From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wr1-x42c.google.com (mail-wr1-x42c.google.com [IPv6:2a00:1450:4864:20::42c]) by sourceware.org (Postfix) with ESMTPS id 8713A3858D29 for ; Fri, 24 May 2024 16:19:12 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 8713A3858D29 Authentication-Results: sourceware.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=gmail.com ARC-Filter: OpenARC Filter v1.0.0 sourceware.org 8713A3858D29 Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=2a00:1450:4864:20::42c ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1716567555; cv=none; b=SyYm9XDMSHzcpIglxB3iAVcK1VDVg5m4h88AUZRbFm25uWIUsG7xwgSn7/5rt4UUO7wrYOL71ZdnajiQaFXCKO5rfz9o5uWNBVQX6/vHyI81rQmxgWtYlr671qBw8NYxgWjKd+oF+MrmPJaaQ/x0e3rPljIB5Htr398AE89U564= ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1716567555; c=relaxed/simple; bh=gzJGTk4sCStlVV41g7tqZ/Wnyva0aSq9V454UghljuU=; h=DKIM-Signature:Message-ID:Date:MIME-Version:Subject:To:From; b=brcwjJLvrkPssyyMO2CWrtJCHwDDGKP/nWy9+J5fbO9zZw435ybAF0bvDGiz2+N14Vdx5Uum9jN0zP1OqiQxyCVfog33FzGtGwYKcEDdkfRNLRLgqC7MZcx1PciIYqLF/VRpDE44aZflz6cofC/aoSxGyvoAr/jLaNi7OH7/jLU= ARC-Authentication-Results: i=1; server2.sourceware.org Received: by mail-wr1-x42c.google.com with SMTP id ffacd0b85a97d-3504f34a086so6225514f8f.1 for ; Fri, 24 May 2024 09:19:12 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1716567551; x=1717172351; darn=gcc.gnu.org; h=content-transfer-encoding:in-reply-to:from:content-language :references:to:subject:cc:user-agent:mime-version:date:message-id :from:to:cc:subject:date:message-id:reply-to; bh=Awv+yBLfiGaxif267a3Dbbt9IJsF/xO4UUmJvwrp0/I=; b=IHY8eCBjvrXMwdZLOF3mGgBl6Hf5QSngRsOzNq6l0h9yf2N9eEkLUrQh92xqhmam5w 5TjxMUfRJBNaG27Ts/0eSEalz5Mm0e5KLyTQ/+/zl+TR2sMruJVQTRS/AIO3MSrRGR2S TXnW/Ij5MDqqiwo1tFMdekANHkvdk+GcKtlwPUQCB9ncxSEepJvxu7LII6rfvjoQ4gmN VxpMDa7C/nBjPrcPUMBAmwOl44jedlizo+Ki+kYfXkHO0UfGvczntz4eooqzHyQouEw4 gppsscdeDe/hK0FMu3NpJ08ufeAVRZDpnQjgKyCMikhESNfndS1hcVk9UiqrRL30VHWD 1s9w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716567551; x=1717172351; h=content-transfer-encoding:in-reply-to:from:content-language :references:to:subject:cc:user-agent:mime-version:date:message-id :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=Awv+yBLfiGaxif267a3Dbbt9IJsF/xO4UUmJvwrp0/I=; b=QdeX9HHQNr283zCB/ChHcKfkCCa/Kiy5/8cQfSzhaASnBhOeGgRGlAA3PkseO8XLu8 e5b3zPXaG3OF9cOcYELPJUOK4Uav1Bs5tEgU1WMav1XmSJ+wU1SLPaM/ljfxVedbRWu4 ylzhiYRYxI+BezaqPWNPybiSFgDLO7qbGk9tTniWbXlVsrjNlDbVwXQZSJQZI4TbCdDX WfPbRtnyuvzmbTKju3ux3n3R7VR1obe37t2aHFgWSCzWIYd1g4gpVYJUeVgC23wIcwxi WuefWMrglZvxBxhpF93z9SIIp9zd5oIAkPYiJbWMKbdmWm8W6alGzwgErdI6EzXxRL/B HOvA== X-Forwarded-Encrypted: i=1; AJvYcCXn/Fxe2vf7Cvy9fS4PUzJsgda8xRNlAbBmVFOs8RUwqSYJA35fLvWUgFtzy/PXZJOwIPxBw5sRGfx7jnoYsj1HgtUIfOFMzA== X-Gm-Message-State: AOJu0YyedX+d0aZqfWuUiCJR3ZOjCXVqStusTnpK2EmOys23+9YM9qZ+ Jhi6d+CFRmNuLSc6kus9gDNmaXZz5GGjVS8+EdDlkb8b1E/Ewf6Lc0GDsw== X-Google-Smtp-Source: AGHT+IH9QKMAgQ76PpLz9ssNGI5oD32GLswy5bFyLbFWfzqX9wuD7j8+KsXAfqr4JwN77F3em52g3w== X-Received: by 2002:adf:e8d2:0:b0:354:f944:11de with SMTP id ffacd0b85a97d-35526c69af9mr2001366f8f.28.1716567550701; Fri, 24 May 2024 09:19:10 -0700 (PDT) Received: from [192.168.1.23] (ip-149-172-150-237.um42.pools.vodafone-ip.de. [149.172.150.237]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3557a090c2bsm1917943f8f.59.2024.05.24.09.19.10 (version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128); Fri, 24 May 2024 09:19:10 -0700 (PDT) Message-ID: Date: Fri, 24 May 2024 18:19:09 +0200 MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Cc: rdapp.gcc@gmail.com, gcc-patches@gcc.gnu.org, Kito Cheng , juzhe.zhong@rivai.ai, jeffreyalaw@gmail.com Subject: [PATCH v2] RISC-V: Introduce -mrvv-allow-misalign. To: Palmer Dabbelt References: Content-Language: en-US From: Robin Dapp In-Reply-To: Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Spam-Status: No, score=-9.1 required=5.0 tests=BAYES_00,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,FREEMAIL_FROM,GIT_PATCH_0,KAM_SHORT,RCVD_IN_DNSWL_NONE,SPF_HELO_NONE,SPF_PASS,TXREP autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org List-Id: > We should have something in doc/invoke too, this one is going to be > tricky for users. We'll also have to define how this interacts with > the existing -mstrict-align. Addressed the rest in the attached v2 which also fixes tests. I'm really not sure about -mstrict-align. I would have hoped that using -mstrict-align we'd never run into any movmisalign situation but that might be wishful thinking. Do we need to specify an interaction, though? For now the new options disables movmisalign so if we hit that despite -mstrict-align we'd still not vectorize it. Regtested on rv64gcv_zvfh_zvbb. Regards Robin This patch changes the default from always enabling movmisalign to not enabling it. It adds an option to override the default and adds generic-ooo to the uarchs that support misaligned vector access. It also adds a check_effective_target_riscv_v_misalign_ok to the testsuite which enables or disables the vector misalignment tests depending on whether the target under test can execute a misaligned vle32. gcc/ChangeLog: * config/riscv/riscv-opts.h (TARGET_VECTOR_MISALIGN_SUPPORTED): Move from here... * config/riscv/riscv.h (TARGET_VECTOR_MISALIGN_SUPPORTED): ...to here and make dependent on uarch and rvv_allow_misalign. * config/riscv/riscv.opt: Add -mrvv-allow-unaligned. gcc/testsuite/ChangeLog: * lib/target-supports.exp: Add check_effective_target_riscv_v_misalign_ok. * gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-7.c: Add -mrvv-allow-misalign. * gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-10.c: Ditto. * gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-11.c: Ditto. * gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-12.c: Ditto. * gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-8.c: Ditto. * gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-9.c: Ditto. * gcc.target/riscv/rvv/autovec/vls/misalign-1.c: --- gcc/config/riscv/riscv-opts.h | 3 -- gcc/config/riscv/riscv.cc | 18 ++++++++++ gcc/config/riscv/riscv.h | 6 ++++ gcc/config/riscv/riscv.opt | 5 +++ gcc/doc/invoke.texi | 5 +++ .../costmodel/riscv/rvv/dynamic-lmul2-7.c | 2 +- .../vect/costmodel/riscv/rvv/vla_vs_vls-10.c | 2 +- .../vect/costmodel/riscv/rvv/vla_vs_vls-11.c | 2 +- .../vect/costmodel/riscv/rvv/vla_vs_vls-12.c | 2 +- .../vect/costmodel/riscv/rvv/vla_vs_vls-8.c | 2 +- .../vect/costmodel/riscv/rvv/vla_vs_vls-9.c | 2 +- .../riscv/rvv/autovec/vls/misalign-1.c | 2 +- gcc/testsuite/lib/target-supports.exp | 34 +++++++++++++++++-- 13 files changed, 73 insertions(+), 12 deletions(-) diff --git a/gcc/config/riscv/riscv-opts.h b/gcc/config/riscv/riscv-opts.h index 1b2dd5757a8..f58a07abffc 100644 --- a/gcc/config/riscv/riscv-opts.h +++ b/gcc/config/riscv/riscv-opts.h @@ -147,9 +147,6 @@ enum rvv_vector_bits_enum { ? 0 \ : 32 << (__builtin_popcount (opts->x_riscv_zvl_flags) - 1)) -/* TODO: Enable RVV movmisalign by default for now. */ -#define TARGET_VECTOR_MISALIGN_SUPPORTED 1 - /* The maximmum LMUL according to user configuration. */ #define TARGET_MAX_LMUL \ (int) (rvv_max_lmul == RVV_DYNAMIC ? RVV_M8 : rvv_max_lmul) diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc index 85df5b7ab49..cfdeb56559f 100644 --- a/gcc/config/riscv/riscv.cc +++ b/gcc/config/riscv/riscv.cc @@ -287,6 +287,7 @@ struct riscv_tune_param unsigned short memory_cost; unsigned short fmv_cost; bool slow_unaligned_access; + bool rvv_unaligned_access; bool use_divmod_expansion; bool overlap_op_by_pieces; unsigned