{"id":2227688,"url":"http://patchwork.ozlabs.org/api/patches/2227688/?format=json","web_url":"http://patchwork.ozlabs.org/project/qemu-devel/patch/20260424043014.46305-25-richard.henderson@linaro.org/","project":{"id":14,"url":"http://patchwork.ozlabs.org/api/projects/14/?format=json","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":"","list_archive_url":"","list_archive_url_format":"","commit_url_format":""},"msgid":"<20260424043014.46305-25-richard.henderson@linaro.org>","list_archive_url":null,"date":"2026-04-24T04:29:58","name":"[v2,24/40] target/arm: Implement BF1CVT, BF1CVTLT, BF2CVT, BF2CVTLT for SVE","commit_ref":null,"pull_url":null,"state":"new","archived":false,"hash":"76c91b6e6db158d5a35af7d3ecbcaf5dde7895f8","submitter":{"id":72104,"url":"http://patchwork.ozlabs.org/api/people/72104/?format=json","name":"Richard Henderson","email":"richard.henderson@linaro.org"},"delegate":null,"mbox":"http://patchwork.ozlabs.org/project/qemu-devel/patch/20260424043014.46305-25-richard.henderson@linaro.org/mbox/","series":[{"id":501300,"url":"http://patchwork.ozlabs.org/api/series/501300/?format=json","web_url":"http://patchwork.ozlabs.org/project/qemu-devel/list/?series=501300","date":"2026-04-24T04:29:37","name":"target/arm: Implement FEAT_FP8","version":2,"mbox":"http://patchwork.ozlabs.org/series/501300/mbox/"}],"comments":"http://patchwork.ozlabs.org/api/patches/2227688/comments/","check":"pending","checks":"http://patchwork.ozlabs.org/api/patches/2227688/checks/","tags":{},"related":[],"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=oY87iRQ8;\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 4g20WL6qctz1yD5\n\tfor <incoming@patchwork.ozlabs.org>; Fri, 24 Apr 2026 14:35:26 +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 1wG8DD-0001G6-7i; Fri, 24 Apr 2026 00:32:19 -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 1wG8D1-0000jD-Jj\n for qemu-devel@nongnu.org; Fri, 24 Apr 2026 00:32:09 -0400","from mail-oa1-x29.google.com ([2001:4860:4864:20::29])\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 1wG8Cz-0003HW-PL\n for qemu-devel@nongnu.org; Fri, 24 Apr 2026 00:32:07 -0400","by mail-oa1-x29.google.com with SMTP id\n 586e51a60fabf-40974bf7781so6629175fac.0\n for <qemu-devel@nongnu.org>; Thu, 23 Apr 2026 21:32:05 -0700 (PDT)","from stoup.. ([172.58.183.19]) by smtp.gmail.com with ESMTPSA id\n 586e51a60fabf-42b9ac54ec5sm18880864fac.13.2026.04.23.21.32.01\n (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256);\n Thu, 23 Apr 2026 21:32:04 -0700 (PDT)"],"DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=linaro.org; s=google; t=1777005125; x=1777609925; 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=BiQ5icxQbNLrKse61brBqsCLHCU36Le6q/LoWKJ1fb4=;\n b=oY87iRQ8WPRYwj6oXpPoEMxb3RucdR1LHuawyNlGtoVndx7+ktWfHH/Swg2UBsclzl\n 4LLk343FKdVuIFlf3Y0IneSqllRTLdfILCKdTnCvWTubI6LIBf/3+xWgPfleTMUz8sEE\n Zsk+LjsyogJmsrKcv5tJVC347unMn7WSGOSeXwCo9sFOoLbDMw2hcto1NhWNXE7mexxO\n kFKtM+kUXtJp3r28t/sOdfXMpejW0zNhlYDdkMLDhm22BOCvs9yQxdkhMNitVFjra7Rp\n 7yUiFHDUvDjpI4m+KA1syY+ONR3F4GMkBc7whyXemwCMCAoq0HSPh8UcAqpNI9YUJ4xd\n 8Guw==","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1777005125; x=1777609925;\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=BiQ5icxQbNLrKse61brBqsCLHCU36Le6q/LoWKJ1fb4=;\n b=G5uaDS4fAUhnK3w0k1IFSpld5GHJ82gBPK5mA+brMT+ELTHByuUpux6PNPE8YR7+ZO\n aRPpRy1lnE0mRqfwfkxCz4tdJxTZPKlBSC/pLVGNAKWv+k4ys7Q8kdrCvHh6qMV6JsNJ\n PTXE6PHrTbhiSYYqfg2LUFVz6qwTZUTZ33yoPYAtL/528C0W8fEaSCAW98FxoCwYW5nf\n 