From patchwork Fri Sep 18 18:37:03 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 273346 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-12.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 91889C43463 for ; Fri, 18 Sep 2020 19:08:42 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 011CF21D7F for ; Fri, 18 Sep 2020 19:08:41 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=linaro.org header.i=@linaro.org header.b="zM1ruSuI" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 011CF21D7F Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=linaro.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Received: from localhost ([::1]:47194 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1kJLkP-00061o-4c for qemu-devel@archiver.kernel.org; Fri, 18 Sep 2020 15:08:41 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:48250) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1kJLHM-0000SD-Uy for qemu-devel@nongnu.org; Fri, 18 Sep 2020 14:38:40 -0400 Received: from mail-pl1-x641.google.com ([2607:f8b0:4864:20::641]:36620) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1kJLHK-00079p-Qe for qemu-devel@nongnu.org; Fri, 18 Sep 2020 14:38:40 -0400 Received: by mail-pl1-x641.google.com with SMTP id k13so3442835plk.3 for ; Fri, 18 Sep 2020 11:38:38 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=16ObUsciA5sTLGBaYdN2/secK6wqo2MfYlYAt1+Qus8=; b=zM1ruSuIdrogJrevkujSv8/ZDVdBc3R1QH8euSWlZkwYgP+BpRujHrW7Tsy9x7hCrq 9yqbTEex2JVNY/wjPDsN42NvVwJybXTXGu5BDJPPFrrboOKzXHsrd4SbseNnbmfpbOj5 OWiz2vClFoBZzq3k+8WF5QZDZOtpmfmJVAASjeZQFLNvzlHZ5gommAhicCNrkhCTVPcG OZaz6iEW3xz3587KsBP0iDNcsrpVsBQVVjGcgH4qJD+O2Fpi11klN9jLN56WAuosgT/a m1MsMtkRRJg6xD4Av+foKYxR/84QyPvAXxlkglNvJPxSqpFRoG/1bndk+y/zz4sTCrQ0 2ULw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=16ObUsciA5sTLGBaYdN2/secK6wqo2MfYlYAt1+Qus8=; b=WHixUKKPVWVoWyDt+trIPpZcfBN49Ulx+xzQ0gECoME5jEd0/xWw7h1T3L5jE3o7j+ NENTb4CWbfa0osSVYR0b65GpzMwKlrd0mefn8D+zlvtkxkO4xoGg866oVvuFw3kiIPnB CDlTEF52IJWUL+C8+nFl8Jguz4UuOLzeUnw2vmHOVXEZ0Vo67EmqqKn02YWFN31z2rCY mXsVcdvsobdeLZjCNrT/N7eSV1H53Q36QMZrXuFywUEcgV21ck0BF4baY2W1s9WIhTDw TNtMNhAnMdb7SS7qYF1vmVlIYgUrpV2qJFvpevmiBV2GcGgWMCjnBDI4jJAWtmpVbAvD 7AiA== X-Gm-Message-State: AOAM53094E4Tn9HW+MKDs+5Gs/FLarf3X80VsRM3RYNDddpsGWvkB4GS LLjmcZYMqzXPhnyg7dfZx9j0/DJpcLld+g== X-Google-Smtp-Source: ABdhPJwO2aE/m51QbsDYVg9CnfcN479jucGK15XXN2Ef1ONeAu0s5oCQFiy1bULzfM890rVK/7QLgg== X-Received: by 2002:a17:902:8549:b029:d1:e603:af73 with SMTP id d9-20020a1709028549b02900d1e603af73mr15856813plo.60.1600454316848; Fri, 18 Sep 2020 11:38:36 -0700 (PDT) Received: from localhost.localdomain ([71.212.141.89]) by smtp.gmail.com with ESMTPSA id f4sm3680723pfj.147.2020.09.18.11.38.35 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 18 Sep 2020 11:38:36 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Subject: [PATCH v3 33/81] target/arm: Implement SVE2 WHILEGT, WHILEGE, WHILEHI, WHILEHS Date: Fri, 18 Sep 2020 11:37:03 -0700 Message-Id: <20200918183751.2787647-34-richard.henderson@linaro.org> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20200918183751.2787647-1-richard.henderson@linaro.org> References: <20200918183751.2787647-1-richard.henderson@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2607:f8b0:4864:20::641; envelope-from=richard.henderson@linaro.org; helo=mail-pl1-x641.google.com X-detected-operating-system: by eggs.gnu.org: No matching host in p0f cache. That's all we know. X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: peter.maydell@linaro.org, alex.bennee@linaro.org Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: "Qemu-devel" Rename the existing sve_while (less-than) helper to sve_whilel to make room for a new sve_whileg helper for greater-than. Signed-off-by: Richard Henderson --- v2: Use a new helper function to implement this. --- target/arm/helper-sve.h | 3 +- target/arm/sve.decode | 2 +- target/arm/sve_helper.c | 38 +++++++++++++++++++++++++- target/arm/translate-sve.c | 56 ++++++++++++++++++++++++++++---------- 4 files changed, 82 insertions(+), 17 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index 04b3ae3219..6b4ae8f98b 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -913,7 +913,8 @@ DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32) -DEF_HELPER_FLAGS_3(sve_while, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_whilel, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32) DEF_HELPER_FLAGS_4(sve_subri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_subri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index 5f76a95139..b7038f9f57 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -700,7 +700,7 @@ SINCDECP_z 00100101 .. 