Patch Detail
get:
Show a patch.
patch:
Update a patch.
put:
Update a patch.
GET /api/1.1/patches/2228458/?format=api
{ "id": 2228458, "url": "http://patchwork.ozlabs.org/api/1.1/patches/2228458/?format=api", "web_url": "http://patchwork.ozlabs.org/project/qemu-devel/patch/20260426134002.865628-83-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": "<20260426134002.865628-83-richard.henderson@linaro.org>", "date": "2026-04-26T13:39:59", "name": "[82/84] target/arm: Use FloatParts64 in bfdotadd_ebf", "commit_ref": null, "pull_url": null, "state": "new", "archived": false, "hash": "08bb30b41c96b52829488219e10669b3ee1fa3bf", "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/20260426134002.865628-83-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/2228458/comments/", "check": "pending", "checks": "http://patchwork.ozlabs.org/api/patches/2228458/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=rlYK4HFa;\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 4g3Sp317ZDz1yHg\n\tfor <incoming@patchwork.ozlabs.org>; Sun, 26 Apr 2026 23:53:15 +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 1wGzsX-0007eO-J8; Sun, 26 Apr 2026 09:50:33 -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 1wGzs1-000763-W4\n for qemu-devel@nongnu.org; Sun, 26 Apr 2026 09:50:05 -0400", "from mail-pf1-x42b.google.com ([2607:f8b0:4864:20::42b])\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 1wGzry-0002sh-1i\n for qemu-devel@nongnu.org; Sun, 26 Apr 2026 09:50:01 -0400", "by mail-pf1-x42b.google.com with SMTP id\n d2e1a72fcca58-82f69a286dbso7071144b3a.2\n for <qemu-devel@nongnu.org>; Sun, 26 Apr 2026 06:49:57 -0700 (PDT)", "from stoup.. ([180.233.125.15]) by smtp.gmail.com with ESMTPSA id\n d2e1a72fcca58-82f8ebba485sm36307102b3a.38.2026.04.26.06.49.54\n (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256);\n Sun, 26 Apr 2026 06:49:56 -0700 (PDT)" ], "DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=linaro.org; s=google; t=1777211396; x=1777816196; 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=xlytXwevs67gNFcr4ujyMnKHEGjQPMghBz+4SCH2y1E=;\n b=rlYK4HFapxxU61YSLBWquYxKAdV83KqThs1zA2qf4qXthQATjPPzbxRLxZ2Xn0C5Nj\n 4cSF65xH2t1xn6/M2/udTyelID7P1czxCBy1N4G2I/SUy5Bh3F6s3Vvm1SjQc3czRgSl\n 5u+3xyKYL2EyzT2/BGOpcpDK3lP2s2suECBAI5pK1qk0DmYGzP3uJgZeLf+0dbpvq8sO\n DUld/xedPlDw01OHpSKfG9zj+5h7shi93Cee2otyVudGV4edj36mIC9rh9MLONky4ewl\n tjUU7ItmLbGvGdFRKhJUZ+Z0Y86yUnVIHh53fP3hUfJ+LOWpMYKPgh7aNdwytir7mjxI\n JD3g==", "X-Google-DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1777211396; x=1777816196;\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=xlytXwevs67gNFcr4ujyMnKHEGjQPMghBz+4SCH2y1E=;\n b=frgj9au3ALPriR2kZMbRQxFclBJwcopIG0AxQ97v1zTsrJ6BRpeoVjos9p8Y5AoCk0\n SaolevBG212ABcCeYfLcn/kyLkMXErNhBNKdcTrdQAQ4FAHmMwTWrFSWd6z6UOkV+IZz\n ZJhSNqqcqddudUHNm7RCyFxcN97kDPCNc05hVU6CsEAidb1CMTLmSTqdvf0EFjtXJMfe\n Vf6rx6IEq4FJ1Vi6oUpRf+vABiUl8eTvZ0cAZPj1ln7yj51shI5mv211neLuO2DoNFNU\n GQpPo+Ar7KkCWKfLM1MWc0Sqn6+lVAVh+70/RlKl6hX/+taD0d+MDs746PmOlIKCtLYO\n TAZg==", "X-Gm-Message-State": "AOJu0Yy+2Mtvn+iVoKnxq/A9UdaZCQ867lXwsN/tQoUzUI4bGlcrI0Pk\n dnLIjOuVoDdumjrtMqhIjTuMlAVtvKNTQf9t+CRGRua64JBE/LYBl7/d6hRiY51R+kR4nh2dMe0\n +GcS5y6s=", "X-Gm-Gg": "AeBDieu+fOk4ZQFOUMXxBNDI0dUhxDEUhJ28X+NyK5LPwccRJ8IsbuiWcAzRVh34G97\n xs24fJ6+XrAVDKMKsdChvGaj0b8jc3omsQPSdpVAuM3EvW8WFHOYYx6QwgkFW0aUzfm9ofOeo73\n Fn95jOhep57JMO0waRXKa0MZScieu/zQuhG5pF01ZIGRLVy6mx2KMzFVEZByu5qHEMIMK4RJx+y\n qrs0P9ol1q515pGj8iGXx3dp8o7aq7kLS8+G4JNf871UBKYM99UM547rWyLxxQaXH95/fJozThX\n h3527m6foblKeXqJh6MGxlUU7YEX8G1/qvQpCd4s6vgWI00Wdnxj86auWzuxob/ZnTeQuG8bMYq\n pRZPTVuisZGI1untgj5R3+HuI71ZWk3LJ8XuwY8REKgvYj1o3Wyoh0XEhS4X2UYTSn/Tf9U7IxU\n DZwUqiIjbqmSdGn2rb1gUhQD5QTtQEWnZSeQnifnrQ", "X-Received": "by 2002:a05:6a00:408e:b0:827:2a07:231d with SMTP id\n d2e1a72fcca58-82f8c839c08mr41148041b3a.17.1777211396516;\n Sun, 26 Apr 2026 06:49:56 -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 82/84] target/arm: Use FloatParts64 in bfdotadd_ebf", "Date": "Sun, 26 Apr 2026 23:39:59 +1000", "Message-ID": "<20260426134002.865628-83-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::42b;\n envelope-from=richard.henderson@linaro.org; helo=mail-pf1-x42b.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=ham 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/vec_helper.c | 77 +++++++++++++++++++------------------\n 1 file changed, 40 insertions(+), 37 deletions(-)", "diff": "diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c\nindex 91e98d28ae..1f305515cf 100644\n--- a/target/arm/tcg/vec_helper.c\n+++ b/target/arm/tcg/vec_helper.c\n@@ -22,6 +22,7 @@\n #include \"helper.h\"\n #include \"tcg/tcg-gvec-desc.h\"\n #include \"fpu/softfloat.h\"\n+#include \"fpu/softfloat-parts.h\"\n #include \"qemu/int128.h\"\n #include \"crypto/clmul.h\"\n #include \"vec_internal.h\"\n@@ -2895,61 +2896,63 @@ float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2, float_status *fpst)\n float32 bfdotadd_ebf(float32 sum, uint32_t e1, uint32_t e2,\n float_status *fpst, float_status *fpst_odd)\n {\n+ /* Unpack two BFloat16 into two Float32, trivially. */\n float32 s1r = e1 << 16;\n float32 s1c = e1 & 0xffff0000u;\n float32 s2r = e2 << 16;\n float32 s2c = e2 & 0xffff0000u;\n float32 t32;\n \n+ /*\n+ * Compare f16_dotadd() in sme_helper.c, but here we have\n+ * bfloat16 inputs. In particular that means that we do not\n+ * want the FPCR.FZ16 flush semantics, so we use the normal\n+ * float_status for the input handling here.\n+ */\n+ FloatParts64 p1r = float32_unpack_canonical(s1r, fpst);\n+ FloatParts64 p1c = float32_unpack_canonical(s1c, fpst);\n+ FloatParts64 p2r = float32_unpack_canonical(s2r, fpst);\n+ FloatParts64 p2c = float32_unpack_canonical(s2c, fpst);\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 (float32_is_any_nan(s1r) || float32_is_any_nan(s1c) ||\n- float32_is_any_nan(s2r) || float32_is_any_nan(s2c)) {\n- if (float32_is_signaling_nan(s1r, fpst)) {\n- t32 = s1r;\n- } else if (float32_is_signaling_nan(s1c, fpst)) {\n- t32 = s1c;\n- } else if (float32_is_signaling_nan(s2r, fpst)) {\n- t32 = s2r;\n- } else if (float32_is_signaling_nan(s2c, fpst)) {\n- t32 = s2c;\n- } else if (float32_is_any_nan(s1r)) {\n- t32 = s1r;\n- } else if (float32_is_any_nan(s1c)) {\n- t32 = s1c;\n- } else if (float32_is_any_nan(s2r)) {\n- t32 = s2r;\n+ if (unlikely(all_mask & float_cmask_anynan)) {\n+ if (unlikely(all_mask & float_cmask_snan)) {\n+ if (p1r.cls == float_class_snan) {\n+ t32 = s1r;\n+ } else if (p1c.cls == float_class_snan) {\n+ t32 = s1c;\n+ } else if (p2r.cls == float_class_snan) {\n+ t32 = s2r;\n+ } else {\n+ t32 = s2c;\n+ }\n } else {\n- t32 = s2c;\n+ if (p1r.cls == float_class_qnan) {\n+ t32 = s1r;\n+ } else if (p1c.cls == float_class_qnan) {\n+ t32 = s1c;\n+ } else if (p2r.cls == float_class_qnan) {\n+ t32 = s2r;\n+ } else {\n+ t32 = s2c;\n+ }\n }\n /*\n * FPConvertNaN(FPProcessNaN(t32)) will be done as part\n * of the final addition below.\n */\n } else {\n- /*\n- * Compare f16_dotadd() in sme_helper.c, but here we have\n- * bfloat16 inputs. In particular that means that we do not\n- * want the FPCR.FZ16 flush semantics, so we use the normal\n- * float_status for the input handling here.\n- */\n- float64 e1r = float32_to_float64(s1r, fpst);\n- float64 e1c = float32_to_float64(s1c, fpst);\n- float64 e2r = float32_to_float64(s2r, fpst);\n- float64 e2c = float32_to_float64(s2c, fpst);\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, fpst_odd);\n- t64 = float64r32_muladd(e1c, e2c, t64, 0, fpst);\n+ FloatParts64 tmp = parts64_mul(&p1r, &p2r, fpst);\n+ tmp = parts64_muladd_scalbn(&p1c, &p2c, &tmp, 0, 0, fpst);\n \n- /* This conversion is exact, because we've already rounded. */\n- t32 = float64_to_float32(t64, fpst);\n+ t32 = float32_round_pack_canonical(&tmp, fpst);\n }\n \n /* The final accumulation step is not fused. */\n", "prefixes": [ "82/84" ] }