6kBYVN8GwfzbRL5C9ZUY7sZPlflpuhgRs9hjMwWrbWfPXtuXGSwcJCa66zCKjII4y7ql\n kgA6ybt+IJ12uIHidAdyoMj1rElK60+oO0n/RK5CFRvIihaQcmJ5Zk8GlDpaFZc0IwwD\n rM5w==","X-Gm-Message-State":"AOJu0Yyw3BqQiI+l5MPJ8q9MR0GObvMF7HD9LB9tAUbreOm2d5u1vR0Z\n m6xpA7+Ubu2O+YYmGHi6h6FwcP2j54M2JpKKu7IPtaegE1R3jD7V6QjiDS8VOmb2moI1ZOeOAJU\n RRetfpf8=","X-Gm-Gg":"AeBDieuascl1kSt3sRhX5DH5129xnRz6VUGVLB97vf9SQuu5+6/M0ptxTJQ2ZDR/ivp\n 65s3/oKFCHHIAVyCjXoZ7hosDQrIlO5AehWqEk5Buk2rNPtMvQpULyHPg2RyYmcHO3lB06yCuTT\n tXeLwdrEp8Lm9Ky6JH24qyZZ0DVoruffuwRLiEzs4msD3U9BtPGpLyJA+gvjmkoQmg/TDOzfwAW\n YpFodvQfijJrtgeJlOaI0DgHTKsd9YZIDC2372ah7Q7IKQBELgnNQE769WCC8h7qDrRO6ygz4cE\n vk5hbqc5hCmdB15BKd5QCa1+aQq24r1KTRSx+DU8v1ooXbOAtITNoJMDFlbPPQ5DXPMEOCizRsk\n rSA5TEF+zyGa9MwFJ3AQ1JwNKUR8LQuCxprdKxDCICDAQ+4qelQAwmB6IS5+z/G1LIcLY6+27yc\n 9LqygJNMF3/focegCanAsfcTEK9lxeBewUF9QT1MZvdDB0VEHTKck6rav2AGtHOw==","X-Received":"by 2002:a05:6870:b50e:b0:409:6148:e23e with SMTP id\n 586e51a60fabf-42a9986c2f1mr15470732fac.10.1777005124487;\n Thu, 23 Apr 2026 21:32:04 -0700 (PDT)","From":"Richard Henderson <richard.henderson@linaro.org>","To":"qemu-devel@nongnu.org","Cc":"qemu-arm@nongnu.org","Subject":"[PATCH v2 24/40] target/arm: Implement BF1CVT, BF1CVTLT, BF2CVT,\n BF2CVTLT for SVE","Date":"Fri, 24 Apr 2026 14:29:58 +1000","Message-ID":"<20260424043014.46305-25-richard.henderson@linaro.org>","X-Mailer":"git-send-email 2.43.0","In-Reply-To":"<20260424043014.46305-1-richard.henderson@linaro.org>","References":"<20260424043014.46305-1-richard.henderson@linaro.org>","MIME-Version":"1.0","Content-Transfer-Encoding":"8bit","Received-SPF":"pass client-ip=2001:4860:4864:20::29;\n envelope-from=richard.henderson@linaro.org; helo=mail-oa1-x29.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/cpu-features.h        |  6 ++++++\n target/arm/tcg/helper-fp8-defs.h |  1 +\n target/arm/tcg/fp8_helper.c      | 28 ++++++++++++++++++++++++++++\n target/arm/tcg/translate-sve.c   | 23 +++++++++++++++++++++++\n target/arm/tcg/sve.decode        |  6 ++++++\n 5 files changed, 64 insertions(+)","diff":"diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h\nindex 8a6e5d555b..7f1a394ef0 100644\n--- a/target/arm/cpu-features.h\n+++ b/target/arm/cpu-features.h\n@@ -1624,6 +1624,12 @@ isar_feature_aa64_sme2_or_sve2_faminmax(const ARMISARegisters *id)\n     return isar_feature_aa64_sme2_or_sve2(id) && isar_feature_aa64_faminmax(id);\n }\n \n+static inline bool\n+isar_feature_aa64_sme2_or_sve2_f8cvt(const ARMISARegisters *id)\n+{\n+    return isar_feature_aa64_sme2_or_sve2(id) && isar_feature_aa64_f8cvt(id);\n+}\n+\n /*\n  * Feature tests for \"does this exist in either 32-bit or 64-bit?\"\n  */\ndiff --git a/target/arm/tcg/helper-fp8-defs.h b/target/arm/tcg/helper-fp8-defs.h\nindex 0caaf63749..18ff483bb0 100644\n--- a/target/arm/tcg/helper-fp8-defs.h\n+++ b/target/arm/tcg/helper-fp8-defs.h\n@@ -4,3 +4,4 @@\n  */\n \n DEF_HELPER_FLAGS_4(advsimd_bfcvtl, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)\n+DEF_HELPER_FLAGS_4(sve2_bfcvt, 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 a2efdd5cd7..b03345c670 100644\n--- a/target/arm/tcg/fp8_helper.c\n+++ b/target/arm/tcg/fp8_helper.c\n@@ -121,3 +121,31 @@ void HELPER(advsimd_bfcvtl)(void *vd, void *vn, CPUARMState *env, uint32_t desc)\n     fp8_finish(env, &ctx);\n     clear_tail(vd, 16, simd_maxsz(desc));\n }\n+\n+void HELPER(sve2_bfcvt)(void *vd, void *vn, CPUARMState *env, uint32_t desc)\n+{\n+    FP8Context ctx = fp8_src_start(env, desc, 0x3f);\n+    uint8_t *n = vn;\n+    uint16_t *d = vd;\n+    size_t nelem = simd_oprsz(desc) / 