{"id":2227681,"url":"http://patchwork.ozlabs.org/api/patches/2227681/?format=json","web_url":"http://patchwork.ozlabs.org/project/qemu-devel/patch/20260424043014.46305-35-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":"<20260424043014.46305-35-richard.henderson@linaro.org>","list_archive_url":null,"date":"2026-04-24T04:30:08","name":"[v2,34/40] target/arm: Implement FCVTNB, FCVTNT for SVE","commit_ref":null,"pull_url":null,"state":"new","archived":false,"hash":"13efcebc8fc88866a80997da60987577f19e3ed9","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/20260424043014.46305-35-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/2227681/comments/","check":"pending","checks":"http://patchwork.ozlabs.org/api/patches/2227681/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=HcMIb/bE;\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 4g20VB1QSWz1yDD\n\tfor <incoming@patchwork.ozlabs.org>; Fri, 24 Apr 2026 14:34:26 +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 1wG8De-00038J-Vb; Fri, 24 Apr 2026 00:32:47 -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 1wG8DY-0002wR-Fh\n for qemu-devel@nongnu.org; Fri, 24 Apr 2026 00:32:40 -0400","from mail-oo1-xc2e.google.com ([2607:f8b0:4864:20::c2e])\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 1wG8DW-0003cA-JA\n for qemu-devel@nongnu.org; Fri, 24 Apr 2026 00:32:40 -0400","by mail-oo1-xc2e.google.com with SMTP id\n 006d021491bc7-67e0d3f288aso4596861eaf.0\n for <qemu-devel@nongnu.org>; Thu, 23 Apr 2026 21:32:38 -0700 (PDT)","from stoup.. ([172.58.183.19]) by smtp.gmail.com with ESMTPSA id\n 586e51a60fabf-42b9ac54ec5sm18880864fac.13.2026.04.23.21.32.33\n (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256);\n Thu, 23 Apr 2026 21:32:36 -0700 (PDT)"],"DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=linaro.org; s=google; t=1777005157; x=1777609957; 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=WADg8Bv+oZ53s3C00yS+/mTr8WhaGyfIt8vkJcIP8Zg=;\n b=HcMIb/bE3x3f4MXgaO+WrNpxTBRBcHZdXwvnalzokLswK6IzsEMH4PCbgGdjQS+OKl\n bmeTqRwNb7guNSKWIjS3pN5ng7AROti309U9DfP3Qp5r3pQefb/YdU82SQn2B/7gKC1j\n L9JDQhzVrkblE1Xkg6BBmFHPzIGZDGYYCbvshxV1lSg5iOiC4U+10A6zhF5ycISGPB/k\n tFXSkphkTAihMRkQb6jJPiYfvQpyKzyPGP/C6pfxJvbKrSZ7GNfn37XblMIB5Y1vxRTr\n JMclhSB4HldyT3RUBID59jVFMdaetiF/0XAdRxPravnSsDQZq1wNJpqrifwN+8dWmnX9\n 7HjA==","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1777005157; x=1777609957;\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=WADg8Bv+oZ53s3C00yS+/mTr8WhaGyfIt8vkJcIP8Zg=;\n b=RGoFPP3dPVdIXfWITJeHBOs4yxvM7wntQB1R4hsmg9u7W2Z+7uKGxtmRhIqTrridK7\n GggP1/EIRL5GtR+y8dBF9NO+mbIK0iSwBk40bd9adv/iNDKTICprh90Irz7Co8Ho0+69\n Ke7ZvUjSkYqzdd5nPSc2ihXHt031sBrnMzkAqFGv75PQcQI48TDy+6OSGmpmFZCeViTi\n pSTkgK+UKv2rY9eEd7pt6aaIdsK3lOuVeRN1p43c2WNxyd/SL3FGW3nAlW7ORd5+b9Co\n o+oWdYY5SY6NEV7NexTT9rha9C+tNtJAVFRwM/WsT35mddgnUnD6FjeM9eZvRwxH86tL\n wCJw==","X-Gm-Message-State":"AOJu0Yz61xsbSDc9p1leh8FI9b/kwKS5gAPe7scq9B7bcamu3PuIx6TU\n b3rCR8HPb8kq/0g61u0cC+I97L1Ok/71juZnhdCjPvaEHekToufE7kBveDZ62iwouawWau3v1h/\n RgQF8sDg=","X-Gm-Gg":"AeBDieveaFPh+gNPwreq74T77oLyMceZIAAUUKhiZi7bSkD588fvA/n4fECVMPi3I0N\n J4joOs/V1Q1aODWGiyll8vKn1CY4UJt91vqFIbUoMZ9FEgCY9Pcoyfq9aEw20jCqgrrLFhZ4sai\n MzdgPFImwmRBguw56lwrT6e2V8zbS1L375/CnqjpDjMrhLvAOsdUezWopkWLc94zNLMEyqS8Ry7\n FTlulcUB1vsot+lwDPKSNnIKn0yMf1oyBE9jZpmPi9zlEj1fzX+GsaT5Y0AP9oQjiQbNp6RJKYU\n hX7VHIgQQ3BGB2ANNOjuUNwG8CNhYd28JuwfWgSH7vYEHwA4KheyvupZU6ny6KSvAzeDlBYRCfH\n fabGGoUJXXmo2oouPUJvjFItyy17oEXwZ1r30PoDdPIITm/Syn+Yh5Tqd2RZThO1g1XmnT9A5YZ\n /tlsgVK9fcc+hTqjHKwFQyFuqGCBWNfMHNI3rt/eu82xUWaaSJSv5TZ1DMdioVHg==","X-Received":"by 2002:a05:6820:c0cb:10b0:67e:36e9:79ac with SMTP id\n 006d021491bc7-69462e6234dmr12220810eaf.27.1777005157324;\n Thu, 23 Apr 2026 21:32:37 -0700 (PDT)","From":"Richard Henderson <richard.henderson@linaro.org>","To":"qemu-devel@nongnu.org","Cc":"qemu-arm@nongnu.org","Subject":"[PATCH v2 34/40] target/arm: Implement FCVTNB, FCVTNT for SVE","Date":"Fri, 24 Apr 2026 14:30:08 +1000","Message-ID":"<20260424043014.46305-35-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=2607:f8b0:4864:20::c2e;\n envelope-from=richard.henderson@linaro.org; helo=mail-oo1-xc2e.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      | 85 +++++++++++++++++++++++++++++++-\n target/arm/tcg/translate-sve.c   |  4 ++\n target/arm/tcg/sve.decode        |  2 +\n 4 files changed, 92 insertions(+), 1 deletion(-)","diff":"diff --git a/target/arm/tcg/helper-fp8-defs.h b/target/arm/tcg/helper-fp8-defs.h\nindex e67fb191c2..5863a6dbb8 100644\n--- a/target/arm/tcg/helper-fp8-defs.h\n+++ b/target/arm/tcg/helper-fp8-defs.h\n@@ -19,3 +19,5 @@ DEF_HELPER_FLAGS_5(gvec_fcvt_bh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32)\n DEF_HELPER_FLAGS_4(sve2_fcvtn_bh, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)\n \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)\ndiff --git a/target/arm/tcg/fp8_helper.c b/target/arm/tcg/fp8_helper.c\nindex 9bc1349950..ebd448b466 100644\n--- a/target/arm/tcg/fp8_helper.c\n+++ b/target/arm/tcg/fp8_helper.c\n@@ -520,7 +520,6 @@ void HELPER(sve2_fcvtn_bh)(void *vd, void *vn, CPUARMState *env, uint32_t desc)\n     fp8_finish(env, &ctx);\n }\n \n-\n void HELPER(advsimd_fcvt_bs)(void *vd, void *vn, void *vm,\n                              CPUARMState *env, uint32_t desc)\n {\n@@ -562,3 +561,87 @@ void HELPER(advsimd_fcvt_bs)(void *vd, void *vn, void *vm,\n     fp8_finish(env, &ctx);\n     clear_tail(vd, ctx.high ? 16 : 8, simd_maxsz(desc));\n }\n+\n+void HELPER(sve2_fcvtnb_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+    uint16_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+            d[H2(2 * i + 0)] =\n+                float32_to_float8_e5m2(e0, ctx.scale, osc, &ctx.stat);\n+            d[H2(2 * i + 1)] =\n+                float32_to_float8_e5m2(e1, 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+            d[H2(2 * i + 0)] =\n+                float32_to_float8_e4m3(e0, ctx.scale, osc, &ctx.stat);\n+            d[H2(2 * i + 1)] =\n+                float32_to_float8_e4m3(e1, ctx.scale, osc, &ctx.stat);\n+        }\n+        break;\n+    default:\n+        for (size_t i = 0; i < oprsz; i += 8) {\n+            *(uint64_t *)(vd + i) = 0x00ff00ff00ff00ffull;\n+        }\n+        float_raise(float_flag_invalid, &ctx.stat);\n+        break;\n+    }\n+\n+    fp8_finish(env, &ctx);\n+}\n+\n+void HELPER(sve2_fcvtnt_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+    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+            uint8_t d0 = float32_to_float8_e5m2(e0, ctx.scale, osc, &ctx.stat);\n+            uint8_t d1 = float32_to_float8_e5m2(e1, ctx.scale, osc, &ctx.stat);\n+            d[H1(4 * i + 1)] = d0;\n+            d[H1(4 * i + 3)] = d1;\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+            uint8_t d0 = float32_to_float8_e4m3(e0, ctx.scale, osc, &ctx.stat);\n+            uint8_t d1 = float32_to_float8_e4m3(e1, ctx.scale, osc, &ctx.stat);\n+            d[H1(4 * i + 1)] = d0;\n+            d[H1(4 * i + 3)] = d1;\n+        }\n+        break;\n+    default:\n+        for (size_t i = 0; i < oprsz; i += 8) {\n+            *(uint64_t *)(vd + i) |= 0xff00ff00ff00ff00ull;\n+        }\n+        float_raise(float_flag_invalid, &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 319a28e94a..eff3e71ade 100644\n--- a/target/arm/tcg/translate-sve.c\n+++ b/target/arm/tcg/translate-sve.c\n@@ -4102,6 +4102,10 @@ TRANS_FEAT(FCVTN, aa64_sme2_or_sve2_f8cvt, do_f8cvt,\n            a, gen_helper_sve2_fcvtn_bh, false, false)\n TRANS_FEAT(BFCVTN, aa64_sme2_or_sve2_f8cvt, do_f8cvt,\n            a, gen_helper_sve2_bfcvtn_bh, false, false)\n+TRANS_FEAT(FCVTNB, aa64_sme2_or_sve2_f8cvt, do_f8cvt,\n+           a, gen_helper_sve2_fcvtnb_bs, false, false)\n+TRANS_FEAT(FCVTNT, aa64_sme2_or_sve2_f8cvt, do_f8cvt,\n+           a, gen_helper_sve2_fcvtnt_bs, false, false)\n \n /*\n  *** SVE Floating Point Compare with Zero Group\ndiff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode\nindex 806953bc35..7fce189b36 100644\n--- a/target/arm/tcg/sve.decode\n+++ b/target/arm/tcg/sve.decode\n@@ -1103,6 +1103,8 @@ BF2CVTLT        01100101 00 001 001 001111 ..... .....          @rd_rn_e0\n \n FCVTN           01100101 00 001 010 001100 ....0 .....          @rd_rnx2 esz=1\n BFCVTN          01100101 00 001 010 001110 ....0 .....          @rd_rnx2 esz=1\n+FCVTNB          01100101 00 001 010 001101 ....0 .....          @rd_rnx2 esz=1\n+FCVTNT          01100101 00 001 010 001111 ....0 .....          @rd_rnx2 esz=1\n \n ### SVE FP Compare with Zero Group\n \n","prefixes":["v2","34/40"]}