Patch Detail
get:
Show a patch.
patch:
Update a patch.
put:
Update a patch.
GET /api/1.1/patches/2228466/?format=api
{ "id": 2228466, "url": "http://patchwork.ozlabs.org/api/1.1/patches/2228466/?format=api", "web_url": "http://patchwork.ozlabs.org/project/qemu-devel/patch/20260426134002.865628-85-richard.henderson@linaro.org/", "project": { "id": 14, "url": "http://patchwork.ozlabs.org/api/1.1/projects/14/?format=api", "name": "QEMU Development", "link_name": "qemu-devel", "list_id": "qemu-devel.nongnu.org", "list_email": "qemu-devel@nongnu.org", "web_url": "", "scm_url": "", "webscm_url": "" }, "msgid": "<20260426134002.865628-85-richard.henderson@linaro.org>", "date": "2026-04-26T13:40:01", "name": "[84/84] target/arm: Use FloatParts64 in f16_dotadd", "commit_ref": null, "pull_url": null, "state": "new", "archived": false, "hash": "d2de7b136f504c70c8f9b8e8657d13930419d507", "submitter": { "id": 72104, "url": "http://patchwork.ozlabs.org/api/1.1/people/72104/?format=api", "name": "Richard Henderson", "email": "richard.henderson@linaro.org" }, "delegate": null, "mbox": "http://patchwork.ozlabs.org/project/qemu-devel/patch/20260426134002.865628-85-richard.henderson@linaro.org/mbox/", "series": [ { "id": 501533, "url": "http://patchwork.ozlabs.org/api/1.1/series/501533/?format=api", "web_url": "http://patchwork.ozlabs.org/project/qemu-devel/list/?series=501533", "date": "2026-04-26T13:38:37", "name": "fpu: Export some internals for targets", "version": 1, "mbox": "http://patchwork.ozlabs.org/series/501533/mbox/" } ], "comments": "http://patchwork.ozlabs.org/api/patches/2228466/comments/", "check": "pending", "checks": "http://patchwork.ozlabs.org/api/patches/2228466/checks/", "tags": {}, "headers": { "Return-Path": "<qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org>", "X-Original-To": "incoming@patchwork.ozlabs.org", "Delivered-To": "patchwork-incoming@legolas.ozlabs.org", "Authentication-Results": [ "legolas.ozlabs.org;\n\tdkim=pass (2048-bit key;\n unprotected) header.d=linaro.org header.i=@linaro.org header.a=rsa-sha256\n header.s=google header.b=WAYmfVvk;\n\tdkim-atps=neutral", "legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=nongnu.org\n (client-ip=209.51.188.17; helo=lists1p.gnu.org;\n envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org;\n receiver=patchwork.ozlabs.org)" ], "Received": [ "from lists1p.gnu.org (lists1p.gnu.org [209.51.188.17])\n\t(using TLSv1.2 with cipher ECDHE-ECDSA-AES256-GCM-SHA384 (256/256 bits))\n\t(No client certificate requested)\n\tby legolas.ozlabs.org (Postfix) with ESMTPS id 4g3Ss84164z1yJ1\n\tfor <incoming@patchwork.ozlabs.org>; Sun, 26 Apr 2026 23:55:56 +1000 (AEST)", "from localhost ([::1] helo=lists1p.gnu.org)\n\tby lists1p.gnu.org with esmtp (Exim 4.90_1)\n\t(envelope-from <qemu-devel-bounces@nongnu.org>)\n\tid 1wGzsh-0008Ez-DR; Sun, 26 Apr 2026 09:50:43 -0400", "from eggs.gnu.org ([2001:470:142:3::10])\n by lists1p.