0xf1 }; +VECT_VAR_DECL(expected_vld2_1,int,16,4) [] = { 0xfff0, 0xfff1, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld2_1,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld2_1,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld2_1,uint,8,8) [] = { 0xf0, 0xf1, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld2_1,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1 }; +VECT_VAR_DECL(expected_vld2_1,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 }; +VECT_VAR_DECL(expected_vld2_1,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld2_1,poly,8,8) [] = { 0xf0, 0xf1, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld2_1,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1 }; +VECT_VAR_DECL(expected_vld2_1,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld2_1,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld2_1,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xfff0, 0xfff1, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld2_1,int,32,4) [] = { 0xfffffff0, 0xfffffff1, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld2_1,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld2_1,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld2_1,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld2_1,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld2_1,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld2_1,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld2_1,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld2_1,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, + 0xaaaaaaaa, 0xaaaaaaaa }; + +/* vld3/chunk 0. */ +VECT_VAR_DECL(expected_vld3_0,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld3_0,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 }; +VECT_VAR_DECL(expected_vld3_0,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld3_0,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld3_0,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_0,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld3_0,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld3_0,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld3_0,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 }; +VECT_VAR_DECL(expected_vld3_0,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld3_0,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_0,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld3_0,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld3_0,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld3_0,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_0,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, + 0xfffffff2, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld3_0,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld3_0,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld3_0,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_0,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; + +/* vld3/chunk 1. */ +VECT_VAR_DECL(expected_vld3_1,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld3_1,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1 }; +VECT_VAR_DECL(expected_vld3_1,int,32,2) [] = { 0xfffffff2, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld3_1,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld3_1,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xf0, 0xf1, 0xf2, 0xaa }; +VECT_VAR_DECL(expected_vld3_1,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_1,uint,32,2) [] = { 0xaaaaaaaa, 0xfffffff0 }; +VECT_VAR_DECL(expected_vld3_1,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld3_1,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xf0, 0xf1, 0xf2, 0xaa }; +VECT_VAR_DECL(expected_vld3_1,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_1,hfloat,32,2) [] = { 0xc1600000, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld3_1,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld3_1,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_1,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xfffffff0, 0xfffffff1 }; +VECT_VAR_DECL(expected_vld3_1,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld3_1,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld3_1,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 }; +VECT_VAR_DECL(expected_vld3_1,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld3_1,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld3_1,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld3_1,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 }; +VECT_VAR_DECL(expected_vld3_1,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xc1800000, 0xc1700000 }; + +/* vld3/chunk 2. */ +VECT_VAR_DECL(expected_vld3_2,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xf0, 0xf1, 0xf2 }; +VECT_VAR_DECL(expected_vld3_2,int,16,4) [] = { 0xfff2, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_2,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld3_2,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld3_2,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld3_2,uint,16,4) [] = { 0xaaaa, 0xfff0, 0xfff1, 0xfff2 }; +VECT_VAR_DECL(expected_vld3_2,uint,32,2) [] = { 0xfffffff1, 0xfffffff2 }; +VECT_VAR_DECL(expected_vld3_2,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld3_2,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld3_2,poly,16,4) [] = { 0xaaaa, 0xfff0, 0xfff1, 0xfff2 }; +VECT_VAR_DECL(expected_vld3_2,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld3_2,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld3_2,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, + 0xfff2, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_2,int,32,4) [] = { 0xfffffff2, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld3_2,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld3_2,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld3_2,uint,16,8) [] = { 0xfff1, 0xfff2, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_2,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld3_2,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld3_2,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld3_2,poly,16,8) [] = { 0xfff1, 0xfff2, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld3_2,hfloat,32,4) [] = { 0xc1600000, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; + +/* vld4/chunk 0. */ +VECT_VAR_DECL(expected_vld4_0,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld4_0,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 }; +VECT_VAR_DECL(expected_vld4_0,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_0,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld4_0,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_0,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld4_0,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_0,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld4_0,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 }; +VECT_VAR_DECL(expected_vld4_0,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld4_0,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_0,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld4_0,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_0,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld4_0,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_0,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, + 0xfffffff2, 0xfffffff3 }; +VECT_VAR_DECL(expected_vld4_0,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_0,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld4_0,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_0,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; + +/* vld4/chunk 1. */ +VECT_VAR_DECL(expected_vld4_1,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld4_1,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_1,int,32,2) [] = { 0xfffffff2, 0xfffffff3 }; +VECT_VAR_DECL(expected_vld4_1,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_1,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld4_1,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_1,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld4_1,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_1,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld4_1,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_1,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 }; +VECT_VAR_DECL(expected_vld4_1,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld4_1,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_1,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld4_1,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_1,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld4_1,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_1,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld4_1,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_1,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld4_1,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_1,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; + +/* vld4/chunk 2. */ +VECT_VAR_DECL(expected_vld4_2,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld4_2,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 }; +VECT_VAR_DECL(expected_vld4_2,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld4_2,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_2,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld4_2,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_2,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 }; +VECT_VAR_DECL(expected_vld4_2,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_2,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld4_2,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_2,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld4_2,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld4_2,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_2,int,32,4) [] = { 0xfffffff0, 0xfffffff1, + 0xfffffff2, 0xfffffff3 }; +VECT_VAR_DECL(expected_vld4_2,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_2,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld4_2,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xfff0, 0xfff1, 0xfff2, 0xfff3 }; +VECT_VAR_DECL(expected_vld4_2,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld4_2,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_2,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld4_2,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xfff0, 0xfff1, 0xfff2, 0xfff3 }; +VECT_VAR_DECL(expected_vld4_2,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, + 0xc1600000, 0xc1500000 }; + +/* vld4/chunk 3. */ +VECT_VAR_DECL(expected_vld4_3,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xf0, 0xf1, 0xf2, 0xf3 }; +VECT_VAR_DECL(expected_vld4_3,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_3,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld4_3,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_3,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld4_3,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 }; +VECT_VAR_DECL(expected_vld4_3,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 }; +VECT_VAR_DECL(expected_vld4_3,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_3,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, + 0xaa, 0xaa, 0xaa, 0xaa }; +VECT_VAR_DECL(expected_vld4_3,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 }; +VECT_VAR_DECL(expected_vld4_3,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld4_3,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld4_3,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_3,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld4_3,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_3,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld4_3,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_3,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; +VECT_VAR_DECL(expected_vld4_3,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected_vld4_3,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33, + 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected_vld4_3,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, + 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa }; +VECT_VAR_DECL(expected_vld4_3,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, + 0xaaaaaaaa, 0xaaaaaaaa }; + +/* Declare additional input buffers as needed. */ +/* Input buffers for vld2_lane */ +VECT_VAR_DECL_INIT(buffer_vld2_lane, int, 8, 2); +VECT_VAR_DECL_INIT(buffer_vld2_lane, int, 16, 2); +VECT_VAR_DECL_INIT(buffer_vld2_lane, int, 32, 2); +VECT_VAR_DECL_INIT(buffer_vld2_lane, int, 64, 2); +VECT_VAR_DECL_INIT(buffer_vld2_lane, uint, 8, 2); +VECT_VAR_DECL_INIT(buffer_vld2_lane, uint, 16, 2); +VECT_VAR_DECL_INIT(buffer_vld2_lane, uint, 32, 2); +VECT_VAR_DECL_INIT(buffer_vld2_lane, uint, 64, 2); +VECT_VAR_DECL_INIT(buffer_vld2_lane, poly, 8, 2); +VECT_VAR_DECL_INIT(buffer_vld2_lane, poly, 16, 2); +VECT_VAR_DECL_INIT(buffer_vld2_lane, float, 32, 2); + +/* Input buffers for vld3_lane */ +VECT_VAR_DECL_INIT(buffer_vld3_lane, int, 8, 3); +VECT_VAR_DECL_INIT(buffer_vld3_lane, int, 16, 3); +VECT_VAR_DECL_INIT(buffer_vld3_lane, int, 32, 3); +VECT_VAR_DECL_INIT(buffer_vld3_lane, int, 64, 3); +VECT_VAR_DECL_INIT(buffer_vld3_lane, uint, 8, 3); +VECT_VAR_DECL_INIT(buffer_vld3_lane, uint, 16, 3); +VECT_VAR_DECL_INIT(buffer_vld3_lane, uint, 32, 3); +VECT_VAR_DECL_INIT(buffer_vld3_lane, uint, 64, 3); +VECT_VAR_DECL_INIT(buffer_vld3_lane, poly, 8, 3); +VECT_VAR_DECL_INIT(buffer_vld3_lane, poly, 16, 3); +VECT_VAR_DECL_INIT(buffer_vld3_lane, float, 32, 3); + +/* Input buffers for vld4_lane */ +VECT_VAR_DECL_INIT(buffer_vld4_lane, int, 8, 4); +VECT_VAR_DECL_INIT(buffer_vld4_lane, int, 16, 4); +VECT_VAR_DECL_INIT(buffer_vld4_lane, int, 32, 4); +VECT_VAR_DECL_INIT(buffer_vld4_lane, int, 64, 4); +VECT_VAR_DECL_INIT(buffer_vld4_lane, uint, 8, 4); +VECT_VAR_DECL_INIT(buffer_vld4_lane, uint, 16, 4); +VECT_VAR_DECL_INIT(buffer_vld4_lane, uint, 32, 4); +VECT_VAR_DECL_INIT(buffer_vld4_lane, uint, 64, 4); +VECT_VAR_DECL_INIT(buffer_vld4_lane, poly, 8, 4); +VECT_VAR_DECL_INIT(buffer_vld4_lane, poly, 16, 4); +VECT_VAR_DECL_INIT(buffer_vld4_lane, float, 32, 4); + +void exec_vldX_lane (void) +{ + /* In this case, input variables are arrays of vectors. */ +#define DECL_VLDX_LANE(T1, W, N, X) \ + VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(vector, T1, W, N, X); \ + VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(vector_src, T1, W, N, X); \ + VECT_VAR_DECL(result_bis_##X, T1, W, N)[X * N] + + /* We need to use a temporary result buffer (result_bis), because + the one used for other tests is not large enough. A subset of the + result data is moved from result_bis to result, and it is this + subset which is used to check the actual behaviour. The next + macro enables to move another chunk of data from result_bis to + result. */ + /* We also use another extra input buffer (buffer_src), which we + fill with 0xAA, and which it used to load a vector from which we + read a given lane. */ +#define TEST_VLDX_LANE(Q, T1, T2, W, N, X, L) \ + memset (VECT_VAR(buffer_src, T1, W, N), 0xAA, \ + sizeof(VECT_VAR(buffer_src, T1, W, N))); \ + \ + VECT_ARRAY_VAR(vector_src, T1, W, N, X) = \ + vld##X##Q##_##T2##W(VECT_VAR(buffer_src, T1, W, N)); \ + \ + VECT_ARRAY_VAR(vector, T1, W, N, X) = \ + /* Use dedicated init buffer, of size. X */ \ + vld##X##Q##_lane_##T2##W(VECT_VAR(buffer_vld##X##_lane, T1, W, X), \ + VECT_ARRAY_VAR(vector_src, T1, W, N, X), \ + L); \ + vst##X##Q##_##T2##W(VECT_VAR(result_bis_##X, T1, W, N), \ + VECT_ARRAY_VAR(vector, T1, W, N, X)); \ + memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis_##X, T1, W, N), \ + sizeof(VECT_VAR(result, T1, W, N))) + + /* Overwrite "result" with the contents of "result_bis"[Y]. */ +#define TEST_EXTRA_CHUNK(T1, W, N, X, Y) \ + memcpy(VECT_VAR(result, T1, W, N), \ + &(VECT_VAR(result_bis_##X, T1, W, N)[Y*N]), \ + sizeof(VECT_VAR(result, T1, W, N))); + + /* We need all variants in 64 bits, but there is no 64x2 variant. */ +#define DECL_ALL_VLDX_LANE(X) \ + DECL_VLDX_LANE(int, 8, 8, X); \ + DECL_VLDX_LANE(int, 16, 4, X); \ + DECL_VLDX_LANE(int, 32, 2, X); \ + DECL_VLDX_LANE(uint, 8, 8, X); \ + DECL_VLDX_LANE(uint, 16, 4, X); \ + DECL_VLDX_LANE(uint, 32, 2, X); \ + DECL_VLDX_LANE(poly, 