int fusible_ops; @@ -299,6 +300,10 @@ struct riscv_tune_param /* Whether unaligned accesses execute very slowly. */ bool riscv_slow_unaligned_access_p; +/* Whether misaligned vector accesses are supported (i.e. do not + throw an exception). */ +bool riscv_rvv_unaligned_access_p; + /* Whether user explicitly passed -mstrict-align. */ bool riscv_user_wants_strict_align; @@ -441,6 +446,7 @@ static const struct riscv_tune_param rocket_tune_info = { 5, /* memory_cost */ 8, /* fmv_cost */ true, /* slow_unaligned_access */ + false, /* rvv_unaligned_access */ false, /* use_divmod_expansion */ false, /* overlap_op_by_pieces */ RISCV_FUSE_NOTHING, /* fusible_ops */ @@ -459,6 +465,7 @@ static const struct riscv_tune_param sifive_7_tune_info = { 3, /* memory_cost */ 8, /* fmv_cost */ true, /* slow_unaligned_access */ + false, /* rvv_unaligned_access */ false, /* use_divmod_expansion */ false, /* overlap_op_by_pieces */ RISCV_FUSE_NOTHING, /* fusible_ops */ @@ -477,6 +484,7 @@ static const struct riscv_tune_param sifive_p400_tune_info = { 3, /* memory_cost */ 4, /* fmv_cost */ true, /* slow_unaligned_access */ + false, /* rvv_unaligned_access */ false, /* use_divmod_expansion */ false, /* overlap_op_by_pieces */ RISCV_FUSE_LUI_ADDI | RISCV_FUSE_AUIPC_ADDI, /* fusible_ops */ @@ -495,6 +503,7 @@ static const struct riscv_tune_param sifive_p600_tune_info = { 3, /* memory_cost */ 4, /* fmv_cost */ true, /* slow_unaligned_access */ + false, /* rvv_unaligned_access */ false, /* use_divmod_expansion */ false, /* overlap_op_by_pieces */ RISCV_FUSE_LUI_ADDI | RISCV_FUSE_AUIPC_ADDI, /* fusible_ops */ @@ -513,6 +522,7 @@ static const struct riscv_tune_param thead_c906_tune_info = { 5, /* memory_cost */ 8, /* fmv_cost */ false, /* slow_unaligned_access */ + false, /* rvv_unaligned_access */ false, /* use_divmod_expansion */ false, /* overlap_op_by_pieces */ RISCV_FUSE_NOTHING, /* fusible_ops */ @@ -531,6 +541,7 @@ static const struct riscv_tune_param xiangshan_nanhu_tune_info = { 3, /* memory_cost */ 3, /* fmv_cost */ true, /* slow_unaligned_access */ + false, /* rvv_unaligned_access */ false, /* use_divmod_expansion */ false, /* overlap_op_by_pieces */ RISCV_FUSE_ZEXTW | RISCV_FUSE_ZEXTH, /* fusible_ops */ @@ -549,6 +560,7 @@ static const struct riscv_tune_param generic_ooo_tune_info = { 4, /* memory_cost */ 4, /* fmv_cost */ false, /* slow_unaligned_access */ + true, /* rvv_unaligned_access */ false, /* use_divmod_expansion */ true, /* overlap_op_by_pieces */ RISCV_FUSE_NOTHING, /* fusible_ops */ @@ -567,6 +579,7 @@ static const struct riscv_tune_param optimize_size_tune_info = { 2, /* memory_cost */ 8, /* fmv_cost */ false, /* slow_unaligned_access */ + false, /* rvv_unaligned_access */ false, /* use_divmod_expansion */ false, /* overlap_op_by_pieces */ RISCV_FUSE_NOTHING, /* fusible_ops */ @@ -9536,6 +9549,11 @@ riscv_override_options_internal (struct gcc_options *opts) riscv_slow_unaligned_access_p = (cpu->tune_param->slow_unaligned_access || TARGET_STRICT_ALIGN); + /* Use -mtune's setting to determine whether unaligned vector accesses + are supported. */ + riscv_rvv_unaligned_access_p = (cpu->tune_param->rvv_unaligned_access + && !TARGET_STRICT_ALIGN); + /* Make a note if user explicitly passed -mstrict-align for later builtin macro generation. Can't use target_flags_explicitly since it is set even for -mno-strict-align. */ diff --git a/gcc/config/riscv/riscv.h b/gcc/config/riscv/riscv.h index d6b14c4d620..691d0a6fc57 100644 --- a/gcc/config/riscv/riscv.h +++ b/gcc/config/riscv/riscv.h @@ -934,6 +934,11 @@ extern enum riscv_cc get_riscv_cc (const rtx use); || (riscv_microarchitecture == sifive_p400) \ || (riscv_microarchitecture == sifive_p600)) +/* True if the target supports misaligned vector loads and stores. */ +#define