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)\n (Exim 4.90_1) (envelope-from <richard.henderson@linaro.org>)\n id 1wGzs5-0007ED-W2\n for qemu-devel@nongnu.org; Sun, 26 Apr 2026 09:50:08 -0400", "from mail-pf1-x42d.google.com ([2607:f8b0:4864:20::42d])\n by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128)\n (Exim 4.90_1) (envelope-from <richard.henderson@linaro.org>)\n id 1wGzs3-0002ui-Fb\n for qemu-devel@nongnu.org; Sun, 26 Apr 2026 09:50:05 -0400", "by mail-pf1-x42d.google.com with SMTP id\n d2e1a72fcca58-82f9fdfc965so3680033b3a.1\n for <qemu-devel@nongnu.org>; Sun, 26 Apr 2026 06:50:03 -0700 (PDT)", "from stoup.. ([180.233.125.15]) by smtp.gmail.com with ESMTPSA id\n d2e1a72fcca58-82f8ebba485sm36307102b3a.38.2026.04.26.06.49.59\n (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256);\n Sun, 26 Apr 2026 06:50:01 -0700 (PDT)" ], "DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=linaro.org; s=google; t=1777211402; x=1777816202; darn=nongnu.org;\n h=content-transfer-encoding:mime-version:references:in-reply-to\n :message-id:date:subject:cc:to:from:from:to:cc:subject:date\n :message-id:reply-to;\n bh=p0uQob+N5O8wbOKZuJ2cl6QGt2btZMLnp6lMLH+YdM8=;\n b=WAYmfVvk9iC1JFCcZFJSiiCydk7qp2AmVUV0ZDF6GruI1+dSnu7689JhTgrnisbMIl\n tk/xTA2wuDA180ok0UU+2nmUaO2tA+uQUqmPBdrYUFmxCtz7LlX3ka45qA5SlkKYBeLd\n 8UQp6SXcL2buIEMorisLMGlPFlNFmRc5+bAh0VgJ2DlYDjSp+4qvt2Vs0lch/d/EFvhm\n 5phUga8ADIUESzyMTnSCTNBSfxm5dhy42oi413K5/dXD4UPBb0W8hFCNtdYNcccI55Hd\n V7u0esqkLN3rUnoy5+6ObhCUWT7jy9PjsJonw+WXz26thivFwxNB19k5pYY9ZMHalzQ+\n gpvw==", "X-Google-DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1777211402; x=1777816202;\n h=content-transfer-encoding:mime-version:references:in-reply-to\n :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from\n :to:cc:subject:date:message-id:reply-to;\n bh=p0uQob+N5O8wbOKZuJ2cl6QGt2btZMLnp6lMLH+YdM8=;\n b=oMgXhEfszovTgMnXf14v9hN9Z2mKSWNTMSXHpRBGwDhbzYtAsgWSNrsmMXP8SRDsX7\n 4VYBm4l18YLzwdT/UsjuGgQkSFqf5TWFaU6s1IM+gLRNrAuXy2rqCUe9iaerTc5D5oyw\n DmmSbO4UvJjm1sRamQJziCaozpoKNaxaR68rvj5y5PjAqCj9q8LivwwDeJPokIZli5di\n dgnTH7PgxmI/VXGjRMohpyoO4xDa1aXg9KDcV6u7XURCdOJjD/WMJtgDm1FEswLjFyk0\n 2O2YqvmDGo6SW0nEULdFRHtqo0m7H1mf9s5xnQPnFhyDMAkEfDUayK0jraQAQ8X/YMpF\n sCRA==", "X-Gm-Message-State": "AOJu0YwAOiTQ2NmAvybi4oMy3hdoSd/03WMC5XbNUQjihAJZ5VOoA/kB\n w1qVHowwTgTmfeQOr53y2BgK/lEGIZo4two6s97QNaWW/B/YkRSjD6t116K5KXhkUuWSN8+bOi2\n ozov9wXA=", "X-Gm-Gg": "AeBDieuemHiGHP74vvPKBuZ9jK5aDR1KKdFcWtkcfy7qIO5bwd3pU2zMAqHQKf8iUkK\n 0FBj9ci/2ZOt9he9TIyFr1fiiwVfrxeU8HV8wkLPo8nVYmzBg4ugYB4RTUtO2hPJ9GZB2DnaHm+\n j8+IOy7PTr9FGiYVWUDccY/hZNPNvHMMOO3g4m6gBTfFTJqPn/l/6it77Z3rRd+rz8qxj488iST\n dhYyr1fJ9WzXCtek0EeqO9Ay1ZR5nCyreQOc4RNqjrPVh1TLOaTbtYXxwekBBPQfqqeVCOSNGsF\n edQtbu0W1mQ5NrKqK4ApkGZuw+x5evMFIuEN1Sr84MOh8yHpX1hw7Cij0M+aShv00Q0yBoXQ/GO\n LfN1MmLozBch7ls7WJZX5FuxqrCRZIs7APwVvNlEkf9y4Q53uWdwLxA6pvdL7FmB3cl54QW7+87\n mU16ozry4VVYK0Dofx6muIQfIfVOAyr4hSKOZ4kqsx", "X-Received": "by 2002:a05:6a00:6c8d:b0:82c:7f08:8826 with SMTP id\n d2e1a72fcca58-82f8c8b3dbemr35029369b3a.17.1777211401888;\n Sun, 26 Apr 2026 06:50:01 -0700 (PDT)", "From": "Richard Henderson <richard.henderson@linaro.org>", "To": "qemu-devel@nongnu.org", "Cc": "qemu-arm@nongnu.org,\n\tqemu-s390x@nongnu.org", "Subject": "[PATCH 84/84] target/arm: Use FloatParts64 in f16_dotadd", "Date": "Sun, 26 Apr 2026 23:40:01 +1000", "Message-ID": "<20260426134002.865628-85-richard.henderson@linaro.org>", "X-Mailer": "git-send-email 2.43.0", "In-Reply-To": "<20260426134002.865628-1-richard.henderson@linaro.org>", "References": "<20260426134002.865628-1-richard.henderson@linaro.org>", "MIME-Version": "1.0", "Content-Transfer-Encoding": "8bit", "Received-SPF": "pass client-ip=2607:f8b0:4864:20::42d;\n envelope-from=richard.henderson@linaro.org; helo=mail-pf1-x42d.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,\n DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1,\n RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001,\n SPF_PASS=-0.001 autolearn=unavailable autolearn_force=no", "X-Spam_action": "no action", "X-BeenThere": "qemu-devel@nongnu.org", "X-Mailman-Version": "2.1.29", "Precedence": "list", "List-Id": "qemu development <qemu-devel.nongnu.org>", "List-Unsubscribe": "<https://lists.nongnu.org/mailman/options/qemu-devel>,\n <mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>", "List-Archive": "<https://lists.nongnu.org/archive/html/qemu-devel>", "List-Post": "<mailto:qemu-devel@nongnu.org>", "List-Help": "<mailto:qemu-devel-request@nongnu.org?subject=help>", "List-Subscribe": "<https://lists.nongnu.org/mailman/listinfo/qemu-devel>,\n <mailto:qemu-devel-request@nongnu.org?subject=subscribe>", "Errors-To": "qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org", "Sender": "qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org" }, "content": "Use softfloat-parts.h so that we can more naturally\nperform the required operations witha single rounding step.\nThis happens to also simplify the NaN detection step.\n\nSigned-off-by: Richard Henderson <richard.henderson@linaro.org>\n---\n target/arm/tcg/sme_helper.c | 96 ++++++++++++++++---------------------\n 1 file changed, 40 insertions(+), 56 deletions(-)", "diff": "diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c\nindex 0702a1b129..71fe44445d 100644\n--- a/target/arm/tcg/sme_helper.c\n+++ b/target/arm/tcg/sme_helper.c\n@@ -27,6 +27,7 @@\n #include \"accel/tcg/helper-retaddr.h\"\n #include \"qemu/int128.h\"\n #include \"fpu/softfloat.h\"\n+#include \"fpu/softfloat-parts.h\"\n #include \"vec_internal.h\"\n #include \"sve_ldst_internal.h\"\n \n@@ -1227,18 +1228,15 @@ static inline uint32_t bf16mop_ah_neg_adj_pair(uint32_t pair, uint32_t pg)\n }\n \n static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2,\n- float_status *s_f16, float_status *s_std,\n- float_status *s_odd)\n+ float_status *s_f16, float_status *s_std)\n {\n /*\n- * We need three different float_status for different parts of this\n+ * We need two different float_status for different parts of this\n * operation:\n * - the input conversion of the float16 values must use the\n * f16-specific float_status, so that the FPCR.FZ16 