8, 8, X); \ + DECL_VLDX_LANE(poly, 16, 4, X); \ + DECL_VLDX_LANE(int, 16, 8, X); \ + DECL_VLDX_LANE(int, 32, 4, X); \ + DECL_VLDX_LANE(uint, 16, 8, X); \ + DECL_VLDX_LANE(uint, 32, 4, X); \ + DECL_VLDX_LANE(poly, 16, 8, X); \ + DECL_VLDX_LANE(float, 32, 2, X); \ + DECL_VLDX_LANE(float, 32, 4, X) + + /* Add some padding to try to catch out of bound accesses. */ +#define ARRAY1(V, T, W, N) VECT_VAR_DECL(V,T,W,N)[1]={42} +#define DUMMY_ARRAY(V, T, W, N, L) \ + VECT_VAR_DECL(V,T,W,N)[N*L]={0}; \ + ARRAY1(V##_pad,T,W,N) + + /* Use the same lanes regardless of the size of the array (X), for + simplicity. */ +#define TEST_ALL_VLDX_LANE(X) \ + TEST_VLDX_LANE(, int, s, 8, 8, X, 7); \ + TEST_VLDX_LANE(, int, s, 16, 4, X, 2); \ + TEST_VLDX_LANE(, int, s, 32, 2, X, 0); \ + TEST_VLDX_LANE(, uint, u, 8, 8, X, 4); \ + TEST_VLDX_LANE(, uint, u, 16, 4, X, 3); \ + TEST_VLDX_LANE(, uint, u, 32, 2, X, 1); \ + TEST_VLDX_LANE(, poly, p, 8, 8, X, 4); \ + TEST_VLDX_LANE(, poly, p, 16, 4, X, 3); \ + TEST_VLDX_LANE(q, int, s, 16, 8, X, 6); \ + TEST_VLDX_LANE(q, int, s, 32, 4, X, 2); \ + TEST_VLDX_LANE(q, uint, u, 16, 8, X, 5); \ + TEST_VLDX_LANE(q, uint, u, 32, 4, X, 0); \ + TEST_VLDX_LANE(q, poly, p, 16, 8, X, 5); \ + TEST_VLDX_LANE(, float, f, 32, 2, X, 0); \ + TEST_VLDX_LANE(q, float, f, 32, 4, X, 2) + +#define TEST_ALL_EXTRA_CHUNKS(X, Y) \ + TEST_EXTRA_CHUNK(int, 8, 8, X, Y); \ + TEST_EXTRA_CHUNK(int, 16, 4, X, Y); \ + TEST_EXTRA_CHUNK(int, 32, 2, X, Y); \ + TEST_EXTRA_CHUNK(uint, 8, 8, X, Y); \ + TEST_EXTRA_CHUNK(uint, 16, 4, X, Y); \ + TEST_EXTRA_CHUNK(uint, 32, 2, X, Y); \ + TEST_EXTRA_CHUNK(poly, 8, 8, X, Y); \ + TEST_EXTRA_CHUNK(poly, 16, 4, X, Y); \ + TEST_EXTRA_CHUNK(int, 16, 8, X, Y); \ + TEST_EXTRA_CHUNK(int, 32, 4, X, Y); \ + TEST_EXTRA_CHUNK(uint, 16, 8, X, Y); \ + TEST_EXTRA_CHUNK(uint, 32, 4, X, Y); \ + TEST_EXTRA_CHUNK(poly, 16, 8, X, Y); \ + TEST_EXTRA_CHUNK(float, 32, 2, X, Y); \ + TEST_EXTRA_CHUNK(float, 32, 4, X, Y) + + /* Declare the temporary buffers / variables. */ + DECL_ALL_VLDX_LANE(2); + DECL_ALL_VLDX_LANE(3); + DECL_ALL_VLDX_LANE(4); + + /* Define dummy input arrays, large enough for x4 vectors. */ + DUMMY_ARRAY(buffer_src, int, 8, 8, 4); + DUMMY_ARRAY(buffer_src, int, 16, 4, 4); + DUMMY_ARRAY(buffer_src, int, 32, 2, 4); + DUMMY_ARRAY(buffer_src, uint, 8, 8, 4); + DUMMY_ARRAY(buffer_src, uint, 16, 4, 4); + DUMMY_ARRAY(buffer_src, uint, 32, 2, 4); + DUMMY_ARRAY(buffer_src, poly, 8, 8, 4); + DUMMY_ARRAY(buffer_src, poly, 16, 4, 4); + DUMMY_ARRAY(buffer_src, int, 16, 8, 4); + DUMMY_ARRAY(buffer_src, int, 32, 4, 4); + DUMMY_ARRAY(buffer_src, uint, 16, 8, 4); + DUMMY_ARRAY(buffer_src, uint, 32, 4, 4); + DUMMY_ARRAY(buffer_src, poly, 16, 8, 4); + DUMMY_ARRAY(buffer_src, float, 32, 2, 4); + DUMMY_ARRAY(buffer_src, float, 32, 4, 4); + + /* Check vld2_lane/vld2q_lane. */ + clean_results (); +#define TEST_MSG "VLD2_LANE/VLD2Q_LANE" + TEST_ALL_VLDX_LANE(2); + CHECK_RESULTS_NAMED (TEST_MSG, expected_vld2_0, " chunk 0"); + + TEST_ALL_EXTRA_CHUNKS(2, 1); + CHECK_RESULTS_NAMED (TEST_MSG, expected_vld2_1, " chunk 1"); + + /* Check vld3_lane/vld3q_lane. */ + clean_results (); +#undef TEST_MSG +#define TEST_MSG "VLD3_LANE/VLD3Q_LANE" + TEST_ALL_VLDX_LANE(3); + CHECK_RESULTS_NAMED (TEST_MSG, expected_vld3_0, " chunk 0"); + + TEST_ALL_EXTRA_CHUNKS(3, 1); + CHECK_RESULTS_NAMED (TEST_MSG, expected_vld3_1, " chunk 1"); + + TEST_ALL_EXTRA_CHUNKS(3, 2); + CHECK_RESULTS_NAMED (TEST_MSG, expected_vld3_2, " chunk 2"); + + /* Check vld4_lane/vld4q_lane. */ + clean_results (); +#undef TEST_MSG +#define TEST_MSG "VLD4_LANE/VLD4Q_LANE" + TEST_ALL_VLDX_LANE(4); + CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_0, " chunk 0"); + + TEST_ALL_EXTRA_CHUNKS(4, 1); + CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_1, " chunk 1"); + TEST_ALL_EXTRA_CHUNKS(4, 2); + + CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_2, " chunk 2"); + + TEST_ALL_EXTRA_CHUNKS(4, 3); + CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_3, " chunk 3"); +} + +int main (void) +{ + exec_vldX_lane (); + return 0; +}