2;\n+\n+    switch (ctx.f8fmt) {\n+    case OFP8_E5M2:\n+        for (size_t i = 0; i < nelem; ++i) {\n+            float8_e5m2 e = n[H1(2 * i + ctx.high)];\n+            d[H2(i)] = float8_e5m2_to_bfloat16(e, ctx.scale, &ctx.stat);\n+        }\n+        break;\n+    case OFP8_E4M3:\n+        for (size_t i = 0; i < nelem; ++i) {\n+            float8_e4m3 e = n[H1(2 * i + ctx.high)];\n+            d[H2(i)] = float8_e4m3_to_bfloat16(e, ctx.scale, &ctx.stat);\n+        }\n+        break;\n+    default:\n+        bfloat16_invalid_input(d, nelem, &ctx.stat);\n+        break;\n+    }\n+\n+    fp8_finish(env, &ctx);\n+}\ndiff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c\nindex 756c4373b5..1540cbd6de 100644\n--- a/target/arm/tcg/translate-sve.c\n+++ b/target/arm/tcg/translate-sve.c\n@@ -21,6 +21,7 @@\n #include \"cpu.h\"\n #include \"helper-sme.h\"\n #include \"helper-sve.h\"\n+#include \"helper-fp8.h\"\n #include \"translate.h\"\n #include \"translate-a64.h\"\n #include \"fpu/softfloat.h\"\n@@ -4066,6 +4067,28 @@ TRANS_FEAT(FRSQRTE, aa64_sme_or_sve, gen_gvec_fpst_ah_arg_zz,\n            s->fpcr_ah && dc_isar_feature(aa64_rpres, s) ?\n            frsqrte_rpres_fns[a->esz] : frsqrte_fns[a->esz], a, 0)\n \n+static bool do_f8cvt(DisasContext *s, arg_rr_esz *a,\n+                     gen_helper_gvec_2_ptr *fn, bool issrc2, bool isodd)\n+{\n+    if (fpmr_access_check(s) && sve_access_check(s)) {\n+        unsigned vsz = vec_full_reg_size(s);\n+        tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->rd),\n+                           vec_full_reg_offset(s, a->rn),\n+                           tcg_env, vsz, vsz,\n+                           issrc2 | (isodd << 1) | (FPST_A64 << 2), fn);\n+    }\n+    return true;\n+}\n+\n+TRANS_FEAT(BF1CVT, aa64_sme2_or_sve2_f8cvt, do_f8cvt, a,\n+           gen_helper_sve2_bfcvt, false, false)\n+TRANS_FEAT(BF2CVT, aa64_sme2_or_sve2_f8cvt, do_f8cvt, a,\n+           gen_helper_sve2_bfcvt, true, false)\n+TRANS_FEAT(BF1CVTLT, aa64_sme2_or_sve2_f8cvt, do_f8cvt, a,\n+           gen_helper_sve2_bfcvt, false, true)\n+TRANS_FEAT(BF2CVTLT, aa64_sme2_or_sve2_f8cvt, do_f8cvt, a,\n+           gen_helper_sve2_bfcvt, true, true)\n+\n /*\n  *** SVE Floating Point Compare with Zero Group\n  */\ndiff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode\nindex 078a085a79..e7984fa8e0 100644\n--- a/target/arm/tcg/sve.decode\n+++ b/target/arm/tcg/sve.decode\n@@ -108,6 +108,7 @@\n # Two operand\n @pd_pn          ........ esz:2 .. .... ....... rn:4 . rd:4      &rr_esz\n @rd_rn          ........ esz:2 ...... ...... rn:5 rd:5          &rr_esz\n+@rd_rn_e0       ........ .. ...... ...... rn:5 rd:5             &rr_esz esz=0\n @rd_rnx2        ........ ... ..... ...... ..... rd:5            &rr_esz rn=%rn_ax2\n \n # Two operand with governing predicate, flags setting\n@@ -1090,6 +1091,11 @@ FMINQV          01100100 .. 010 111 101 ... ..... .....         @rd_pg_rn\n FRECPE          01100101 .. 001 110 001100 ..... .....          @rd_rn\n FRSQRTE         01100101 .. 001 111 001100 ..... .....          @rd_rn\n \n+BF1CVT          01100101 00 001 000 001110 ..... .....          @rd_rn_e0\n+BF2CVT          01100101 00 001 000 001111 ..... .....          @rd_rn_e0\n+BF1CVTLT        01100101 00 001 001 001110 ..... .....          @rd_rn_e0\n+BF2CVTLT        01100101 00 001 001 001111 ..... .....          @rd_rn_e0\n+\n ### SVE FP Compare with Zero Group\n \n FCMGE_ppz0      01100101 .. 0100 00 001 ... ..... 0 ....        @pd_pg_rn\n","prefixes":["v2","24/40"]}