control is applied\n * - operations on float32 including the final accumulation must use\n * the normal float_status, so that FPCR.FZ is applied\n- * - we have pre-set-up copy of s_std which is set to round-to-odd,\n- * for the multiply (see below)\n */\n float16 h1r = e1 & 0xffff;\n float16 h1c = e1 >> 16;\n@@ -1246,48 +1244,49 @@ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2,\n float16 h2c = e2 >> 16;\n float32 t32;\n \n+ FloatParts64 p1r = float16_unpack_canonical(h1r, s_f16);\n+ FloatParts64 p1c = float16_unpack_canonical(h1c, s_f16);\n+ FloatParts64 p2r = float16_unpack_canonical(h2r, s_f16);\n+ FloatParts64 p2c = float16_unpack_canonical(h2c, s_f16);\n+\n+ int all_mask = (float_cmask(p1r.cls) | float_cmask(p1c.cls) |\n+ float_cmask(p1r.cls) | float_cmask(p1c.cls));\n+\n /* C.f. FPProcessNaNs4 */\n- if (float16_is_any_nan(h1r) || float16_is_any_nan(h1c) ||\n- float16_is_any_nan(h2r) || float16_is_any_nan(h2c)) {\n+ if (unlikely(all_mask & float_cmask_anynan)) {\n float16 t16;\n \n- if (float16_is_signaling_nan(h1r, s_f16)) {\n- t16 = h1r;\n- } else if (float16_is_signaling_nan(h1c, s_f16)) {\n- t16 = h1c;\n- } else if (float16_is_signaling_nan(h2r, s_f16)) {\n- t16 = h2r;\n- } else if (float16_is_signaling_nan(h2c, s_f16)) {\n- t16 = h2c;\n- } else if (float16_is_any_nan(h1r)) {\n- t16 = h1r;\n- } else if (float16_is_any_nan(h1c)) {\n- t16 = h1c;\n- } else if (float16_is_any_nan(h2r)) {\n- t16 = h2r;\n+ if (unlikely(all_mask & float_cmask_snan)) {\n+ if (p1r.cls == float_class_snan) {\n+ t16 = h1r;\n+ } else if (p1c.cls == float_class_snan) {\n+ t16 = h1c;\n+ } else if (p2r.cls == float_class_snan) {\n+ t16 = h2r;\n+ } else {\n+ t16 = h2c;\n+ }\n } else {\n- t16 = h2c;\n+ if (p1r.cls == float_class_qnan) {\n+ t16 = h1r;\n+ } else if (p1c.cls == float_class_qnan) {\n+ t16 = h1c;\n+ } else if (p2r.cls == float_class_qnan) {\n+ t16 = h2r;\n+ } else {\n+ t16 = h2c;\n+ }\n }\n t32 = float16_to_float32(t16, true, s_f16);\n } else {\n- float64 e1r = float16_to_float64(h1r, true, s_f16);\n- float64 e1c = float16_to_float64(h1c, true, s_f16);\n- float64 e2r = float16_to_float64(h2r, true, s_f16);\n- float64 e2c = float16_to_float64(h2c, true, s_f16);\n- float64 t64;\n-\n /*\n * The ARM pseudocode function FPDot performs both multiplies\n- * and the add with a single rounding operation. Emulate this\n- * by performing the first multiply in round-to-odd, then doing\n- * the second multiply as fused multiply-add, and rounding to\n- * float32 all in one step.\n+ * and the add with a single rounding operation.\n */\n- t64 = float64_mul(e1r, e2r, s_odd);\n- t64 = float64r32_muladd(e1c, e2c, t64, 0, s_std);\n+ FloatParts64 tmp = parts64_mul(&p1r, &p2r, s_std);\n+ tmp = parts64_muladd_scalbn(&p1c, &p2c, &tmp, 0, 0, s_std);\n \n- /* This conversion is exact, because we've already rounded. */\n- t32 = float64_to_float32(t64, s_std);\n+ t32 = float32_round_pack_canonical(&tmp, s_std);\n }\n \n /* The final accumulation step is not fused. */\n@@ -1299,9 +1298,6 @@ static void