Patch Detail
get:
Show a patch.
patch:
Update a patch.
put:
Update a patch.
GET /api/patches/2227677/?format=api
{ "id": 2227677, "url": "http://patchwork.ozlabs.org/api/patches/2227677/?format=api", "web_url": "http://patchwork.ozlabs.org/project/qemu-devel/patch/20260424043014.46305-27-richard.henderson@linaro.org/", "project": { "id": 14, "url": "http://patchwork.ozlabs.org/api/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": "", "list_archive_url": "", "list_archive_url_format": "", "commit_url_format": "" }, "msgid": "<20260424043014.46305-27-richard.henderson@linaro.org>", "list_archive_url": null, "date": "2026-04-24T04:30:00", "name": "[v2,26/40] target/arm: Implement BF1CVT, BF1CVTL, BF2CVT, BF2CVTL for SME", "commit_ref": null, "pull_url": null, "state": "new", "archived": false, "hash": "6b164afbb9b9f2eb0240b3f87d444c74a71da1f4", "submitter": { "id": 72104, "url": "http://patchwork.ozlabs.org/api/people/72104/?format=api", "name": "Richard Henderson", "email": "richard.henderson@linaro.org" }, "delegate": null, "mbox": "http://patchwork.ozlabs.org/project/qemu-devel/patch/20260424043014.46305-27-richard.henderson@linaro.org/mbox/", "series": [ { "id": 501300, "url": "http://patchwork.ozlabs.org/api/series/501300/?format=api", "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/2227677/comments/", "check": "pending", "checks": "http://patchwork.ozlabs.org/api/patches/2227677/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=m9zR1A5u;\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 4g20Th6hWMz1yDD\n\tfor <incoming@patchwork.ozlabs.org>; Fri, 24 Apr 2026 14:34:00 +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 1wG8DF-0001ck-WD; Fri, 24 Apr 2026 00:32:22 -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 1wG8DC-0001Fo-BM\n for qemu-devel@nongnu.org; Fri, 24 Apr 2026 00:32:18 -0400", "from mail-ot1-x333.google.com ([2607:f8b0:4864:20::333])\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 1wG8DA-0003ON-7Z\n for qemu-devel@nongnu.org; Fri, 24 Apr 2026 00:32:17 -0400", "by mail-ot1-x333.google.com with SMTP id\n 46e09a7af769-7dbcb467f2bso6819289a34.3\n for <qemu-devel@nongnu.org>; Thu, 23 Apr 2026 21:32:15 -0700 (PDT)", "from stoup.. ([172.58.183.19]) by smtp.gmail.com with ESMTPSA id\n 586e51a60fabf-42b9ac54ec5sm18880864fac.13.2026.04.23.21.32.10\n (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256);\n Thu, 23 Apr 2026 21:32:12 -0700 (PDT)" ], "DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=linaro.org; s=google; t=1777005133; x=1777609933; 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=YtGKPI9ZpKsuZkMA/HWHFsmsOIe2bn1o6/gZpN9uRvQ=;\n b=m9zR1A5uSdUp7p6XgmaF4fGjRP6SZHS137+KOZ8/02tnjpBu0OQyrq9hYhgp++Yvcn\n t+Yf054IsLqCknLODwtEU28jrc6/aqvZVJ/zLEJMkXE3KENX46bZCsKvTDErGivIYjGu\n W7CAsl4uuxETwmcpqPU6EKo9cM7EmTDxRk627LB1JmUW7upzbL2RpYOiaosGV/ejee6a\n N5/fJ0Y4QRpop/cFjgyiRIQR6U3RpiCIxQKL2Ynm8nuDjqBb7qU22iOoHqrY9FTBcJM4\n BRQXv+j8TrdP7j1z8P4phzMn4smKHDS7j6npVlIWHvgNIeUMfRDNJHLcRVkxqfKoMghD\n 4lLQ==", "X-Google-DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1777005133; x=1777609933;\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=YtGKPI9ZpKsuZkMA/HWHFsmsOIe2bn1o6/gZpN9uRvQ=;\n