1010 d:1 u:1 10000 00 .... ..... @incdec2_pred CTERM 00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000 # SVE integer compare scalar count and limit -WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 1 rn:5 eq:1 rd:4 +WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 lt:1 rn:5 eq:1 rd:4 ### SVE Integer Wide Immediate - Unpredicated Group diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index 2a3dc76d87..0bb9d73cbf 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -3746,7 +3746,7 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) return sum; } -uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) +uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) { uintptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; intptr_t esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2); @@ -3772,6 +3772,42 @@ uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) return predtest_ones(d, oprsz, esz_mask); } +uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uintptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2); + uint64_t esz_mask = pred_esz_masks[esz]; + ARMPredicateReg *d = vd; + intptr_t i, invcount, oprbits; + uint64_t bits; + + if (count == 0) { + return do_zero(d, oprsz); + } + + oprbits = oprsz * 8; + tcg_debug_assert(count <= oprbits); + + bits = esz_mask; + if (oprbits & 63) { + bits &= MAKE_64BIT_MASK(0, oprbits & 63); + } + + invcount = oprbits - count; + for (i = (oprsz - 1) / 8; i > invcount / 64; --i) { + d->p[i] = bits; + bits = esz_mask; + } + + d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64); + + while (--i >= 0) { + d->p[i] = 0; + } + + return predtest_ones(d, oprsz, esz_mask); +} + /* Recursive reduction on a function; * C.f. the ARM ARM function ReducePredicated. * diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index 5091c0bc67..f1bc4c63e6 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -3121,7 +3121,14 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) TCGv_ptr ptr; unsigned desc, vsz = vec_full_reg_size(s); TCGCond cond; + uint64_t maxval; + /* Note that GE/HS has a->eq == 0 and GT/HI has a->eq == 1. */ + bool eq = a->eq == a->lt; + /* The greater-than conditions are all SVE2. */ + if (!a->lt && !dc_isar_feature(aa64_sve2, s)) { + return false; + } if (!sve_access_check(s)) { return true; } @@ -3144,22 +3151,42 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) */ t0 = tcg_temp_new_i64(); t1 = tcg_temp_new_i64(); - tcg_gen_sub_i64(t0, op1, op0); + + if (a->lt) { + tcg_gen_sub_i64(t0, op1, op0); + if (a->u) { + maxval = a->sf ? UINT64_MAX : UINT32_MAX; + cond = eq ? TCG_COND_LEU : TCG_COND_LTU; + } else { + maxval = a->sf ? INT64_MAX : INT32_MAX; + cond = eq ? TCG_COND_LE : TCG_COND_LT; + } + } else { + tcg_gen_sub_i64(t0, op0, op1); + if (a->u) { + maxval = 0; + cond = eq ? TCG_COND_GEU : TCG_COND_GTU; + } else { + maxval = a->sf ? INT64_MIN : INT32_MIN; + cond = eq ? TCG_COND_GE : TCG_COND_GT; + } + } tmax = tcg_const_i64(vsz >> a->esz); - if (a->eq) { + if (eq) { /* Equality means one more iteration. */ tcg_gen_addi_i64(t0, t0, 1); - /* If op1 is max (un)signed integer (and the only time the addition - * above could overflow), then we produce an all-true predicate by - * setting the count to the vector length. This is because the - * pseudocode is described as an increment + compare loop, and the - * max integer would always compare true. + /* + * For the less-than while, if op1 is maxval (and the only time + * the addition above could overflow), then we produce an all-true + * predicate by setting the count to the vector length. This is + * because the pseudocode is described as an increment + compare + * loop, and the maximum integer would always compare true. + * Similarly, the greater-than while has the same issue with the + * minimum integer due to the decrement + compare loop. */ - tcg_gen_movi_i64(t1, (a->sf - ? (a->u ? UINT64_MAX : INT64_MAX) - : (a->u ? UINT32_MAX : INT32_MAX))); + tcg_gen_movi_i64(t1, maxval); tcg_gen_movcond_i64(TCG_COND_EQ, t0, op1, t1, tmax, t0); } @@ -3168,9 +3195,6 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) tcg_temp_free_i64(tmax); /* Set the count to zero if the condition is false. */ - cond = (a->u - ? (a->eq ? TCG_COND_LEU : TCG_COND_LTU) - : (a->eq ? TCG_COND_LE : TCG_COND_LT)); tcg_gen_movi_i64(t1, 0); tcg_gen_movcond_i64(cond, t0, op0, op1, t0, t1); tcg_temp_free_i64(t1); @@ -3190,7 +3214,11 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) ptr = tcg_temp_new_ptr(); tcg_gen_addi_ptr(ptr, cpu_env, pred_full_reg_offset(s, a->rd)); - gen_helper_sve_while(t2, ptr, t2, t3); + if (a->lt) { + gen_helper_sve_whilel(t2, ptr, t2, t3); + } else { + gen_helper_sve_whileg(t2, ptr, t2, t3); + } do_pred_flags(t2); tcg_temp_free_ptr(ptr);