do_fmopa_w_h(void *vza, void *vzn, void *vzm, uint16_t *pn,\n uint32_t negx, bool ah_neg)\n {\n intptr_t row, col, oprsz = simd_maxsz(desc);\n- float_status fpst_odd = env->vfp.fp_status[FPST_ZA];\n-\n- set_float_rounding_mode(float_round_to_odd, &fpst_odd);\n \n for (row = 0; row < oprsz; ) {\n uint16_t prow = pn[H2(row >> 4)];\n@@ -1325,8 +1321,7 @@ static void do_fmopa_w_h(void *vza, void *vzn, void *vzm, uint16_t *pn,\n m = f16mop_adj_pair(m, pcol, 0);\n *a = f16_dotadd(*a, n, m,\n &env->vfp.fp_status[FPST_ZA_F16],\n- &env->vfp.fp_status[FPST_ZA],\n- &fpst_odd);\n+ &env->vfp.fp_status[FPST_ZA]);\n }\n col += 4;\n pcol >>= 4;\n@@ -1363,15 +1358,12 @@ void HELPER(sme2_fdot_h)(void *vd, void *vn, void *vm, void *va,\n bool za = extract32(desc, SIMD_DATA_SHIFT, 1);\n float_status *fpst_std = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64];\n float_status *fpst_f16 = &env->vfp.fp_status[za ? FPST_ZA_F16 : FPST_A64_F16];\n- float_status fpst_odd = *fpst_std;\n float32 *d = vd, *a = va;\n uint32_t *n = vn, *m = vm;\n \n- set_float_rounding_mode(float_round_to_odd, &fpst_odd);\n-\n for (i = 0; i < oprsz / sizeof(float32); ++i) {\n d[H4(i)] = f16_dotadd(a[H4(i)], n[H4(i)], m[H4(i)],\n- fpst_f16, fpst_std, &fpst_odd);\n+ fpst_f16, fpst_std);\n }\n }\n \n@@ -1385,17 +1377,14 @@ void HELPER(sme2_fdot_idx_h)(void *vd, void *vn, void *vm, void *va,\n bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1);\n float_status *fpst_std = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64];\n float_status *fpst_f16 = &env->vfp.fp_status[za ? FPST_ZA_F16 : FPST_A64_F16];\n- float_status fpst_odd = *fpst_std;\n float32 *d = vd, *a = va;\n uint32_t *n = vn, *m = (uint32_t *)vm + H4(idx);\n \n- set_float_rounding_mode(float_round_to_odd, &fpst_odd);\n-\n for (i = 0; i < elements; i += eltspersegment) {\n uint32_t mm = m[i];\n for (j = 0; j < eltspersegment; ++j) {\n d[H4(i + j)] = f16_dotadd(a[H4(i + j)], n[H4(i + j)], mm,\n- fpst_f16, fpst_std, &fpst_odd);\n+ fpst_f16, fpst_std);\n }\n }\n }\n@@ -1408,24 +1397,19 @@ void HELPER(sme2_fvdot_idx_h)(void *vd, void *vn, void *vm, void *va,\n intptr_t eltspersegment = MIN(4, elements);\n int idx = extract32(desc, SIMD_DATA_SHIFT, 2);\n int sel = extract32(desc, SIMD_DATA_SHIFT + 2, 1);\n- float_status fpst_odd, *fpst_std, *fpst_f16;\n float32 *d = vd, *a = va;\n uint16_t *n0 = vn;\n uint16_t *n1 = vn + sizeof(ARMVectorReg);\n uint32_t *m = (uint32_t *)vm + H4(idx);\n \n- fpst_std = &env->vfp.fp_status[FPST_ZA];\n- fpst_f16 = &env->vfp.fp_status[FPST_ZA_F16];\n- fpst_odd = *fpst_std;\n- set_float_rounding_mode(float_round_to_odd, &fpst_odd);\n-\n for (i = 0; i < elements; i += eltspersegment) {\n uint32_t mm = m[i];\n for (j = 0; j < eltspersegment; ++j) {\n uint32_t nn = (n0[H2(2 * (i + j) + sel)])\n | (n1[H2(2 * (i + j) + sel)] << 16);\n d[i + H4(j)] = f16_dotadd(a[i + H4(j)], nn, mm,\n- fpst_f16, fpst_std, &fpst_odd);\n+ &env->vfp.fp_status[FPST_ZA_F16],\n+ &env->vfp.fp_status[FPST_ZA]);\n }\n }\n }\n", "prefixes": [ "84/84" ] }