Patch Detail
get:
Show a patch.
patch:
Update a patch.
put:
Update a patch.
GET /api/1.1/patches/2230748/?format=api
{ "id": 2230748, "url": "http://patchwork.ozlabs.org/api/1.1/patches/2230748/?format=api", "web_url": "http://patchwork.ozlabs.org/project/qemu-devel/patch/20260430002046.59739-35-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": "<20260430002046.59739-35-richard.henderson@linaro.org>", "date": "2026-04-30T00:20:33", "name": "[v3,34/47] target/arm: Implement FCVT, FCVTN (FP32 to FP8) for SME", "commit_ref": null, "pull_url": null, "state": "new", "archived": false, "hash": "70e7e3ede5e8ed460007e56bc0d745e1829de0da", "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/20260430002046.59739-35-richard.henderson@linaro.org/mbox/", "series": [ { "id": 502175, "url": "http://patchwork.ozlabs.org/api/1.1/series/502175/?format=api", "web_url": "http://patchwork.ozlabs.org/project/qemu-devel/list/?series=502175", "date": "2026-04-30T00:20:06", "name": "target/arm: Implement FEAT_FP8", "version": 3, "mbox": "http://patchwork.ozlabs.org/series/502175/mbox/" } ], "comments": "http://patchwork.ozlabs.org/api/patches/2230748/comments/", "check": "pending", "checks": "http://patchwork.ozlabs.org/api/patches/2230748/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=EiT+25mh;\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 4g5Zj56jZCz1yJr\n\tfor <incoming@patchwork.ozlabs.org>; Thu, 30 Apr 2026 10:26:17 +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 1wIFAX-0007uU-9N; Wed, 29 Apr 2026 20:22:17 -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 1wIFAP-0007YO-HG\n for qemu-devel@nongnu.org; Wed, 29 Apr 2026 20:22:09 -0400", "from mail-pf1-x430.google.com ([2607:f8b0:4864:20::430])\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 1wIFAN-0006aV-NJ\n for qemu-devel@nongnu.org; Wed, 29 Apr 2026 20:22:09 -0400", "by mail-pf1-x430.google.com with SMTP id\n d2e1a72fcca58-82f33d28c1dso206047b3a.3\n for <qemu-devel@nongnu.org>; Wed, 29 Apr 2026 17:22:07 -0700 (PDT)", "from stoup.. ([180.233.125.15]) by smtp.gmail.com with ESMTPSA id\n d2e1a72fcca58-834ed5cd3b8sm3461727b3a.16.2026.04.29.17.22.04\n (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256);\n Wed, 29 Apr 2026 17:22:05 -0700 (PDT)" ], "DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=linaro.org; s=google; t=1777508526; x=1778113326; 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=GiTDWBFvFfWsIlgU7QlGePW8lBNeuuWLOhvxSB1tt1M=;\n b=EiT+25mh/ooc8gEfJgK/7j6+bF4JNcoKJqiU8flAayYuJRNAyZTgoh6vHOKl3tkcU2\n