From patchwork Tue Mar 7 05:34:31 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Taylor Simpson X-Patchwork-Id: 13162803 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 DA17DC678DB for ; Tue, 7 Mar 2023 05:35:50 +0000 (UTC) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1pZPyZ-0006lq-AQ; Tue, 07 Mar 2023 00:35:03 -0500 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 1pZPyN-0006XE-8E for qemu-devel@nongnu.org; Tue, 07 Mar 2023 00:34:53 -0500 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 1pZPyJ-0006Z9-Gx for qemu-devel@nongnu.org; Tue, 07 Mar 2023 00:34:51 -0500 Received: from pps.filterd (m0279868.ppops.net [127.0.0.1]) by mx0a-0031df01.pphosted.com (8.17.1.19/8.17.1.19) with ESMTP id 326McPvw022029; Tue, 7 Mar 2023 05:34:46 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=dScYJt0u2ueJeaV/bE7zmVLbnYTHqzemw+GFu4lEWr8=; b=ZWKtQgXnSvDWjWuoEPzYv/UX+0fLx1NRQ7Dgg3fBADoxbk4QZmr1FWI9w+QjTdboWF0/ FLBHUNU/FlOt0cZSVU+yjqbUsAmGqI4M7FyuaSHP+Cq4vaQow2TyCUgLzn+7sku9jp5R PHjrNx5L+qSkfUihrdym8h5ZP2qO4eIIKy0rkpKmWHLGrKYA+rfFnHAAiNo/KAFcAmZv XHQwxQN1YGAIff6Ckg3vQLdE7hopwifR4VM9LZmJbsj4M56JPscUD3++uHtO732iSQMv O0Kdv+NtkvOBKbbebhFNisnqggg7PEcIVlwxkdaZa0LMKF8QxhK/+wHDU8p4eDA6UBgA Qg== Received: from nalasppmta01.qualcomm.com (Global_NAT1.qualcomm.com [129.46.96.20]) by mx0a-0031df01.pphosted.com (PPS) with ESMTPS id 3p5rqjru2u-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Tue, 07 Mar 2023 05:34:46 +0000 Received: from pps.filterd (NALASPPMTA01.qualcomm.com [127.0.0.1]) by NALASPPMTA01.qualcomm.com (8.17.1.5/8.17.1.5) with ESMTP id 3275Yis2000546; Tue, 7 Mar 2023 05:34:45 GMT Received: from pps.reinject (localhost [127.0.0.1]) by NALASPPMTA01.qualcomm.com (PPS) with ESMTPS id 3p4fhbm8nh-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Tue, 07 Mar 2023 05:34:44 +0000 Received: from NALASPPMTA01.qualcomm.com (NALASPPMTA01.qualcomm.com [127.0.0.1]) by pps.reinject (8.17.1.5/8.17.1.5) with ESMTP id 3275Yh1t000514; Tue, 7 Mar 2023 05:34:43 GMT Received: from hu-devc-sd-u20-a-1.qualcomm.com (hu-tsimpson-lv.qualcomm.com [10.47.204.221]) by NALASPPMTA01.qualcomm.com (PPS) with ESMTPS id 3275Yh9c000508 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Tue, 07 Mar 2023 05:34:43 +0000 Received: by hu-devc-sd-u20-a-1.qualcomm.com (Postfix, from userid 47164) id 9CB15A77; Mon, 6 Mar 2023 21:34:42 -0800 (PST) From: Taylor Simpson To: qemu-devel@nongnu.org Cc: tsimpson@quicinc.com, richard.henderson@linaro.org, philmd@linaro.org, peter.maydell@linaro.org, bcain@quicinc.com, quic_mathbern@quicinc.com, stefanha@redhat.com, ale@rev.ng, anjo@rev.ng Subject: [PULL 10/17] Hexagon (target/hexagon) Analyze packet for HVX Date: Mon, 6 Mar 2023 21:34:31 -0800 Message-Id: <20230307053438.2416629-11-tsimpson@quicinc.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230307053438.2416629-1-tsimpson@quicinc.com> References: <20230307053438.2416629-1-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-ORIG-GUID: 4ylsx4ppPKuyp7flaPBCBSlUFpZL_87_ X-Proofpoint-GUID: 4ylsx4ppPKuyp7flaPBCBSlUFpZL_87_ X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.219,Aquarius:18.0.942,Hydra:6.0.573,FMLib:17.11.170.22 definitions=2023-03-06_14,2023-03-06_01,2023-02-09_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 malwarescore=0 phishscore=0 priorityscore=1501 clxscore=1015 lowpriorityscore=0 adultscore=0 mlxscore=0 spamscore=0 suspectscore=0 bulkscore=0 impostorscore=0 mlxlogscore=527 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2212070000 definitions=main-2303070049 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 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 