TARGET_VECTOR_MISALIGN_SUPPORTED \ + (rvv_allow_misalign == 1 \ + || riscv_rvv_unaligned_access_p) + #define LOGICAL_OP_NON_SHORT_CIRCUIT 0 /* Control the assembler format that we output. */ @@ -1161,6 +1166,7 @@ while (0) #ifndef USED_FOR_TARGET extern const enum reg_class riscv_regno_to_class[]; extern bool riscv_slow_unaligned_access_p; +extern bool riscv_rvv_unaligned_access_p; extern bool riscv_user_wants_strict_align; extern unsigned riscv_stack_boundary; extern unsigned riscv_bytes_per_vector_chunk; diff --git a/gcc/config/riscv/riscv.opt b/gcc/config/riscv/riscv.opt index 87f58332016..0162429ee8f 100644 --- a/gcc/config/riscv/riscv.opt +++ b/gcc/config/riscv/riscv.opt @@ -628,3 +628,8 @@ Specify TLS dialect. mfence-tso Target Var(TARGET_FENCE_TSO) Init(1) Specifies whether the fence.tso instruction should be used. + +mrvv-allow-misalign +Target Var(rvv_allow_misalign) Init(0) +Allow the creation of element-misaligned vector loads and stores irrespective +of the current uarch. The default is off. diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi index c9d8f6b37b6..0586caa52a0 100644 --- a/gcc/doc/invoke.texi +++ b/gcc/doc/invoke.texi @@ -31163,6 +31163,11 @@ Generate little-endian code. This is the default when GCC is configured for a @samp{riscv64-*-*} or @samp{riscv32-*-*} but not a @samp{riscv64be-*-*} or @samp{riscv32be-*-*} target. +@opindex mrvv-allow-misalign +@item -mrvv-allow-misalign +Allow the creation of element-misaligned vector loads and stores irrespective +of the current uarch. The default is off. + @opindex mstack-protector-guard @opindex mstack-protector-guard-reg @opindex mstack-protector-guard-offset diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-7.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-7.c index 49ea3c2cf72..4b72c6a4d20 100644 --- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-7.c +++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-7.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -mrvv-max-lmul=dynamic" } */ +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -mrvv-max-lmul=dynamic -mrvv-allow-misalign" } */ int x264_pixel_8x8 (unsigned char *pix1, unsigned char *pix2, int i_stride_pix2) diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-10.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-10.c index 144479324d7..c31e2fbe12e 100644 --- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-10.c +++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-10.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -mrvv-max-lmul=m4 -fno-schedule-insns -fno-schedule-insns2" } */ +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -mrvv-max-lmul=m4 -fno-schedule-insns -fno-schedule-insns2 -mrvv-allow-misalign" } */ #include diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-11.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-11.c index 13ae8bd3bcf..a6381368b81 100644 --- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-11.c +++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-11.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -mrvv-max-lmul=m8 -fno-schedule-insns -fno-schedule-insns2" } */ +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -mrvv-max-lmul=m8 -fno-schedule-insns -fno-schedule-insns2 -mrvv-allow-misalign" } */ #include diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-12.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-12.c index 1f9fa48264e..f29a94fffe4 100644 --- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-12.c +++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-12.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -mrvv-max-lmul=dynamic -fno-schedule-insns -fno-schedule-insns2" } */ +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -mrvv-max-lmul=dynamic -fno-schedule-insns -fno-schedule-insns2 -mrvv-allow-misalign" } */ #include diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-8.