From patchwork Tue Oct 21 13:03:13 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Christophe Lyon X-Patchwork-Id: 39136 Return-Path: X-Original-To: linaro@patches.linaro.org Delivered-To: linaro@patches.linaro.org Received: from mail-wg0-f72.google.com (mail-wg0-f72.google.com [74.125.82.72]) by ip-10-151-82-157.ec2.internal (Postfix) with ESMTPS id A11FE202DB for ; Tue, 21 Oct 2014 13:12:40 +0000 (UTC) Received: by mail-wg0-f72.google.com with SMTP id m15sf781162wgh.11 for ; Tue, 21 Oct 2014 06:12:36 -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=5FjHGQ+H0J/BAaDiScpNztfwbrRI8t7sIzmy/MqQFNM=; b=D2FQqO5WOqVW7qaHmuWfrxOxkOlTSUyt4MU/oVxctPG3TWKKGYrUKy1rTilBV1LsB7 QY1Y5lkekW7W3BSk39O1D16FWeZfgmOA295//XWRZGuac3VbStVhZX21X9rhLy/GGomp shy5Etn3AYotV+cyulwDfIDj9itytb620uJwLKA61LrJ3yS87KITif0UtzLL0TD8el/q /FzsQdJzcnDSr930CDO6DAO97rhIPgfNxJqcDZlvH0IHwgg2BU179IpOXYSF9djFxZ9S ueEovXYrQ3RyTL78KxYp23w4llgSGiyG6SqLyOFiyWd63usCeVCrBR6Nf9b/9ab/BLeD 9sfw== X-Gm-Message-State: ALoCoQlzkQgpjnyn5GuW8htbRhwosviQ8vx1/K3BLaEUMS3qWnj/tVAP+6dLnBLSMg2HO29iuSvz X-Received: by 10.112.24.42 with SMTP id r10mr402055lbf.15.1413897156101; Tue, 21 Oct 2014 06:12:36 -0700 (PDT) MIME-Version: 1.0 X-BeenThere: patchwork-forward@linaro.org Received: by 10.152.23.74 with SMTP id k10ls57943laf.6.gmail; Tue, 21 Oct 2014 06:12:35 -0700 (PDT) X-Received: by 10.112.189.10 with SMTP id ge10mr34332910lbc.23.1413897155888; Tue, 21 Oct 2014 06:12:35 -0700 (PDT) Received: from mail-lb0-x22f.google.com (mail-lb0-x22f.google.com. [2a00:1450:4010:c04::22f]) by mx.google.com with ESMTPS id u14si18899371laz.45.2014.10.21.06.12.34 for (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Tue, 21 Oct 2014 06:12:34 -0700 (PDT) Received-SPF: pass (google.com: domain of patch+caf_=patchwork-forward=linaro.org@linaro.org designates 2a00:1450:4010:c04::22f as permitted sender) client-ip=2a00:1450:4010:c04::22f; Received: by mail-lb0-f175.google.com with SMTP id u10so991651lbd.34 for ; Tue, 21 Oct 2014 06:12:34 -0700 (PDT) X-Received: by 10.152.5.38 with SMTP id p6mr29810493lap.44.1413897154078; Tue, 21 Oct 2014 06:12:34 -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 c5csp494139lbz; Tue, 21 Oct 2014 06:12:33 -0700 (PDT) X-Received: by 10.66.253.105 with SMTP id zz9mr35453928pac.49.1413897152370; Tue, 21 Oct 2014 06:12:32 -0700 (PDT) Received: from sourceware.org (server1.sourceware.org. [209.132.180.131]) by mx.google.com with ESMTPS id uh7si6380705pac.156.2014.10.21.06.12.31 for (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Tue, 21 Oct 2014 06:12:32 -0700 (PDT) Received-SPF: pass (google.com: domain of gcc-patches-return-381286-patch=linaro.org@gcc.gnu.org designates 209.132.180.131 as permitted