From patchwork Wed Apr 26 00:42:27 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Taylor Simpson X-Patchwork-Id: 13223954 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org 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 smtp.lore.kernel.org (Postfix) with ESMTPS id 89F7DC77B61 for ; Wed, 26 Apr 2023 00:46:51 +0000 (UTC) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1prTFo-0000cU-Tg; Tue, 25 Apr 2023 20:43:29 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1prTFm-0000OU-GL for qemu-devel@nongnu.org; Tue, 25 Apr 2023 20:43:26 -0400 Received: from mx0b-0031df01.pphosted.com ([205.220.180.131]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1prTF9-0006PZ-Cg for qemu-devel@nongnu.org; Tue, 25 Apr 2023 20:43:26 -0400 Received: from pps.filterd (m0279871.ppops.net [127.0.0.1]) by mx0a-0031df01.pphosted.com (8.17.1.19/8.17.1.19) with ESMTP id 33Q0elkc016628; Wed, 26 Apr 2023 00:42:37 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=quicinc.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-type : content-transfer-encoding; s=qcppdkim1; bh=/nfPv/TvobWq4Kqpip6qMM0TTe91TZpql8EgzSt29zQ=; b=aDJAfPflk7ZQ7pAj8Py+QLziiYHRuVvzBl0/9h6cDEx3/6fIdaWF6KjoDbsrgPUncXLD b0BqlOTr9gZoNJcPxB1F8oYjtN98Ua3QDyNwJyiQnooUFCJxStytoBmm4aEUBY1A0rkZ a6J+ir+sL1AVLvO2P+x7MrFYd/1pYR5VxTRtupNm9TrtsXfuOfuayS3oXWeATZ22B8l+ S3W+fV0JARJs6DczStx3chBfBCCxDQ/VmYJMdnQbWzpDbDgoravToqKkmK1zkyQmt5V5 C1y01lnKkmXqfwgheGfsuQ8f7KOGJ2V3dR6hnZMn/QQr0EZdmIhYQxxguodS3tcN9uW2 IA== Received: from nalasppmta03.qualcomm.com (Global_NAT1.qualcomm.com [129.46.96.20]) by mx0a-0031df01.pphosted.com (PPS) with ESMTPS id 3q5qv6vtgq-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Wed, 26 Apr 2023 00:42:37 +0000 Received: from pps.filterd (NALASPPMTA03.qualcomm.com [127.0.0.1]) by NALASPPMTA03.qualcomm.com (8.17.1.5/8.17.1.5) with ESMTP id 33Q0gaC3017535; Wed, 26 Apr 2023 00:42:36 GMT Received: from pps.reinject (localhost [127.0.0.1]) by NALASPPMTA03.qualcomm.com (PPS) with ESMTPS id 3q48nm4ycw-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Wed, 26 Apr 2023 00:42:36 +0000 Received: from NALASPPMTA03.qualcomm.com (NALASPPMTA03.qualcomm.com [127.0.0.1]) by pps.reinject (8.17.1.5/8.17.1.5) with ESMTP id 33Q0gaut017524; Wed, 26 Apr 2023 00:42:36 GMT Received: from hu-devc-sd-u20-a-1.qualcomm.com (hu-tsimpson-lv.qualcomm.com [10.47.204.221]) by NALASPPMTA03.qualcomm.com (PPS) with ESMTPS id 33Q0gZNs017522 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Wed, 26 Apr 2023 00:42:36 +0000 Received: by hu-devc-sd-u20-a-1.qualcomm.com (Postfix, from userid 47164) id A0E73666; Tue, 25 Apr 2023 17:42:35 -0700 (PDT) From: Taylor Simpson To: qemu-devel@nongnu.org Cc: tsimpson@quicinc.com, richard.henderson@linaro.org, philmd@linaro.org, ale@rev.ng, anjo@rev.ng, bcain@quicinc.com, quic_mathbern@quicinc.com Subject: [PATCH 12/21] Hexagon (target/hexagon) Short-circuit packet predicate writes Date: Tue, 25 Apr 2023 17:42:27 -0700 Message-Id: <20230426004234.1319401-3-tsimpson@quicinc.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230426004234.1319401-1-tsimpson@quicinc.com> References: <20230426004234.1319401-1-tsimpson@quicinc.com> MIME-Version: 1.0 X-QCInternal: smtphost X-QCInternal: smtphost X-Proofpoint-Virus-Version: vendor=nai engine=6200 definitions=5800 signatures=585085 X-Proofpoint-Virus-Version: vendor=nai engine=6200 definitions=5800 signatures=585085 X-Proofpoint-GUID: r3zK3_bMi0BfsZCXK3XQx8o0_m79-k2c X-Proofpoint-ORIG-GUID: r3zK3_bMi0BfsZCXK3XQx8o0_m79-k2c X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.254,Aquarius:18.0.942,Hydra:6.0.573,FMLib:17.11.170.22 definitions=2023-04-25_11,2023-04-25_01,2023-02-09_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 clxscore=1015 spamscore=0 adultscore=0 impostorscore=0 lowpriorityscore=0 mlxlogscore=954 bulkscore=0 mlxscore=0 suspectscore=0 malwarescore=0 