Extend the analyze_ functions for HVX vector and predicate writes Remove calls to ctx_log_vreg_write[_pair] from gen_tcg_funcs.py During gen_start_packet, reload the predicated HVX registers into fugure_VRegs and tmp_VRegs Signed-off-by: Taylor Simpson Reviewed-by: Anton Johansson Message-Id: <20230307025828.1612809-8-tsimpson@quicinc.com> --- target/hexagon/translate.h | 14 ++++++++------ target/hexagon/translate.c | 30 +++++++++++++++++++++++++++++ target/hexagon/gen_analyze_funcs.py | 17 +++++++++++++--- target/hexagon/gen_tcg_funcs.py | 18 ----------------- 4 files changed, 52 insertions(+), 27 deletions(-) diff --git a/target/hexagon/translate.h b/target/hexagon/translate.h index 34368b2186..765f2c6a22 100644 --- a/target/hexagon/translate.h +++ b/target/hexagon/translate.h @@ -54,6 +54,8 @@ typedef struct DisasContext { DECLARE_BITMAP(vregs_updated_tmp, NUM_VREGS); DECLARE_BITMAP(vregs_updated, NUM_VREGS); DECLARE_BITMAP(vregs_select, NUM_VREGS); + DECLARE_BITMAP(predicated_future_vregs, NUM_VREGS); + DECLARE_BITMAP(predicated_tmp_vregs, NUM_VREGS); int qreg_log[NUM_QREGS]; bool qreg_is_predicated[NUM_QREGS]; int qreg_log_idx; @@ -99,12 +101,6 @@ static inline void ctx_log_reg_write_pair(DisasContext *ctx, int rnum, ctx_log_reg_write(ctx, rnum + 1, is_predicated); } -static inline bool is_vreg_preloaded(DisasContext *ctx, int num) -{ - return test_bit(num, ctx->vregs_updated) || - test_bit(num, ctx->vregs_updated_tmp); -} - intptr_t ctx_future_vreg_off(DisasContext *ctx, int regnum, int num, bool alloc_ok); intptr_t ctx_tmp_vreg_off(DisasContext *ctx, int regnum, @@ -120,12 +116,18 @@ static inline void ctx_log_vreg_write(DisasContext *ctx, ctx->vreg_log_idx++; set_bit(rnum, ctx->vregs_updated); + if (is_predicated) { + set_bit(rnum, ctx->predicated_future_vregs); + } } if (type == EXT_NEW) { set_bit(rnum, ctx->vregs_select); } if (type == EXT_TMP) { set_bit(rnum, ctx->vregs_updated_tmp); + if (is_predicated) { + set_bit(rnum, ctx->predicated_tmp_vregs); + } } } diff --git a/target/hexagon/translate.c b/target/hexagon/translate.c index 01671d5451..493bc75d27 100644 --- a/target/hexagon/translate.c +++ b/target/hexagon/translate.c @@ -364,6 +364,8 @@ static void gen_start_packet(DisasContext *ctx) bitmap_zero(ctx->vregs_updated_tmp, NUM_VREGS); bitmap_zero(ctx->vregs_updated, NUM_VREGS); bitmap_zero(ctx->vregs_select, NUM_VREGS); + bitmap_zero(ctx->predicated_future_vregs, NUM_VREGS); + bitmap_zero(ctx->predicated_tmp_vregs, NUM_VREGS); ctx->qreg_log_idx = 0; for (i = 0; i < STORES_MAX; i++) { ctx->store_width[i] = 0; @@ -415,6 +417,34 @@ static void gen_start_packet(DisasContext *ctx) } } + /* Preload the predicated HVX registers into future_VRegs and tmp_VRegs */ + if (!bitmap_empty(ctx->predicated_future_vregs, NUM_VREGS)) { + int i = find_first_bit(ctx->predicated_future_vregs, NUM_VREGS); + while (i < NUM_VREGS) { + const intptr_t VdV_off = + ctx_future_vreg_off(ctx, i, 1, true); + intptr_t src_off = offsetof(CPUHexagonState, VRegs[i]); + tcg_gen_gvec_mov(MO_64, VdV_off, + src_off, + sizeof(MMVector), + sizeof(MMVector)); + i = find_next_bit(ctx->predicated_future_vregs, NUM_VREGS, i + 1); + } + } + if (!bitmap_empty(ctx->predicated_tmp_vregs, NUM_VREGS)) { + int i = find_first_bit(ctx->predicated_tmp_vregs, NUM_VREGS); + while (i < NUM_VREGS) { + const intptr_t VdV_off = + ctx_tmp_vreg_off(ctx, i, 1, true); + intptr_t src_off = offsetof(CPUHexagonState, VRegs[i]); + tcg_gen_gvec_mov(MO_64, VdV_off, + src_off, + sizeof(MMVector), + sizeof(MMVector)); + i = find_next_bit(ctx->predicated_tmp_vregs, NUM_VREGS, i + 1); + } + } + if (pkt->pkt_has_hvx) { tcg_gen_movi_tl(hex_VRegs_updated, 