sender) client-ip=209.132.180.131; Received: (qmail 29875 invoked by alias); 21 Oct 2014 13:04:01 -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 28575 invoked by uid 89); 21 Oct 2014 13:03:44 -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-wi0-f181.google.com Received: from mail-wi0-f181.google.com (HELO mail-wi0-f181.google.com) (209.85.212.181) by sourceware.org (qpsmtpd/0.93/v0.84-503-g423c35a) with (AES128-SHA encrypted) ESMTPS; Tue, 21 Oct 2014 13:03:36 +0000 Received: by mail-wi0-f181.google.com with SMTP id hi2so1755698wib.8 for ; Tue, 21 Oct 2014 06:03:31 -0700 (PDT) X-Received: by 10.180.74.237 with SMTP id x13mr1939466wiv.6.1413896611348; Tue, 21 Oct 2014 06:03:31 -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.2.2014.10.21.06.03.29 for (version=TLSv1.2 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Tue, 21 Oct 2014 06:03:30 -0700 (PDT) From: Christophe Lyon To: gcc-patches@gcc.gnu.org Subject: [Patch ARM-AArch64/testsuite v3 21/21] Add vuzp and vzip tests. Date: Tue, 21 Oct 2014 15:03:13 +0200 Message-Id: <1413896593-26607-22-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:c04::22f 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/vuzp.c: New file. * gcc.target/aarch64/advsimd-intrinsics/vzip.c: Likewise. diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vuzp.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vuzp.c new file mode 100644 index 0000000..53f875e --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vuzp.c @@ -0,0 +1,245 @@ +#include +#include "arm-neon-ref.h" +#include "compute-ref-data.h" + +/* Expected results splitted in several chunks. */ +/* Chunk 0. */ +VECT_VAR_DECL(expected0,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, + 0xf4, 0xf5, 0xf6, 0xf7 }; +VECT_VAR_DECL(expected0,int,16,4) [] = { 0xfff0, 0xfff1, + 0xfff2, 0xfff3 }; +VECT_VAR_DECL(expected0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 }; +VECT_VAR_DECL(expected0,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected0,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, + 0xf4, 0xf5, 0xf6, 0xf7 }; +VECT_VAR_DECL(expected0,uint,16,4) [] = { 0xfff0, 0xfff1, + 0xfff2, 0xfff3 }; +VECT_VAR_DECL(expected0,uint,32,2) [] = { 0xfffffff0, + 0xfffffff1 }; +VECT_VAR_DECL(expected0,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected0,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, + 0xf4, 0xf5, 0xf6, 0xf7 }; +VECT_VAR_DECL(expected0,poly,16,4) [] = { 0xfff0, 0xfff1, + 0xfff2, 0xfff3 }; +VECT_VAR_DECL(expected0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 }; +VECT_VAR_DECL(expected0,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, + 0xf4, 0xf5, 0xf6, 0xf7, + 0xf8, 0xf9, 0xfa, 0xfb, + 0xfc, 0xfd, 0xfe, 0xff }; +VECT_VAR_DECL(expected0,int,16,8) [] = { 0xfff0, 0xfff1, + 0xfff2, 0xfff3, + 0xfff4, 0xfff5, + 0xfff6, 0xfff7 }; +VECT_VAR_DECL(expected0,int,32,4) [] = { 0xfffffff0, 0xfffffff1, + 0xfffffff2, 0xfffffff3 }; +VECT_VAR_DECL(expected0,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected0,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, + 0xf4, 0xf5, 0xf6, 0xf7, + 0xf8, 0xf9, 0xfa, 0xfb, + 0xfc, 0xfd, 0xfe, 0xff }; +VECT_VAR_DECL(expected0,uint,16,8) [] = { 0xfff0, 0xfff1, + 0xfff2, 0xfff3, + 0xfff4, 0xfff5, + 0xfff6, 0xfff7 }; +VECT_VAR_DECL(expected0,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, + 0xfffffff2, 0xfffffff3 }; +VECT_VAR_DECL(expected0,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected0,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, + 0xf4, 0xf5, 0xf6, 0xf7, + 0xf8, 0xf9, 0xfa, 0xfb, + 0xfc, 0xfd, 0xfe, 0xff }; +VECT_VAR_DECL(expected0,poly,16,8) [] = { 0xfff0, 0xfff1, + 0xfff2, 0xfff3, + 0xfff4, 0xfff5, + 0xfff6, 0xfff7 }; +VECT_VAR_DECL(expected0,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, + 0xc1600000, 0xc1500000 }; + +/* Chunk 1. */ +VECT_VAR_DECL(expected1,int,8,8) [] = { 0x11, 0x11, 0x11, 0x11, + 0x11, 0x11, 0x11, 0x11 }; +VECT_VAR_DECL(expected1,int,16,4) [] = { 0x22, 0x22, 0x22, 0x22 }; +VECT_VAR_DECL(expected1,int,32,2) [] = { 0x33, 0x33 }; +VECT_VAR_DECL(expected1,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected1,uint,8,8) [] = { 0x55, 0x55, 0x55, 0x55, + 0x55, 0x55, 0x55, 0x55 }; +VECT_VAR_DECL(expected1,uint,16,4) [] = { 0x66, 0x66, 0x66, 0x66 }; +VECT_VAR_DECL(expected1,uint,32,2) [] = { 0x77, 0x77 }; +VECT_VAR_DECL(expected1,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected1,poly,8,8) [] = { 0x55, 0x55, 0x55, 0x55, + 0x55, 0x55, 0x55, 0x55 }; +VECT_VAR_DECL(expected1,poly,16,4) [] = { 0x66, 0x66, 0x66, 0x66 }; +VECT_VAR_DECL(expected1,hfloat,32,2) [] = { 0x42066666, 0x42066666 }; +VECT_VAR_DECL(expected1,int,8,16) [] = { 0x11, 0x11, 0x11, 0x11, + 0x11, 0x11, 0x11, 0x11, + 0x11, 0x11, 0x11, 0x11, + 0x11, 0x11, 0x11, 0x11 }; +VECT_VAR_DECL(expected1,int,16,8) [] = { 0x22, 0x22, 0x22, 0x22, + 0x22, 0x22, 0x22, 0x22 }; +VECT_VAR_DECL(expected1,int,32,4) [] = { 0x33, 0x33, 0x33, 0x33 }; +VECT_VAR_DECL(expected1,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected1,uint,8,16) [] = { 0x55, 0x55, 0x55, 0x55, + 0x55, 0x55, 0x55, 0x55, + 0x55, 0x55, 0x55, 0x55, + 0x55, 0x55, 0x55, 0x55 }; +VECT_VAR_DECL(expected1,uint,16,8) [] = { 0x66, 0x66, 0x66, 0x66, + 0x66, 0x66, 0x66, 0x66 }; +VECT_VAR_DECL(expected1,uint,32,4) [] = { 0x77, 0x77, 0x77, 0x77 }; +VECT_VAR_DECL(expected1,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected1,poly,8,16) [] = { 0x55, 0x55, 0x55, 0x55, + 0x55, 