priorityscore=1501 phishscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2303200000 definitions=main-2304260004 Received-SPF: pass client-ip=205.220.180.131; envelope-from=tsimpson@qualcomm.com; helo=mx0b-0031df01.pphosted.com X-Spam_score_int: -17 X-Spam_score: -1.8 X-Spam_bar: - X-Spam_report: (-1.8 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org In certain cases, we can avoid the overhead of writing to hex_new_pred_value and write directly to hex_pred. We consider predicate reads/writes when computing ctx->need_commit. The get_result_pred() function uses this field to decide between hex_new_pred_value and hex_pred. Then, we can early-exit from gen_pred_writes. Signed-off-by: Taylor Simpson Reviewed-by: Richard Henderson --- target/hexagon/genptr.h | 1 + target/hexagon/genptr.c | 15 ++++++++++++--- target/hexagon/translate.c | 14 +++++++++++--- 3 files changed, 24 insertions(+), 6 deletions(-) diff --git a/target/hexagon/genptr.h b/target/hexagon/genptr.h index 420867f934..e11ccc2358 100644 --- a/target/hexagon/genptr.h +++ b/target/hexagon/genptr.h @@ -35,6 +35,7 @@ void gen_store4i(TCGv_env cpu_env, TCGv vaddr, int32_t src, uint32_t slot); void gen_store8i(TCGv_env cpu_env, TCGv vaddr, int64_t src, uint32_t slot); TCGv gen_read_reg(TCGv result, int num); TCGv gen_read_preg(TCGv pred, uint8_t num); +TCGv get_result_pred(DisasContext *ctx, int pnum); void gen_log_reg_write(DisasContext *ctx, int rnum, TCGv val); void gen_log_pred_write(DisasContext *ctx, int pnum, TCGv val); void gen_set_usr_field(DisasContext *ctx, int field, TCGv val); diff --git a/target/hexagon/genptr.c b/target/hexagon/genptr.c index 9431beebc3..da68d19ed3 100644 --- a/target/hexagon/genptr.c +++ b/target/hexagon/genptr.c @@ -110,8 +110,18 @@ static void gen_log_reg_write_pair(DisasContext *ctx, int rnum, TCGv_i64 val) gen_log_reg_write(ctx, rnum + 1, val32); } +TCGv get_result_pred(DisasContext *ctx, int pnum) +{ + if (ctx->need_commit) { + return hex_new_pred_value[pnum]; + } else { + return hex_pred[pnum]; + } +} + void gen_log_pred_write(DisasContext *ctx, int pnum, TCGv val) { + TCGv pred = get_result_pred(ctx, pnum); TCGv base_val = tcg_temp_new(); tcg_gen_andi_tl(base_val, val, 0xff); @@ -124,10 +134,9 @@ void gen_log_pred_write(DisasContext *ctx, int pnum, TCGv val) * straight assignment. Otherwise, do an and. */ if (!test_bit(pnum, ctx->pregs_written)) { - tcg_gen_mov_tl(hex_new_pred_value[pnum], base_val); + tcg_gen_mov_tl(pred, base_val); } else { - tcg_gen_and_tl(hex_new_pred_value[pnum], - hex_new_pred_value[pnum], base_val); + tcg_gen_and_tl(pred, pred, base_val); } if (HEX_DEBUG) { tcg_gen_ori_tl(hex_pred_written, hex_pred_written, 1 << pnum); diff --git a/target/hexagon/translate.c b/target/hexagon/translate.c index a87f7e7130..07ed36f6a8 100644 --- a/target/hexagon/translate.c +++ b/target/hexagon/translate.c @@ -386,6 +386,14 @@ static bool need_commit(DisasContext *ctx) } } + /* Check for overlap between predicate reads and writes */ + for (int i = 0; i < ctx->preg_log_idx; i++) { + int pnum = ctx->preg_log[i]; + if (test_bit(pnum, ctx->pregs_read)) { + return true; + } + } + return false; } @@ -503,7 +511,7 @@ static void gen_start_packet(DisasContext *ctx) * Preload the predicated pred registers into hex_new_pred_value[pred_num] * Only endloop instructions conditionally write to pred registers */ - if (pkt->pkt_has_endloop) { + if (ctx->need_commit && pkt->pkt_has_endloop) { for (int i = 0; i < ctx->preg_log_idx; i++) { int pred_num = ctx->preg_log[i]; tcg_gen_mov_tl(hex_new_pred_value[pred_num], hex_pred[pred_num]); @@ -619,8 +627,8 @@ static void gen_reg_writes(DisasContext *ctx) static void gen_pred_writes(DisasContext *ctx) { - /* Early exit if the log is empty */ - if (!ctx->preg_log_idx) { + /* Early exit if not needed or the log is empty */ + if (!ctx->need_commit || !ctx->preg_log_idx) { return; }