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-8.c index ea6a7cbe2b1..f60e54d2cb8 100644 --- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-8.c +++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-8.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */ +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -mrvv-allow-misalign" } */ #include diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-9.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-9.c index cb4abeca989..b84256811c7 100644 --- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-9.c +++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/vla_vs_vls-9.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -mrvv-max-lmul=m2" } */ +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -mrvv-max-lmul=m2 -mrvv-allow-misalign" } */ #include diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/misalign-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/misalign-1.c index 1a076cbcd0f..9c11d897371 100644 --- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/misalign-1.c +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/misalign-1.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -fno-schedule-insns -fno-schedule-insns2 -mrvv-max-lmul=m4 -fno-tree-loop-distribute-patterns" } */ +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -fno-schedule-insns -fno-schedule-insns2 -mrvv-max-lmul=m4 -fno-tree-loop-distribute-patterns -mrvv-allow-misalign" } */ #include diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp index f0f6da52275..ebb908f5c8f 100644 --- a/gcc/testsuite/lib/target-supports.exp +++ b/gcc/testsuite/lib/target-supports.exp @@ -2034,7 +2034,7 @@ proc check_effective_target_riscv_zvfh_ok { } { # check if we can execute vector insns with the given hardware or # simulator set gcc_march [regsub {[[:alnum:]]*} [riscv_get_arch] &v] - if { [check_runtime ${gcc_march}_exec { + if { [check_runtime ${gcc_march}_zvfh_exec { int main() { asm ("vsetivli zero,8,e16,m1,ta,ma"); @@ -2047,6 +2047,29 @@ proc check_effective_target_riscv_zvfh_ok { } { return 0 } +# Return 1 if we can load a vector from a 1-byte aligned address. + +proc check_effective_target_riscv_v_misalign_ok { } { + + if { ![check_effective_target_riscv_v_ok] } { + return 0 + } + + set gcc_march [riscv_get_arch] + if { [check_runtime ${gcc_march}_misalign_exec { + int main() { + unsigned char a[16] + = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15}; + asm ("vsetivli zero,7,e8,m1,ta,ma"); + asm ("addi a7,%0,1" : : "r" (a) : "a7" ); + asm ("vle8.v v8,0(a7)" : : : "v8"); + return 0; } } "-march=${gcc_march}"] } { + return 1 + } + + return 0 +} + proc riscv_get_arch { } { set gcc_march "" # ??? do we neeed to add more extensions to the list below? @@ -8139,7 +8162,6 @@ proc check_effective_target_vect_hw_misalign { } { || ([istarget mips*-*-*] && [et-is-effective-target mips_msa]) || ([istarget s390*-*-*] && [check_effective_target_s390_vx]) - || ([istarget riscv*-*-*]) || ([istarget loongarch*-*-*]) || [istarget amdgcn*-*-*] } { return 1 @@ -8148,6 +8170,11 @@ proc check_effective_target_vect_hw_misalign { } { && ![check_effective_target_arm_vect_no_misalign] } { return 1 } + if { [istarget riscv*-*-*] + && [check_effective_target_riscv_v_misalign_ok] } { + return 1 + } + return 0 }] } @@ -11565,6 +11592,9 @@ proc check_vect_support_and_set_flags { } { } elseif [istarget riscv*-*-*] { if [check_effective_target_riscv_v] { set dg-do-what-default run + if [check_effective_target_riscv_v_misalign_ok] { + lappend DEFAULT_VECTCFLAGS "-mrvv-allow-misalign" + } } else { foreach item [add_options_for_riscv_v ""] { lappend DEFAULT_VECTCFLAGS $item -- 2.45.0