0x55, 0x55, 0x55, + 0x55, 0x55, 0x55, 0x55, + 0x55, 0x55, 0x55, 0x55 }; +VECT_VAR_DECL(expected1,poly,16,8) [] = { 0x66, 0x66, 0x66, 0x66, + 0x66, 0x66, 0x66, 0x66 }; +VECT_VAR_DECL(expected1,hfloat,32,4) [] = { 0x42073333, 0x42073333, + 0x42073333, 0x42073333 }; + +#ifndef INSN_NAME +#define INSN_NAME vuzp +#define TEST_MSG "VUZP/VUZPQ" +#endif + +#define FNNAME1(NAME) exec_ ## NAME +#define FNNAME(NAME) FNNAME1(NAME) + +void FNNAME (INSN_NAME) (void) +{ + /* In this case, output variables are arrays of vectors. */ +#define DECL_VUZP(T1, W, N) \ + VECT_ARRAY_TYPE(T1, W, N, 2) VECT_ARRAY_VAR(result_vec, T1, W, N, 2); \ + VECT_VAR_DECL(result_bis, T1, W, N)[2 * 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. */ +#define TEST_VUZP(INSN, Q, T1, T2, W, N) \ + VECT_ARRAY_VAR(result_vec, T1, W, N, 2) = \ + INSN##Q##_##T2##W(VECT_VAR(vector1, T1, W, N), \ + VECT_VAR(vector2, T1, W, N)); \ + vst2##Q##_##T2##W(VECT_VAR(result_bis, T1, W, N), \ + VECT_ARRAY_VAR(result_vec, T1, W, N, 2)); \ + memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis, T1, W, N), \ + sizeof(VECT_VAR(result, T1, W, N))); + + /* Overwrite "result" with the contents of "result_bis"[X]. */ +#define TEST_EXTRA_CHUNK(T1, W, N, X) \ + memcpy(VECT_VAR(result, T1, W, N), &(VECT_VAR(result_bis, T1, W, N)[X*N]), \ + sizeof(VECT_VAR(result, T1, W, N))); + + DECL_VARIABLE_ALL_VARIANTS(vector1); + DECL_VARIABLE_ALL_VARIANTS(vector2); + + /* We don't need 64 bits variants. */ +#define DECL_ALL_VUZP() \ + DECL_VUZP(int, 8, 8); \ + DECL_VUZP(int, 16, 4); \ + DECL_VUZP(int, 32, 2); \ + DECL_VUZP(uint, 8, 8); \ + DECL_VUZP(uint, 16, 4); \ + DECL_VUZP(uint, 32, 2); \ + DECL_VUZP(poly, 8, 8); \ + DECL_VUZP(poly, 16, 4); \ + DECL_VUZP(float, 32, 2); \ + DECL_VUZP(int, 8, 16); \ + DECL_VUZP(int, 16, 8); \ + DECL_VUZP(int, 32, 4); \ + DECL_VUZP(uint, 8, 16); \ + DECL_VUZP(uint, 16, 8); \ + DECL_VUZP(uint, 32, 4); \ + DECL_VUZP(poly, 8, 16); \ + DECL_VUZP(poly, 16, 8); \ + DECL_VUZP(float, 32, 4) + + DECL_ALL_VUZP(); + + /* Initialize input "vector" from "buffer". */ + TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer); + VLOAD(vector1, buffer, , float, f, 32, 2); + VLOAD(vector1, buffer, q, float, f, 32, 4); + + /* Choose arbitrary initialization values. */ + VDUP(vector2, , int, s, 8, 8, 0x11); + VDUP(vector2, , int, s, 16, 4, 0x22); + VDUP(vector2, , int, s, 32, 2, 0x33); + VDUP(vector2, , uint, u, 8, 8, 0x55); + VDUP(vector2, , uint, u, 16, 4, 0x66); + VDUP(vector2, , uint, u, 32, 2, 0x77); + VDUP(vector2, , poly, p, 8, 8, 0x55); + VDUP(vector2, , poly, p, 16, 4, 0x66); + VDUP(vector2, , float, f, 32, 2, 33.6f); + + VDUP(vector2, q, int, s, 8, 16, 0x11); + VDUP(vector2, q, int, s, 16, 8, 