0); tcg_gen_movi_tl(hex_QRegs_updated, 0); diff --git a/target/hexagon/gen_analyze_funcs.py b/target/hexagon/gen_analyze_funcs.py index 7e1f221b3c..0bb4fcb476 100755 --- a/target/hexagon/gen_analyze_funcs.py +++ b/target/hexagon/gen_analyze_funcs.py @@ -83,9 +83,16 @@ def analyze_opn_old(f, tag, regtype, regid, regno): else: print("Bad register parse: ", regtype, regid) elif (regtype == "V"): + newv = "EXT_DFL" + if (hex_common.is_new_result(tag)): + newv = "EXT_NEW" + elif (hex_common.is_tmp_result(tag)): + newv = "EXT_TMP" if (regid in {"dd", "xx"}): - f.write("// const int %s = insn->regno[%d];\n" %\ + f.write(" const int %s = insn->regno[%d];\n" %\ (regN, regno)) + f.write(" ctx_log_vreg_write_pair(ctx, %s, %s, %s);\n" % \ + (regN, newv, predicated)) elif (regid in {"uu", "vv"}): f.write("// const int %s = insn->regno[%d];\n" % \ (regN, regno)) @@ -93,14 +100,18 @@ def analyze_opn_old(f, tag, regtype, regid, regno): f.write("// const int %s = insn->regno[%d];\n" % \ (regN, regno)) elif (regid in {"d", "x", "y"}): - f.write("// const int %s = insn->regno[%d];\n" % \ + f.write(" const int %s = insn->regno[%d];\n" % \ (regN, regno)) + f.write(" ctx_log_vreg_write(ctx, %s, %s, %s);\n" % \ + (regN, newv, predicated)) else: print("Bad register parse: ", regtype, regid) elif (regtype == "Q"): if (regid in {"d", "e", "x"}): - f.write("// const int %s = insn->regno[%d];\n" % \ + f.write(" const int %s = insn->regno[%d];\n" % \ (regN, regno)) + f.write(" ctx_log_qreg_write(ctx, %s, %s);\n" % \ + (regN, predicated)) elif (regid in {"s", "t", "u", "v"}): f.write("// const int %s = insn->regno[%d];\n" % \ (regN, regno)) diff --git a/target/hexagon/gen_tcg_funcs.py b/target/hexagon/gen_tcg_funcs.py index 02fa65c5c9..22bcb56917 100755 --- a/target/hexagon/gen_tcg_funcs.py +++ b/target/hexagon/gen_tcg_funcs.py @@ -152,17 +152,6 @@ def genptr_decl(f, tag, regtype, regid, regno): f.write(" ctx_future_vreg_off(ctx, %s%sN," % \ (regtype, regid)) f.write(" 1, true);\n"); - if 'A_CONDEXEC' in hex_common.attribdict[tag]: - f.write(" if (!is_vreg_preloaded(ctx, %s)) {\n" % (regN)) - f.write(" intptr_t src_off =") - f.write(" offsetof(CPUHexagonState, VRegs[%s%sN]);\n"% \ - (regtype, regid)) - f.write(" tcg_gen_gvec_mov(MO_64, %s%sV_off,\n" % \ - (regtype, regid)) - f.write(" src_off,\n") - f.write(" sizeof(MMVector),\n") - f.write(" sizeof(MMVector));\n") - f.write(" }\n") if (not hex_common.skip_qemu_helper(tag)): f.write(" TCGv_ptr %s%sV = tcg_temp_new_ptr();\n" % \ @@ -421,9 +410,6 @@ def genptr_dst_write_ext(f, tag, regtype, regid, newv="EXT_DFL"): (regtype, regid, regtype, regid)) f.write("%s, insn->slot, %s);\n" % \ (newv, is_predicated)) - f.write(" ctx_log_vreg_write_pair(ctx, %s%sN, %s,\n" % \ - (regtype, regid, newv)) - f.write(" %s);\n" % (is_predicated)) elif (regid in {"d", "x", "y"}): if ('A_CONDEXEC' in hex_common.attribdict[tag]): is_predicated = "true" @@ -433,8 +419,6 @@ def genptr_dst_write_ext(f, tag, regtype, regid, newv="EXT_DFL"): (regtype, regid, regtype, regid, newv)) f.write("insn->slot, %s);\n" % \ (is_predicated)) - f.write(" ctx_log_vreg_write(ctx, %s%sN, %s, %s);\n" % \ - (regtype, regid, newv, is_predicated)) else: print("Bad register parse: ", regtype, regid) elif (regtype == "Q"): @@ -446,8 +430,6 @@ def genptr_dst_write_ext(f, tag, regtype, regid, newv="EXT_DFL"): f.write(" gen_log_qreg_write(%s%sV_off, %s%sN, %s, " % \ (regtype, regid, regtype, regid, newv)) f.write("insn->slot, %s);\n" % (is_predicated)) - f.write(" ctx_log_qreg_write(ctx, %s%sN, %s);\n" % \ - (regtype, regid, is_predicated)) else: print("Bad register parse: ", regtype, regid) else: