From patchwork Mon Aug 30 06:24:47 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 504320 Delivered-To: patch@linaro.org Received: by 2002:a02:8629:0:0:0:0:0 with SMTP id e38csp1524331jai; Sun, 29 Aug 2021 23:53:56 -0700 (PDT) X-Google-Smtp-Source: ABdhPJxr36Msn2LbQ/Zc7wix7jD6Q8TBAQcb52kpN/qWmP0W4FbCdM0ds/VCUlfZs7TIAY1AtqvJ X-Received: by 2002:a6b:fc1a:: with SMTP id r26mr17061058ioh.30.1630306436842; Sun, 29 Aug 2021 23:53:56 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1630306436; cv=none; d=google.com; s=arc-20160816; b=VSUatKl54KUeuOW3/OXMebzafcq8bTcPE7t3FwLlcUvJPCLG0eYn24GbjudFufzoqN e1At1oD1MBM6IlojPm+PjG5/0WbLbeYdazcOU+Gw7/7QpsiCXCFDecMocngPy86hlJhJ J5wSUSSRHLl2CArcSwHKtSEmw4MWrJ/CoXJ0T9kPPqilpI6Y23Yz3rqqhWXLuS++OZwj XdicSLF30iQtsNs4Jtpz8aonsW8LvWnjm/mUrBH1oOEyoKbecakOXAAuqkFjdsqjthkK rxx1+rz4zXjuwfQJcPNDEbevJKUlpswovdy9n5s/51Cg+3BLoLXeOedXuiOTZXLNmFuT rV+Q== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=+Wwyb2RZh0dTNoENwmNMl6IMhek0eIp3hILVu1PQ3hU=; b=N1LBIpbiHI2z7X95O7HNFH44T2Qvh2oEVZbaP75N6iWfa/+mY4CSrMgHgA95TBMToP IBzyouup3Fb0Y8WxpZU/sRU69nyu/n7cp8cgBqEHhP6jgDQRHxgpz5HC/acJbsc+77hX QlpShj+rWV0qQPfPHRIHHyz9swvsji2MAVeHn8IzW+vUnowzPsZmN0RnXjSM+iOnkdiW t/pFDBmH7Fi9131MoNgnY3GN89Zdhs3TUrsjA0D3G7MBudbVzx5B/i0bZiqw1qDNulBS CuUid0iwik11paikTi6mudqsBESc0+hoKGj/CIScZMkSiYeE8tQTaz0v6ebzrfMjMIdF BwIQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b="m5XqSt/w"; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d24si7277535jaa.121.2021.08.29.23.53.56 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Sun, 29 Aug 2021 23:53:56 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b="m5XqSt/w"; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1]:49082 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1mKbB6-0004NP-9i for patch@linaro.org; Mon, 30 Aug 2021 02:53:56 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:47176) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1mKamV-0003HI-Vd for qemu-devel@nongnu.org; Mon, 30 Aug 2021 02:28:32 -0400 Received: from mail-pj1-x1029.google.com ([2607:f8b0:4864:20::1029]:44731) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1mKamN-0001p6-At for qemu-devel@nongnu.org; Mon, 30 Aug 2021 02:28:29 -0400 Received: by mail-pj1-x1029.google.com with SMTP id j4-20020a17090a734400b0018f6dd1ec97so9246870pjs.3 for ; Sun, 29 Aug 2021 23:28:22 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:subject:date:message-id:in-reply-to:references:mime-version :content-transfer-encoding; bh=+Wwyb2RZh0dTNoENwmNMl6IMhek0eIp3hILVu1PQ3hU=; b=m5XqSt/waiejr0klOgkq1kj2sc1Dn2OSEt5PWRvggNnwaT3u1k+bFcZN1KN7w9hmvv FMI1sixGe+uqhLvqsze7DvoxQZsPKqe6UfUeoHHh/Bf0/Xt/P+AqzPKYsjHvyDMq5r1I 3jlIt5U1ifYVd2dFN5rCMYtr2OtvHWyzfHvkH6GTJ/EkdfPjECG2Vi7N0aSGYIlFRixh srH1BtlRGvwzGKYCv7K1ksIZNxKsm/32CLcEdZYfsRQvvMp6zZZ+MhasmkuZDnZi9/E7 B4YKCqG4sjn9NRXdl7CKcUA830AhjwqQ07Ytd5WMaj/elGCAByPqynygrBix1kWSL+83 nt0Q== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=+Wwyb2RZh0dTNoENwmNMl6IMhek0eIp3hILVu1PQ3hU=; b=VN9eV4KjcuXRuwmZwt4WqHZ+Z/KwIB0B6mjd/YG+Azdr82L5N6ZXmN6ZRb8bBfATCO jH4zQqxttGihXPPxt/4K8SjSZgPWIAQpppZ3CSl1TjcCNf31kSMDGoEpVkMfJ1bzjIWf YpizGG/XG68Q8C2IFF07duRB0k5J02rmxpc/cXBqIFmTUaO+hA6NiaV0wyA04+peYv17 iUZtOWZswM2uFwsSjHGGTq6i+NKc2jZ5ltuw9jOO9uDsMnXOqYeUOr3dvg5UTg/FB0WN JLXC2Gi1z7KYWMo32sbLFB77ho5FpITuO26JAb4dcceAIfI5YT7UBQ9aYHr/mkN4Zb4T TAoQ== X-Gm-Message-State: AOAM532ysDu3zc1lCDGQ2SsiDy+P65Q07DVLf9XanFjeAT0Lm0Wn7Tgz