0x22); + VDUP(vector2, q, int, s, 32, 4, 0x33); + VDUP(vector2, q, uint, u, 8, 16, 0x55); + VDUP(vector2, q, uint, u, 16, 8, 0x66); + VDUP(vector2, q, uint, u, 32, 4, 0x77); + VDUP(vector2, q, poly, p, 8, 16, 0x55); + VDUP(vector2, q, poly, p, 16, 8, 0x66); + VDUP(vector2, q, float, f, 32, 4, 33.8f); + +#define TEST_ALL_VUZP(INSN) \ + TEST_VUZP(INSN, , int, s, 8, 8); \ + TEST_VUZP(INSN, , int, s, 16, 4); \ + TEST_VUZP(INSN, , int, s, 32, 2); \ + TEST_VUZP(INSN, , uint, u, 8, 8); \ + TEST_VUZP(INSN, , uint, u, 16, 4); \ + TEST_VUZP(INSN, , uint, u, 32, 2); \ + TEST_VUZP(INSN, , poly, p, 8, 8); \ + TEST_VUZP(INSN, , poly, p, 16, 4); \ + TEST_VUZP(INSN, , float, f, 32, 2); \ + TEST_VUZP(INSN, q, int, s, 8, 16); \ + TEST_VUZP(INSN, q, int, s, 16, 8); \ + TEST_VUZP(INSN, q, int, s, 32, 4); \ + TEST_VUZP(INSN, q, uint, u, 8, 16); \ + TEST_VUZP(INSN, q, uint, u, 16, 8); \ + TEST_VUZP(INSN, q, uint, u, 32, 4); \ + TEST_VUZP(INSN, q, poly, p, 8, 16); \ + TEST_VUZP(INSN, q, poly, p, 16, 8); \ + TEST_VUZP(INSN, q, float, f, 32, 4) + +#define TEST_ALL_EXTRA_CHUNKS() \ + TEST_EXTRA_CHUNK(int, 8, 8, 1); \ + TEST_EXTRA_CHUNK(int, 16, 4, 1); \ + TEST_EXTRA_CHUNK(int, 32, 2, 1); \ + TEST_EXTRA_CHUNK(uint, 8, 8, 1); \ + TEST_EXTRA_CHUNK(uint, 16, 4, 1); \ + TEST_EXTRA_CHUNK(uint, 32, 2, 1); \ + TEST_EXTRA_CHUNK(poly, 8, 8, 1); \ + TEST_EXTRA_CHUNK(poly, 16, 4, 1); \ + TEST_EXTRA_CHUNK(float, 32, 2, 1); \ + TEST_EXTRA_CHUNK(int, 8, 16, 1); \ + TEST_EXTRA_CHUNK(int, 16, 8, 1); \ + TEST_EXTRA_CHUNK(int, 32, 4, 1); \ + TEST_EXTRA_CHUNK(uint, 8, 16, 1); \ + TEST_EXTRA_CHUNK(uint, 16, 8, 1); \ + TEST_EXTRA_CHUNK(uint, 32, 4, 1); \ + TEST_EXTRA_CHUNK(poly, 8, 16, 1); \ + TEST_EXTRA_CHUNK(poly, 16, 8, 1); \ + TEST_EXTRA_CHUNK(float, 32, 4, 1) + + clean_results (); + + /* Execute the tests. */ + TEST_ALL_VUZP(INSN_NAME); + + CHECK_RESULTS_NAMED (TEST_MSG, expected0, "(chunk 0)"); + + TEST_ALL_EXTRA_CHUNKS(); + CHECK_RESULTS_NAMED (TEST_MSG, expected1, "(chunk 1)"); +} + +int main (void) +{ + FNNAME (INSN_NAME) (); + + return 0; +} diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vzip.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vzip.c new file mode 100644 index 0000000..a1f1eee --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vzip.c @@ -0,0 +1,243 @@ +#include +#include "arm-neon-ref.h" +#include "compute-ref-data.h" + +/* Expected results splitted in several chunks. */ +/* Chunk 0. */ +VECT_VAR_DECL(expected0,int,8,8) [] = { 0xf0, 0xf4, 0x11, 0x11, + 0xf1, 0xf5, 0x11, 0x11 }; +VECT_VAR_DECL(expected0,int,16,4) [] = { 0xfff0, 0xfff2, + 0x22, 0x22 }; +VECT_VAR_DECL(expected0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 }; +VECT_VAR_DECL(expected0,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected0,uint,8,8) [] = { 