b=iz9n3Tj9pe9UlBjBucYXVxjGIuLGLTMGQ94VntsA0VsajhlmmvRGsOEOzlufYS8S5G\n +UCt6Ruf3841DwYlRiIkW1WVpr7En4VCQxXUpdxyXhJDSYpQ37ALYwR02Il4fJoGJE9j\n qIpJgAI9/PENvfldzPtjLo6voSxB/LkaEXhdeLVcu0rWGv3JsLNNwIPDf1zMWf5NPPPl\n ex5T6oJFGmWWY6JWmo0uHK7vdAFnmLKEm//9PQUXvhB7irsSk6caSPuOEt7JqeFsBelZ\n Yz92irXcyytuRc6kpNLu0/aFuQ6Gj9ptjewjfs8SDQtiwf5EB7g5LpTfvV8C0Yw/NqPl\n sY3g==", "X-Gm-Message-State": "AOJu0YxIdQc/6hgQRugubItmQpm7CwMJuc5zI5DMdP7BA1SFSkGZoIFE\n gkQV76bZdKdlvIJfW3nobwCn4Xo6hcSsIwkXXkd3NDHTDEBTeUGGPrZUjUwSywE5BouGzFwbErk\n EhPCZhqo=", "X-Gm-Gg": "AeBDiet0KSkbmTeVan9dasFGJFZBnMkogjgRGk+F60eUr5o9CzWM0WAQjSmQQJ6LOiP\n WEoBh1FHsODVqBWIU+XT4XO2Ghh5GDvMzjAYxvxxAIOjqVdy+sYEcHlChAc1NSdC79hxf1u9rZA\n NMZL1LOr/dwvHlbGm9qtn9R5gGz1fByvy77b/nUHXFn/Dx/JsWp3h7XK0i3q95MaYQasBbehtOM\n m0+JBS+N0x+RSBj8SKIe9e2yVJIAKzRSOymRRbOcrpYoSKHvFP15Ae8F059gwqJiru9Mw2CPABS\n tgjOU5G8S7O2dBcWSQSj5+eUmr3+sILTkYsOH3dA77IklIVbkyBIl+IC5BbGgUHhHJpZY1L0BXW\n o+z00Ic7aSRorRsXA5n9vghrfYlFVCbIn2zhRzGdJQjTNxaTZqIljNT5iIM7SQIPDBm66RdL2Mp\n mT/r/WMBlIhkh7qyQp0vluCtf0DryLILZDdAvJV9UfWBAI41DIsz4cQcp9p/ejwg==", "X-Received": "by 2002:a05:6820:4df8:b0:694:a362:e3b0 with SMTP id\n 006d021491bc7-694a362e6acmr6081941eaf.49.1777005133406;\n Thu, 23 Apr 2026 21:32:13 -0700 (PDT)", "From": "Richard Henderson <richard.henderson@linaro.org>", "To": "qemu-devel@nongnu.org", "Cc": "qemu-arm@nongnu.org", "Subject": "[PATCH v2 26/40] target/arm: Implement BF1CVT, BF1CVTL, BF2CVT,\n BF2CVTL for SME", "Date": "Fri, 24 Apr 2026 14:30:00 +1000", "Message-ID": "<20260424043014.46305-27-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::333;\n envelope-from=richard.henderson@linaro.org; helo=mail-ot1-x333.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": "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 | 79 ++++++++++++++++++++++++++++++++\n target/arm/tcg/translate-sme.c | 19 ++++++++\n target/arm/tcg/sme.decode | 5 ++\n 4 files changed, 105 insertions(+)", "diff": "diff --git a/target/arm/tcg/helper-fp8-defs.h b/target/arm/tcg/helper-fp8-defs.h\nindex 18ff483bb0..966f83d796 100644\n--- a/target/arm/tcg/helper-fp8-defs.h\n+++ b/target/arm/tcg/helper-fp8-defs.h\n@@ -5,3 +5,5 @@\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)\n+DEF_HELPER_FLAGS_4(sme2_bfcvt_hb, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)\n+DEF_HELPER_FLAGS_4(sme2_bfcvtl_hb, 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 b03345c670..daf9c35720 100644\n--- a/target/arm/tcg/fp8_helper.c\n+++ b/target/arm/tcg/fp8_helper.c\n@@ -149,3 +149,82 @@ void HELPER(sve2_bfcvt)(void *vd, void *vn, CPUARMState *env, uint32_t desc)\n \n fp8_finish(env, &ctx);\n }\n+\n+void HELPER(sme2_bfcvt_hb)(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 *d0 = vd;\n+ uint16_t *d1 = vd + sizeof(ARMVectorReg);\n+ size_t oprsz = simd_oprsz(desc);\n+ size_t nelem = oprsz / 2;\n+ ARMVectorReg scratch;\n+\n+ if (vectors_overlap(vd, 2, vn, 1)) {\n+ n = memcpy(&scratch, vn, oprsz);\n+ }\n+\n+ switch (ctx.f8fmt) {\n+ case OFP8_E5M2:\n+ for (size_t i = 0; i < nelem; ++i) {\n+ float8_e5m2 e = n[H1(i)];\n+ d0[H2(i)] = float8_e5m2_to_bfloat16(e, ctx.scale, &ctx.stat);\n+ }\n+ for (size_t i = 0; i < nelem; ++i) {\n+ float8_e5m2 e = n[H1(i) + nelem];\n+ d1[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(i)];\n+ d0[H2(i)] = float8_e4m3_to_bfloat16(e, ctx.scale, &ctx.stat);\n+ }\n+ for (size_t i = 0; i < nelem; ++i) {\n+ float8_e4m3 e = n[H1(i) + nelem];\n+ d1[H2(i)] = float8_e4m3_to_bfloat16(e, ctx.scale, &ctx.stat);\n+ }\n+ break;\n+ default:\n+ bfloat16_invalid_input(d0, nelem, &ctx.stat);\n+ memcpy(d1, d0, oprsz);\n+ break;\n+ }\n+\n+ fp8_finish(env, &ctx);\n+}\n+\n+void HELPER(sme2_bfcvtl_hb)(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 *d0 = vd;\n+ uint16_t *d1 = vd + sizeof(ARMVectorReg);\n+ size_t oprsz = simd_oprsz(desc);\n+ size_t nelem = oprsz / 2;\n+\n+ switch (ctx.f8fmt) {\n+ case OFP8_E5M2:\n+ for (size_t i = 0; i < nelem; ++i) {\n+ float8_e5m2 e0 = n[H1(2 * i + 0)];\n+ float8_e5m2 e1 = n[H1(2 * i + 1)];\n+ d0[H2(i)] = float8_e5m2_to_bfloat16(e0, ctx.scale, &ctx.stat);\n+ d1[H2(i)] = float8_e5m2_to_bfloat16(e1, ctx.scale, &ctx.stat);\n+ }\n+ break;\n+ case OFP8_E4M3:\n+ for (size_t i = 0; i < nelem; ++i) {\n+ float8_e4m3 e0 = n[H1(2 * i + 0)];\n+ float8_e4m3 e1 = n[H1(2 * i + 1)];\n+ d0[H2(i)] = float8_e4m3_to_bfloat16(e0, ctx.scale, &ctx.stat);\n+ d1[H2(i)] = float8_e4m3_to_bfloat16(e1, ctx.scale, &ctx.stat);\n+ }\n+ break;\n+ default:\n+ bfloat16_invalid_input(d0, nelem, &ctx.stat);\n+ memcpy(d1, d0, oprsz);\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 1267d3e65f..3e1da83535 100644\n--- a/target/arm/tcg/translate-sme.c\n+++ b/target/arm/tcg/translate-sme.c\n@@ -22,6 +22,7 @@\n #include \"helper-a64.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 \n@@ -1531,6 +1532,24 @@ TRANS_FEAT(UUNPK_4bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_bh)\n TRANS_FEAT(UUNPK_4hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_hs)\n TRANS_FEAT(UUNPK_4sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_sd)\n \n+static bool do_f8cvt(DisasContext *s, arg_zz_n *a,\n+ gen_helper_gvec_2_ptr *fn, bool issrc2)\n+{\n+ if (fpmr_access_check(s) && sme_sm_enabled_check(s)) {\n+ int svl = streaming_vec_reg_size(s);\n+ tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->zd),\n+ vec_full_reg_offset(s, a->zn),\n+ tcg_env, svl, svl,\n+ issrc2 | (FPST_ZA << 2), fn);\n+ }\n+ return true;\n+}\n+\n+TRANS_FEAT(BF1CVT, aa64_sme2_f8cvt, do_f8cvt, a, gen_helper_sme2_bfcvt_hb, 0)\n+TRANS_FEAT(BF2CVT, aa64_sme2_f8cvt, do_f8cvt, a, gen_helper_sme2_bfcvt_hb, 1)\n+TRANS_FEAT(BF1CVTL, aa64_sme2_f8cvt, do_f8cvt, a, gen_helper_sme2_bfcvtl_hb, 0)\n+TRANS_FEAT(BF2CVTL, aa64_sme2_f8cvt, do_f8cvt, a, gen_helper_sme2_bfcvtl_hb, 1)\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 7a8e1abb59..df9586c1a5 100644\n--- a/target/arm/tcg/sme.decode\n+++ b/target/arm/tcg/sme.decode\n@@ -853,6 +853,11 @@ UUNPK_4bh 11000001 011 10101 111000 ....0 ...01 @zz_4x2_n1\n UUNPK_4hs 11000001 101 10101 111000 ....0 ...01 @zz_4x2_n1\n UUNPK_4sd 11000001 111 10101 111000 ....0 ...01 @zz_4x2_n1\n \n+BF1CVT 11000001 011 00110 111000 ..... ....0 @zz_2x1\n+BF2CVT 11000001 111 00110 111000 ..... ....0 @zz_2x1\n+BF1CVTL 11000001 011 00110 111000 ..... ....1 @zz_2x1\n+BF2CVTL 11000001 111 00110 111000 ..... ....1 @zz_2x1\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": [ "v2", "26/40" ] }