vlJs3CcJHjaO4WNkml+8nt2ZXDDt3tMJ3QbIIIFjVLse0n9iVxNE1D0bZ7GdjUr7aibk\n ZdW99uy4Hyjhz4JK1KBbZUD+Axtcy2ylkRDZZlbNTsR0sFOprdGL8dteOjknZQBywzQF\n SFaZUb22ZK/S+lY8N66mwT2ydASJKZ41BcPM5HVYhLegBM61zs5g9xdlMJjzVneq7xf1\n +/XEspJjcfTbGetFVV99ZAClRPz7bADyJnNJIyDHkNgF5L9+DlGhj0EsG1G3/0h//w/q\n HKVg==", "X-Google-DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1777508526; x=1778113326;\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=GiTDWBFvFfWsIlgU7QlGePW8lBNeuuWLOhvxSB1tt1M=;\n b=OWn5zPXh69RQla/06QKH6SABW3NZw19PWxynBDSDb1UVoTYRcdcW3H50JcsFN1yhsl\n AA1ithTYioJnHYMguZ8TShBSeSrMtqZH1H10gVfO8f9avBtKV40N/8N+Eh16lLjFdVcF\n ykad4qdTdDOgd9yx4K+dDkSiIHe3LCQk+46WFmrInrqz5s9PocrJpLX/iOSeWF1f40VJ\n u2JdevQp7RIQSvV/n5lui7cK2O+pFnqftnZAsY8+AtPsYhrxIoSiPTvWkrLy/TVc/dbd\n K/9Pw+fnFFeABzuXOUOK4nRhPXGRblGixsZH+rzW4DunhYWpcwZX4y2IpEe9OtUMe4X6\n TxXw==", "X-Gm-Message-State": "AOJu0YyUZBsUBpUwmu+QUix3YHb45WCBM569sNRp9m9kwrDPhtL3i1bG\n Ln2QmCHRDm1DKqdmE/Sug0fQt0yfZB53yGuDoDAS0Ic43hOCuI0EfHZV1gIrF6PehzJuG7GPX9H\n sN6pbj2s=", "X-Gm-Gg": "AeBDieuYZnP834BJXYYa4GLwtHdSygK1ruG2b5OtQGcSGxjaIZyNNHWusujO0/13zqH\n /O114DKOuu3bLg5cGrImjsS8dwY4uZPEvDsfmR0GAmr2zHPhS+IQScQm7ZdpZLDPnmzKTrREgPk\n eTPpV8hINiHbSxvHMgD3o0vzKknS5q5nEFze33QGarGQlit3yNosjdwgeFkqAxfIUlR2no/IdDa\n V1nFgAOEBPx6+yfnxSRZE4DgofOEilsnstUiTwENSotDDgb+NTqZaSLWjignX96k1iNz/lehBzG\n 6gIYDi+vd90koQflhWOhMrbumcUD5U84Nc+R3IwKY220f2KazLlo9Ofxq2cKRn6Xa3wELWZ4zQg\n lh8OYD4nlLEz6ZEqM7MkFDyvjU0lc3cHbg6eGRDonaHThMv4KkM49Zg7lHdOvpb/iSloslDwOq6\n zEzxDHl8EvTbiNENQxuu8TDSBFHZYswq8/pGwkl4CJ", "X-Received": "by 2002:a05:6a00:1827:b0:82f:6b6f:13ec with SMTP id\n d2e1a72fcca58-834fdd080f1mr787651b3a.34.1777508526216;\n Wed, 29 Apr 2026 17:22:06 -0700 (PDT)", "From": "Richard Henderson <richard.henderson@linaro.org>", "To": "qemu-devel@nongnu.org", "Cc": "qemu-arm@nongnu.org", "Subject": "[PATCH v3 34/47] target/arm: Implement FCVT,\n FCVTN (FP32 to FP8) for SME", "Date": "Thu, 30 Apr 2026 10:20:33 +1000", "Message-ID": "<20260430002046.59739-35-richard.henderson@linaro.org>", "X-Mailer": "git-send-email 2.43.0", "In-Reply-To": "<20260430002046.59739-1-richard.henderson@linaro.org>", "References": "<20260430002046.59739-1-richard.henderson@linaro.org>", "MIME-Version": "1.0", "Content-Transfer-Encoding": "8bit", "Received-SPF": "pass client-ip=2607:f8b0:4864:20::430;\n envelope-from=richard.henderson@linaro.org; helo=mail-pf1-x430.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": "Signed-off-by: Richard Henderson <richard.henderson@linaro.org>\n---\n target/arm/tcg/helper-fp8-defs.h | 2 +\n target/arm/tcg/fp8_helper.c | 95 ++++++++++++++++++++++++++++++++\n target/arm/tcg/translate-sme.c | 3 +\n target/arm/tcg/sme.decode | 3 +\n 4 files changed, 103 insertions(+)", "diff": "diff --git a/target/arm/tcg/helper-fp8-defs.h b/target/arm/tcg/helper-fp8-defs.h\nindex 5863a6dbb8..36ae977431 100644\n--- a/target/arm/tcg/helper-fp8-defs.h\n+++ b/target/arm/tcg/helper-fp8-defs.h\n@@ -21,3 +21,5 @@ DEF_HELPER_FLAGS_4(sve2_fcvtn_bh, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)\n DEF_HELPER_FLAGS_5(advsimd_fcvt_bs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32)\n DEF_HELPER_FLAGS_4(sve2_fcvtnb_bs, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)\n DEF_HELPER_FLAGS_4(sve2_fcvtnt_bs, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)\n+DEF_HELPER_FLAGS_4(sme2_fcvt_bs, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)\n+DEF_HELPER_FLAGS_4(sme2_fcvtn_bs, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)\ndiff --git a/target/arm/tcg/fp8_helper.c b/target/arm/tcg/fp8_helper.c\nindex f92ffe68e3..f0f03298d1 100644\n--- a/target/arm/tcg/fp8_helper.c\n+++ b/target/arm/tcg/fp8_helper.c\n@@ -753,3 +753,98 @@ void HELPER(sve2_fcvtnt_bs)(void *vd, void *vn, CPUARMState *env, uint32_t desc)\n \n fp8_finish(env, &ctx);\n }\n+\n+void HELPER(sme2_fcvt_bs)(void *vd, void *vn, CPUARMState *env, uint32_t desc)\n+{\n+ ARMVectorReg scratch[4];\n+ FP8Context ctx = fp8_dst_start(env, desc);\n+ uint32_t *n = vn;\n+ uint8_t *d = vd;\n+ bool osc = FIELD_EX64(env->vfp.fpmr, FPMR, OSC);\n+ size_t oprsz = simd_oprsz(desc);\n+ size_t nelem = oprsz / 4;\n+ size_t stride = sizeof(ARMVectorReg) / 4;\n+\n+ if (vectors_overlap(vd, 1, vn, 4)) {\n+ n = memcpy(scratch, vn, sizeof(scratch));\n+ }\n+\n+ switch (ctx.f8fmt) {\n+ case OFP8_E5M2:\n+ for (size_t i = 0; i < nelem; i++) {\n+ for (size_t j = 0; j < 4; j++) {\n+ float32 e = n[H4(i) + stride * j];\n+ d[H1(i + nelem * j)] =\n+ fcvt_f32_to_fp8e5m2(e, ctx.scale, osc, &ctx.stat);\n+ }\n+ }\n+ break;\n+ case OFP8_E4M3:\n+ for (size_t i = 0; i < nelem; i++) {\n+ for (size_t j = 0; j < 4; j++) {\n+ float32 e = n[H4(i) + stride * j];\n+ d[H1(i + nelem * j)] =\n+ fcvt_f32_to_fp8e4m3(e, ctx.scale, osc, &ctx.stat);\n+ }\n+ }\n+ break;\n+ default:\n+ float8_invalid_output(d, oprsz, &ctx.stat);\n+ break;\n+ }\n+\n+ fp8_finish(env, &ctx);\n+}\n+\n+void HELPER(sme2_fcvtn_bs)(void *vd, void *vn, CPUARMState *env, uint32_t desc)\n+{\n+ FP8Context ctx = fp8_dst_start(env, desc);\n+ uint32_t *n0 = vn;\n+ uint32_t *n1 = vn + sizeof(ARMVectorReg);\n+ uint32_t *n2 = vn + sizeof(ARMVectorReg) * 2;\n+ uint32_t *n3 = vn + sizeof(ARMVectorReg) * 3;\n+ uint8_t *d = vd;\n+ bool osc = FIELD_EX64(env->vfp.fpmr, FPMR, OSC);\n+ size_t oprsz = simd_oprsz(desc);\n+ size_t nelem = oprsz / 4;\n+\n+ switch (ctx.f8fmt) {\n+ case OFP8_E5M2:\n+ for (size_t i = 0; i < nelem; ++i) {\n+ float32 e0 = n0[H2(i)];\n+ float32 e1 = n1[H2(i)];\n+ float32 e2 = n2[H2(i)];\n+ float32 e3 = n3[H2(i)];\n+ d[H1(4 * i + 0)] =\n+ fcvt_f32_to_fp8e5m2(e0, ctx.scale, osc, &ctx.stat);\n+ d[H1(4 * i + 1)] =\n+ fcvt_f32_to_fp8e5m2(e1, ctx.scale, osc, &ctx.stat);\n+ d[H1(4 * i + 2)] =\n+ fcvt_f32_to_fp8e5m2(e2, ctx.scale, osc, &ctx.stat);\n+ d[H1(4 * i + 3)] =\n+ fcvt_f32_to_fp8e5m2(e3, ctx.scale, osc, &ctx.stat);\n+ }\n+ break;\n+ case OFP8_E4M3:\n+ for (size_t i = 0; i < nelem; ++i) {\n+ float32 e0 = n0[H2(i)];\n+ float32 e1 = n1[H2(i)];\n+ float32 e2 = n2[H2(i)];\n+ float32 e3 = n3[H2(i)];\n+ d[H1(4 * i + 0)] =\n+ fcvt_f32_to_fp8e4m3(e0, ctx.scale, osc, &ctx.stat);\n+ d[H1(4 * i + 1)] =\n+ fcvt_f32_to_fp8e4m3(e1, ctx.scale, osc, &ctx.stat);\n+ d[H1(4 * i + 2)] =\n+ fcvt_f32_to_fp8e4m3(e2, ctx.scale, osc, &ctx.stat);\n+ d[H1(4 * i + 3)] =\n+ fcvt_f32_to_fp8e4m3(e3, ctx.scale, osc, &ctx.stat);\n+ }\n+ break;\n+ default:\n+ float8_invalid_output(d, oprsz, &ctx.stat);\n+ break;\n+ }\n+\n+ fp8_finish(env, &ctx);\n+}\ndiff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c\nindex 050c3cfefe..2f79c458e1 100644\n--- a/target/arm/tcg/translate-sme.c\n+++ b/target/arm/tcg/translate-sme.c\n@@ -1572,6 +1572,9 @@ static bool trans_FCVT_bh(DisasContext *s, arg_zz_n *a)\n return true;\n }\n \n+TRANS_FEAT(FCVT_bs, aa64_sme2_f8cvt, do_f8cvt, a, gen_helper_sme2_fcvt_bs, 0)\n+TRANS_FEAT(FCVTN_bs, aa64_sme2_f8cvt, do_f8cvt, a, gen_helper_sme2_fcvtn_bs, 0)\n+\n static bool do_zipuzp_4(DisasContext *s, arg_zz_e *a,\n gen_helper_gvec_2 * const fn[5])\n {\ndiff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode\nindex a02bcc0e22..2b9e41a75a 100644\n--- a/target/arm/tcg/sme.decode\n+++ b/target/arm/tcg/sme.decode\n@@ -865,6 +865,9 @@ BF2CVTL 11000001 111 00110 111000 ..... ....1 @zz_2x1\n \n FCVT_bh 11000001 001 00100 111000 ....0 ..... @zz_1x2\n \n+FCVT_bs 11000001 001 10100 111000 ...00 ..... @zz_1x4\n+FCVTN_bs 11000001 001 10100 111000 ...01 ..... @zz_1x4\n+\n ZIP_4 11000001 esz:2 1 10110 111000 ...00 ... 00 \\\n &zz_e zd=%zd_ax4 zn=%zn_ax4\n ZIP_4 11000001 001 10111 111000 ...00 ... 00 \\\n", "prefixes": [ "v3", "34/47" ] }