0xf0, 0xf4, 0x55, 0x55, + 0xf1, 0xf5, 0x55, 0x55 }; +VECT_VAR_DECL(expected0,uint,16,4) [] = { 0xfff0, 0xfff2, + 0x66, 0x66 }; +VECT_VAR_DECL(expected0,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 }; +VECT_VAR_DECL(expected0,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected0,poly,8,8) [] = { 0xf0, 0xf4, 0x55, 0x55, + 0xf1, 0xf5, 0x55, 0x55 }; +VECT_VAR_DECL(expected0,poly,16,4) [] = { 0xfff0, 0xfff2, + 0x66, 0x66 }; +VECT_VAR_DECL(expected0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 }; +VECT_VAR_DECL(expected0,int,8,16) [] = { 0xf0, 0xf8, 0x11, 0x11, + 0xf1, 0xf9, 0x11, 0x11, + 0xf2, 0xfa, 0x11, 0x11, + 0xf3, 0xfb, 0x11, 0x11 }; +VECT_VAR_DECL(expected0,int,16,8) [] = { 0xfff0, 0xfff4, 0x22, 0x22, + 0xfff1, 0xfff5, 0x22, 0x22 }; +VECT_VAR_DECL(expected0,int,32,4) [] = { 0xfffffff0, 0xfffffff2, + 0x33, 0x33 }; +VECT_VAR_DECL(expected0,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected0,uint,8,16) [] = { 0xf0, 0xf8, 0x55, 0x55, + 0xf1, 0xf9, 0x55, 0x55, + 0xf2, 0xfa, 0x55, 0x55, + 0xf3, 0xfb, 0x55, 0x55 }; +VECT_VAR_DECL(expected0,uint,16,8) [] = { 0xfff0, 0xfff4, 0x66, 0x66, + 0xfff1, 0xfff5, 0x66, 0x66 }; +VECT_VAR_DECL(expected0,uint,32,4) [] = { 0xfffffff0, 0xfffffff2, + 0x77, 0x77 }; +VECT_VAR_DECL(expected0,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected0,poly,8,16) [] = { 0xf0, 0xf8, 0x55, 0x55, + 0xf1, 0xf9, 0x55, 0x55, + 0xf2, 0xfa, 0x55, 0x55, + 0xf3, 0xfb, 0x55, 0x55 }; +VECT_VAR_DECL(expected0,poly,16,8) [] = { 0xfff0, 0xfff4, 0x66, 0x66, + 0xfff1, 0xfff5, 0x66, 0x66 }; +VECT_VAR_DECL(expected0,hfloat,32,4) [] = { 0xc1800000, 0xc1600000, + 0x42073333, 0x42073333 }; + +/* Chunk 1. */ +VECT_VAR_DECL(expected1,int,8,8) [] = { 0xf2, 0xf6, 0x11, 0x11, + 0xf3, 0xf7, 0x11, 0x11 }; +VECT_VAR_DECL(expected1,int,16,4) [] = { 0xfff1, 0xfff3, + 0x22, 0x22 }; +VECT_VAR_DECL(expected1,int,32,2) [] = { 0x33, 0x33 }; +VECT_VAR_DECL(expected1,int,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected1,uint,8,8) [] = { 0xf2, 0xf6, 0x55, 0x55, + 0xf3, 0xf7, 0x55, 0x55 }; +VECT_VAR_DECL(expected1,uint,16,4) [] = { 0xfff1, 0xfff3, + 0x66, 0x66 }; +VECT_VAR_DECL(expected1,uint,32,2) [] = { 0x77, 0x77 }; +VECT_VAR_DECL(expected1,uint,64,1) [] = { 0x3333333333333333 }; +VECT_VAR_DECL(expected1,poly,8,8) [] = { 0xf2, 0xf6, 0x55, 0x55, + 0xf3, 0xf7, 0x55, 0x55 }; +VECT_VAR_DECL(expected1,poly,16,4) [] = { 0xfff1, 0xfff3, + 0x66, 0x66 }; +VECT_VAR_DECL(expected1,hfloat,32,2) [] = { 0x42066666, 0x42066666 }; +VECT_VAR_DECL(expected1,int,8,16) [] = { 0xf4, 0xfc, 0x11, 0x11, + 0xf5, 0xfd, 0x11, 0x11, + 0xf6, 0xfe, 0x11, 0x11, + 0xf7, 0xff, 0x11, 0x11 }; +VECT_VAR_DECL(expected1,int,16,8) [] = { 0xfff2, 0xfff6, 0x22, 0x22, + 0xfff3, 0xfff7, 0x22, 0x22 }; +VECT_VAR_DECL(expected1,int,32,4) [] = { 0xfffffff1, 0xfffffff3, + 0x33, 0x33 }; +VECT_VAR_DECL(expected1,int,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected1,uint,8,16) [] = { 0xf4, 0xfc, 0x55, 0x55, + 0xf5, 0xfd, 0x55, 0x55, + 0xf6, 0xfe, 0x55, 0x55, + 0xf7, 0xff, 0x55, 0x55 }; +VECT_VAR_DECL(expected1,uint,16,8) [] = { 0xfff2, 0xfff6, 0x66, 0x66, + 0xfff3, 0xfff7, 0x66, 0x66 }; +VECT_VAR_DECL(expected1,uint,32,4) [] = { 0xfffffff1, 0xfffffff3, + 0x77, 0x77 }; +VECT_VAR_DECL(expected1,uint,64,2) [] = { 0x3333333333333333, + 0x3333333333333333 }; +VECT_VAR_DECL(expected1,poly,8,16) [] = { 0xf4, 0xfc, 0x55, 0x55, + 0xf5, 0xfd, 0x55, 0x55, + 0xf6, 0xfe, 0x55, 0x55, + 0xf7, 0xff, 0x55, 0x55 }; +VECT_VAR_DECL(expected1,poly,16,8) [] = { 0xfff2, 0xfff6, 0x66, 0x66, + 0xfff3, 0xfff7, 0x66, 0x66 }; +VECT_VAR_DECL(expected1,hfloat,32,4) [] = { 0xc1700000, 0xc1500000, + 0x42073333, 0x42073333 }; + +#ifndef INSN_NAME +#define INSN_NAME vzip +#define TEST_MSG "VZIP/VZIPQ" +#endif + +#define FNNAME1(NAME) exec_ ## NAME +#define FNNAME(NAME) FNNAME1(NAME) + +void FNNAME (INSN_NAME) (void) +{ + /* In this case, output variables are arrays of vectors. */ +#define DECL_VZIP(T1, W, N) \ + VECT_ARRAY_TYPE(T1, W, N, 2) VECT_ARRAY_VAR(result_vec, T1, W, N, 2); \ + VECT_VAR_DECL(result_bis, T1, W, N)[2 * 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. */ +#define TEST_VZIP(INSN, Q, T1, T2, W, N) \ + VECT_ARRAY_VAR(result_vec, T1, W, N, 2) = \ + INSN##Q##_##T2##W(VECT_VAR(vector1, T1, W, N), \ + VECT_VAR(vector2, T1, W, N)); \ + vst2##Q##_##T2##W(VECT_VAR(result_bis, T1, W, N), \ + VECT_ARRAY_VAR(result_vec, T1, W, N, 2)); \ + memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis, T1, W, N), \ + sizeof(VECT_VAR(result, T1, W, N))); + + /* Overwrite "result" with the contents of "result_bis"[X]. */ +#define TEST_EXTRA_CHUNK(T1, W, N, X) \ + memcpy(VECT_VAR(result, T1, W, N), &(VECT_VAR(result_bis, T1, W, N)[X*N]), \ + sizeof(VECT_VAR(result, T1, W, N))); + + DECL_VARIABLE_ALL_VARIANTS(vector1); + DECL_VARIABLE_ALL_VARIANTS(vector2); + + /* We don't need 64 bits variants. */ +#define DECL_ALL_VZIP() \ + DECL_VZIP(int, 8, 8); \ + DECL_VZIP(int, 16, 4); \ + DECL_VZIP(int, 32, 2); \ + DECL_VZIP(uint, 8, 8); \ + DECL_VZIP(uint, 16, 4); \ + DECL_VZIP(uint, 32, 2); \ + DECL_VZIP(poly, 8, 8); \ + DECL_VZIP(poly, 16, 4); \ + DECL_VZIP(float, 32, 2); \ + DECL_VZIP(int, 8, 16); \ + DECL_VZIP(int, 16, 8); \ + DECL_VZIP(int, 32, 4); \ + DECL_VZIP(uint, 8, 16); \ + DECL_VZIP(uint, 16, 8); \ + DECL_VZIP(uint, 32, 4); \ + DECL_VZIP(poly, 8, 16); \ + DECL_VZIP(poly, 16, 8); \ + DECL_VZIP(float, 32, 4) + + DECL_ALL_VZIP(); + + /* Initialize