RTTGg/L5nPQu7U/kLtBtT7d3opOdef+qgA== X-Received: by 2002:a17:902:c192:b0:138:e2f9:7210 with SMTP id d18-20020a170902c19200b00138e2f97210mr1758933pld.79.1630304901475; Sun, 29 Aug 2021 23:28:21 -0700 (PDT) Received: from localhost.localdomain (174-21-72-39.tukw.qwest.net. [174.21.72.39]) by smtp.gmail.com with ESMTPSA id o6sm13337072pjk.4.2021.08.29.23.28.21 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sun, 29 Aug 2021 23:28:21 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Subject: [PATCH 44/48] tcg/optimize: Optimize sign extensions Date: Sun, 29 Aug 2021 23:24:47 -0700 Message-Id: <20210830062451.639572-45-richard.henderson@linaro.org> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20210830062451.639572-1-richard.henderson@linaro.org> References: <20210830062451.639572-1-richard.henderson@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2607:f8b0:4864:20::1029; envelope-from=richard.henderson@linaro.org; helo=mail-pj1-x1029.google.com 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: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" Certain targets, like riscv, produce signed 32-bit results. This can lead to lots of redundant extensions as values are manipulated. Begin by tracking only the obvious sign-extensions, and converting them to simple copies when possible. Signed-off-by: Richard Henderson --- tcg/optimize.c | 129 ++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 105 insertions(+), 24 deletions(-) -- 2.25.1 diff --git a/tcg/optimize.c b/tcg/optimize.c index 334639339b..9a752fbe29 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -42,6 +42,7 @@ typedef struct TempOptInfo { TCGTemp *next_copy; uint64_t val; uint64_t z_mask; /* mask bit is 0 if and only if value bit is 0 */ + uint64_t s_mask; /* a left-aligned mask of clrsb(value) bits. */ } TempOptInfo; typedef struct OptContext { @@ -52,9 +53,37 @@ typedef struct OptContext { /* In flight values from optimization. */ uint64_t a_mask; /* mask bit is 0 iff value identical to first input */ uint64_t z_mask; /* mask bit is 0 iff value bit is 0 */ + uint64_t s_mask; /* mask of clrsb(value) bits */ TCGType type; } OptContext; +/* Calculate the smask for a specific value. */ +static uint64_t smask_from_value(uint64_t value) +{ + int rep = clrsb64(value); + return ~(~0ull >> rep); +} + +/* + * Calculate the smask for a given set of known-zeros. + * If there are lots of zeros on the left, we can consider the remainder + * an unsigned field, and thus the corresponding signed field is one bit + * larger. + */ +static uint64_t smask_from_zmask(uint64_t zmask) +{ + /* + * Only the 0 bits are significant for zmask, thus the msb itself + * must be zero, else we have no sign information. + */ + int rep = clz64(zmask); + if (rep == 0) { + return 0; + } + rep -= 1; + return ~(~0ull >> rep); +} + static inline TempOptInfo *ts_info(TCGTemp *ts) { return ts->state_ptr; @@ -93,6 +122,7 @@ static void reset_ts(TCGTemp *ts) ti->prev_copy = ts; ti->is_const = false; ti->z_mask = -1; + ti->s_mask = 0; } static void reset_temp(TCGArg arg) @@ -123,9 +153,11 @@ static void init_ts_info(OptContext *ctx, TCGTemp *ts) ti->is_const = true; ti->val = ts->val; ti->z_mask = ts->val; + ti->s_mask = smask_from_value(ts->val); } else { ti->is_const = false; ti->z_mask = -1; + ti->s_mask = 0; } } @@ -219,6 +251,7 @@ static bool tcg_opt_gen_mov(OptContext *ctx, TCGOp *op, TCGArg dst, TCGArg src) op->args[1] = src; di->z_mask = si->z_mask; + di->s_mask = si->s_mask; if (src_ts->type == dst_ts->type) { TempOptInfo *ni = ts_info(si->next_copy); @@ -644,13 +677,15 @@ static void finish_folding(OptContext *ctx, TCGOp *op) nb_oargs = def->nb_oargs; for (i = 0; i < nb_oargs; i++) { - reset_temp(op->args[i]); + TCGTemp *ts = arg_temp(op->args[i]); + reset_ts(ts); /* - * Save the corresponding known-zero bits mask for the + * Save the corresponding known-zero/sign bits mask for the * first output argument (only one supported so far). */ if (i == 0) { - arg_info(op->args[i])->z_mask = ctx->z_mask; + ts_info(ts)->z_mask = ctx->z_mask; + ts_info(ts)->s_mask = ctx->s_mask; } } } @@ -700,6 +735,7 @@ static bool fold_masks(OptContext *ctx, TCGOp *op) { uint64_t a_mask = ctx->a_mask; uint64_t z_mask = ctx->z_mask; + uint64_t s_mask = ctx->s_mask; /* * 32-bit ops generate 32-bit results, which for the purpose of @@ -711,7 +747,9 @@ static bool fold_masks(OptContext *ctx, TCGOp *op) if (ctx->type == TCG_TYPE_I32) { a_mask = (int32_t)a_mask; z_mask = (int32_t)z_mask; + s_mask = (int32_t)s_mask; ctx->z_mask = z_mask; + ctx->s_mask = s_mask; } if (z_mask == 0) { @@ -1059,7 +1097,7 @@ static bool fold_brcond2(OptContext *ctx, TCGOp *op) static bool fold_bswap(OptContext *ctx, TCGOp *op) { - uint64_t z_mask, sign; + uint64_t z_mask, s_mask, sign; if (arg_is_const(op->args[1])) { uint64_t t = arg_info(op->args[1])->val; @@ -1069,6 +1107,7 @@ static bool fold_bswap(OptContext *ctx, TCGOp *op) } z_mask = arg_info(op->args[1])->z_mask; + switch (op->opc) { case INDEX_op_bswap16_i32: case INDEX_op_bswap16_i64: @@ -1087,6 +1126,7 @@ static bool fold_bswap(OptContext *ctx, TCGOp *op) default: g_assert_not_reached(); } + s_mask = smask_from_zmask(z_mask); switch (op->args[2] & (TCG_BSWAP_OZ | TCG_BSWAP_OS)) { case TCG_BSWAP_OZ: @@ -1095,14 +1135,17 @@ static bool fold_bswap(OptContext *ctx, TCGOp *op) /* If the sign bit may be 1, force all the bits above to 1. */ if (z_mask & sign) { z_mask |= sign; + s_mask = sign << 1; } break; default: /* The high bits are undefined: force all bits above the sign to 1. */ z_mask |= sign << 1; + s_mask = 0; break; } ctx->z_mask = z_mask; + ctx->s_mask = s_mask; return fold_masks(ctx, op); } @@ -1241,21 +1284,24 @@ static bool fold_eqv(OptContext *ctx, TCGOp *op) static bool fold_extract(OptContext *ctx, TCGOp *op) { uint64_t z_mask_old, z_mask; + int pos = op->args[2]; + int len = op->args[3]; if (arg_is_const(op->args[1])) { uint64_t t; t = arg_info(op->args[1])->val; - t = extract64(t, op->args[2], op->args[3]); + t = extract64(t, pos, len); return tcg_opt_gen_movi(ctx, op, op->args[0], t); } z_mask_old = arg_info(op->args[1])->z_mask; - z_mask = sextract64(z_mask_old, op->args[2], op->args[3]); - if (op->args[2] == 0) { + z_mask = extract64(z_mask_old, pos, len); + if (pos == 0) { ctx->a_mask = z_mask_old ^ z_mask; } ctx->z_mask = z_mask; + ctx->s_mask = smask_from_zmask(z_mask); return fold_masks(ctx, op); } @@ -1281,14 +1327,16 @@ static bool fold_extract2(OptContext *ctx, TCGOp *op) static bool fold_exts(OptContext *ctx, TCGOp *op) { - uint64_t z_mask_old, z_mask, sign; + uint64_t s_mask_old, s_mask, z_mask, sign; bool type_change = false; if (fold_const1(ctx, op)) { return true; } - z_mask_old = z_mask = arg_info(op->args[1])->z_mask; + z_mask = arg_info(op->args[1])->z_mask; + s_mask = arg_info(op->args[1])->s_mask; + s_mask_old = s_mask; switch (op->opc) { CASE_OP_32_64(ext8s): @@ -1312,10 +1360,14 @@ static bool fold_exts(OptContext *ctx, TCGOp *op) if (z_mask & sign) { z_mask |= sign; - } else if (!type_change) { - ctx->a_mask = z_mask_old ^ z_mask; } + s_mask |= sign << 1; + ctx->z_mask = z_mask; + ctx->s_mask = s_mask; + if (!type_change) { + ctx->a_mask = s_mask & ~s_mask_old; + } return fold_masks(ctx, op); } @@ -1354,6 +1406,7 @@ static bool fold_extu(OptContext *ctx, TCGOp *op) } ctx->z_mask = z_mask; + ctx->s_mask = smask_from_zmask(z_mask); if (!type_change) { ctx->a_mask = z_mask_old ^ z_mask; } @@ -1566,8 +1619,12 @@ static bool fold_qemu_ld(OptContext *ctx, TCGOp *op) MemOp mop = get_memop(oi); int width = 8 << (mop & MO_SIZE); - if (!(mop & MO_SIGN) && width < 64) { - ctx->z_mask = MAKE_64BIT_MASK(0, width); + if (width < 64) { + ctx->s_mask = MAKE_64BIT_MASK(width, 64 - width); + if (!(mop & MO_SIGN)) { + ctx->z_mask = MAKE_64BIT_MASK(0, width); + ctx->s_mask <<= 1; + } } /* Opcodes that touch guest memory stop the mb optimization. */ @@ -1677,23 +1734,31 @@ static bool fold_setcond2(OptContext *ctx, TCGOp *op) static bool fold_sextract(OptContext *ctx, TCGOp *op) { - int64_t z_mask_old, z_mask; + uint64_t z_mask, s_mask, s_mask_old; + int pos = op->args[2]; + int len = op->args[3]; if (arg_is_const(op->args[1])) { uint64_t t; t = arg_info(op->args[1])->val; - t = sextract64(t, op->args[2], op->args[3]); + t = sextract64(t, pos, len); return tcg_opt_gen_movi(ctx, op, op->args[0], t); } - z_mask_old = arg_info(op->args[1])->z_mask; - z_mask = sextract64(z_mask_old, op->args[2], op->args[3]); - if (op->args[2] == 0 && z_mask >= 0) { - ctx->a_mask = z_mask_old ^ z_mask; - } + z_mask = arg_info(op->args[1])->z_mask; + z_mask = sextract64(z_mask, pos, len); ctx->z_mask = z_mask; + s_mask_old = arg_info(op->args[1])->s_mask; + s_mask = sextract64(s_mask_old, pos, len); + s_mask |= MAKE_64BIT_MASK(len, 64 - len); + ctx->s_mask = s_mask; + + if (pos == 0) { + ctx->a_mask = s_mask & ~s_mask_old; + } + return fold_masks(ctx, op); } @@ -1770,14 +1835,26 @@ static bool fold_tcg_ld(OptContext *ctx, TCGOp *op) { /* We can't do any folding with a load, but we can record bits. */ switch (op->opc) { + CASE_OP_32_64(ld8s): + ctx->s_mask = MAKE_64BIT_MASK(8, 56); + break; CASE_OP_32_64(ld8u): - ctx->z_mask = 0xff; + ctx->z_mask = MAKE_64BIT_MASK(0, 8); + ctx->s_mask = MAKE_64BIT_MASK(9, 55); + break; + CASE_OP_32_64(ld16s): + ctx->s_mask = MAKE_64BIT_MASK(16, 48); break; CASE_OP_32_64(ld16u): - ctx->z_mask = 0xffff; + ctx->z_mask = MAKE_64BIT_MASK(0, 16); + ctx->s_mask = MAKE_64BIT_MASK(17, 47); + break; + case INDEX_op_ld32s_i64: + ctx->s_mask = MAKE_64BIT_MASK(32, 32); break; case INDEX_op_ld32u_i64: - ctx->z_mask = 0xffffffffu; + ctx->z_mask = MAKE_64BIT_MASK(0, 32); + ctx->s_mask = MAKE_64BIT_MASK(33, 31); break; default: g_assert_not_reached(); @@ -1840,9 +1917,10 @@ void tcg_optimize(TCGContext *s) ctx.type = TCG_TYPE_I32; } - /* Assume all bits affected, and no bits known zero. */ + /* Assume all bits affected, no bits known zero, no sign reps. */ ctx.a_mask = -1; ctx.z_mask = -1; + ctx.s_mask = 0; /* * Process each opcode. @@ -1915,8 +1993,11 @@ void tcg_optimize(TCGContext *s) case INDEX_op_extrh_i64_i32: done = fold_extu(&ctx, op); break; + CASE_OP_32_64(ld8s): CASE_OP_32_64(ld8u): + CASE_OP_32_64(ld16s): CASE_OP_32_64(ld16u): + case INDEX_op_ld32s_i64: case INDEX_op_ld32u_i64: done = fold_tcg_ld(&ctx, op); break;