input "vector" from "buffer". */ + TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer); + VLOAD(vector1, buffer, , float, f, 32, 2); + VLOAD(vector1, buffer, q, float, f, 32, 4); + + /* Choose arbitrary initialization values. */ + VDUP(vector2, , int, s, 8, 8, 0x11); + VDUP(vector2, , int, s, 16, 4, 0x22); + VDUP(vector2, , int, s, 32, 2, 0x33); + VDUP(vector2, , uint, u, 8, 8, 0x55); + VDUP(vector2, , uint, u, 16, 4, 0x66); + VDUP(vector2, , uint, u, 32, 2, 0x77); + VDUP(vector2, , poly, p, 8, 8, 0x55); + VDUP(vector2, , poly, p, 16, 4, 0x66); + VDUP(vector2, , float, f, 32, 2, 33.6f); + + VDUP(vector2, q, int, s, 8, 16, 0x11); + VDUP(vector2, q, int, s, 16, 8, 0x22); + VDUP(vector2, q, int, s, 32, 4, 0x33); + VDUP(vector2, q, uint, u, 8, 16, 0x55); + VDUP(vector2, q, uint, u, 16, 8, 0x66); + VDUP(vector2, q, uint, u, 32, 4, 0x77); + VDUP(vector2, q, poly, p, 8, 16, 0x55); + VDUP(vector2, q, poly, p, 16, 8, 0x66); + VDUP(vector2, q, float, f, 32, 4, 33.8f); + +#define TEST_ALL_VZIP(INSN) \ + TEST_VZIP(INSN, , int, s, 8, 8); \ + TEST_VZIP(INSN, , int, s, 16, 4); \ + TEST_VZIP(INSN, , int, s, 32, 2); \ + TEST_VZIP(INSN, , uint, u, 8, 8); \ + TEST_VZIP(INSN, , uint, u, 16, 4); \ + TEST_VZIP(INSN, , uint, u, 32, 2); \ + TEST_VZIP(INSN, , poly, p, 8, 8); \ + TEST_VZIP(INSN, , poly, p, 16, 4); \ + TEST_VZIP(INSN, , float, f, 32, 2); \ + TEST_VZIP(INSN, q, int, s, 8, 16); \ + TEST_VZIP(INSN, q, int, s, 16, 8); \ + TEST_VZIP(INSN, q, int, s, 32, 4); \ + TEST_VZIP(INSN, q, uint, u, 8, 16); \ + TEST_VZIP(INSN, q, uint, u, 16, 8); \ + TEST_VZIP(INSN, q, uint, u, 32, 4); \ + TEST_VZIP(INSN, q, poly, p, 8, 16); \ + TEST_VZIP(INSN, q, poly, p, 16, 8); \ + TEST_VZIP(INSN, q, float, f, 32, 4) + +#define TEST_ALL_EXTRA_CHUNKS() \ + TEST_EXTRA_CHUNK(int, 8, 8, 1); \ + TEST_EXTRA_CHUNK(int, 16, 4, 1); \ + TEST_EXTRA_CHUNK(int, 32, 2, 1); \ + TEST_EXTRA_CHUNK(uint, 8, 8, 1); \ + TEST_EXTRA_CHUNK(uint, 16, 4, 1); \ + TEST_EXTRA_CHUNK(uint, 32, 2, 1); \ + TEST_EXTRA_CHUNK(poly, 8, 8, 1); \ + TEST_EXTRA_CHUNK(poly, 16, 4, 1); \ + TEST_EXTRA_CHUNK(float, 32, 2, 1); \ + TEST_EXTRA_CHUNK(int, 8, 16, 1); \ + TEST_EXTRA_CHUNK(int, 16, 8, 1); \ + TEST_EXTRA_CHUNK(int, 32, 4, 1); \ + TEST_EXTRA_CHUNK(uint, 8, 16, 1); \ + TEST_EXTRA_CHUNK(uint, 16, 8, 1); \ + TEST_EXTRA_CHUNK(uint, 32, 4, 1); \ + TEST_EXTRA_CHUNK(poly, 8, 16, 1); \ + TEST_EXTRA_CHUNK(poly, 16, 8, 1); \ + TEST_EXTRA_CHUNK(float, 32, 4, 1) + + clean_results (); + + /* Execute the tests. */ + TEST_ALL_VZIP(INSN_NAME); + + CHECK_RESULTS_NAMED (TEST_MSG, expected0, "(chunk 0)"); + + TEST_ALL_EXTRA_CHUNKS(); + CHECK_RESULTS_NAMED (TEST_MSG, expected1, "(chunk 1)"); +} + +int main (void) +{ + FNNAME (INSN_NAME) (); + + return 0; +}