From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-lf1-x12e.google.com (mail-lf1-x12e.google.com [IPv6:2a00:1450:4864:20::12e]) by sourceware.org (Postfix) with ESMTPS id 6583E3858424 for ; Mon, 27 May 2024 12:45:27 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 6583E3858424 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 6583E3858424 Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=2a00:1450:4864:20::12e ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1716813931; cv=none; b=CTyxSouMCL4sdC3OtwSSu4YgJ0lSPfnHshUwDfQX9Kq8nt+135XTdJEx3/sdQNpnWHblMTxO7z6Hli4u2Idy7ujNtbuZ2KYWLsxl+LpInVCJ/ZlBtC1QuSJ0YOv3JP6WI2iiEQM8D7iTXZ1yRfoM58kOLZNtqQSlkbGBvqzv2AQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1716813931; c=relaxed/simple; bh=cNumesOrm+QPeE9ri5og9l2E2NATHNsm8VLJ9LIB8Ng=; h=DKIM-Signature:Message-ID:Date:MIME-Version:Subject:To:From; b=TnDZYOQFR03oUoI6PR3c5CwvLX8eIVzbkqEhUFOCf+ulGuyBCCzOtL25v7S97pjl/Ha6BnUctiLKh/1eOqU4TadYG0n7Y+9ll0YSGcSM9pqDBuccsoY9iiwlzfguZ53QeFaPD3k0RN7esFzwGNEUYhM993w/hsZPmHTqbqhxs6Q= ARC-Authentication-Results: i=1; server2.sourceware.org Received: by mail-lf1-x12e.google.com with SMTP id 2adb3069b0e04-5296232e00bso3377974e87.3 for ; Mon, 27 May 2024 05:45:27 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1716813926; x=1717418726; 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=mq7msrev9pGZjtr4+3ZUSBJhoe2S+9WazB0IrUyEtf0=; b=Ew5pK868XevL0a2hf5Xor0vZ0okCgb40cBMfj6PVz9oS197gDZjA5lm3O3rq07OJCB zKp6tebz4MG5XHVqRWiw4IktmJfjj8NTxPVzaQMwWnUvaLa3d/QfcAdedXcjnhN7HiHA CjTJL2LpPoCDfSMfwGuS6ufg/1hjSlwnBEPNcXiVs1murdEA3d7JBx3rDY7rC5YoFSOD jqCLCm5GnMEUdqaLmWbwF+u0vGlVDBrOVT29VE5a6K0BpR6/d86vJ+hpmAuMi6vnCUDc FyomTaXd9Xfml1Vc49C39ce+OTypGPsKVNjrwqtssuzTLN3/3/Nv0w6znqj1r6sQuGSm xUhg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716813926; x=1717418726; 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=mq7msrev9pGZjtr4+3ZUSBJhoe2S+9WazB0IrUyEtf0=; b=pPGDUaI2YQXvs58+HKOSCX0xKYJy/hse0sK35KBU0CXxrUAOjI6o1WUBAszXxK5RN9 00bjfF+9e+lfJqcOxNQgprdixyqCH4B9ogv7q9pbFYLqdC34HHK5JKtjp67kdsDlFQiw kTikk2wSz/gg0ZGMRaVYApbazNlaeVYZswR3xH9gcrK8SdpD5kntyTxQYfO0SAdZtyVr 4U9TmWRo3u/fvSkiUAgKNuFsyxUlrsV4kKxG1CnROqFRZS4SH086j7hLjVC4v2PPfr6p kZtPUz/0y1+RVXBbPy/imwo0fGRFflj7NmqDeHKAruqu6w3ZL3eMtMNvPPcOskgT+QIo oqMA== X-Forwarded-Encrypted: i=1; AJvYcCUfImpJvOlCUd1kuQYRhVcVK8JVJKHthBh5D5eo+IIvhBOHL6WAWa+su4PwQgt4h9vhCCGEHJhbCj8fj3ocMAwN3EHequMX9A== X-Gm-Message-State: AOJu0YyXSFb6VYMKJggjSNp+5Heg5T1S3Pw8eXykqicaL5IaiAbwmzmO mb3dOqUd/mAneuoBoYSfG487Kx0Ir7VIRqA1OftzaeX46s8Qq2Am X-Google-Smtp-Source: AGHT+IFt+pQRTJxHQGJo/tQ6DIfW926VhGII8Mjyn4WJBYKKZrRSf+GJW3g+2wKNQYiWgD308yXNTg== X-Received: by 2002:a05:6512:b8a:b0:523:8a79:ed62 with SMTP id 2adb3069b0e04-529642034cemr7197459e87.3.1716813925350; Mon, 27 May 2024 05:45:25 -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 4fb4d7f45d1cf-579d0b02625sm1764188a12.9.2024.05.27.05.45.24 (version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128); Mon, 27 May 2024 05:45:24 -0700 (PDT) Message-ID: Date: Mon, 27 May 2024 14:45:23 +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 Subject: [PATCH v3] RISC-V: Introduce -mvector-strict-align. To: Palmer Dabbelt , jeffreyalaw@gmail.com 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,T_SCC_BODY_TEXT_LINE 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: Attached is v3 with the discussed changes. It now has -mscalar-strict-align which is an alias to -mstrict-align as well as -mvector-strict-align. Testsuite shows no new regressions on rv64gcv_zvfh_zvbb. Regards Robin 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 map to riscv_vector_unaligned_access_p. * config/riscv/riscv.opt: Add -mvector-strict-align. * config/riscv/riscv.cc (struct riscv_tune_param): Add vector_unaligned_access. (riscv_override_options_internal): Set riscv_vector_unaligned_access_p. * doc/invoke.texi: Document -mvector-strict-align. 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 -mno-vector-strict-align. * 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: Ditto. --- gcc/config/riscv/riscv-opts.h | 3 -- gcc/config/riscv/riscv.cc | 19 +++++++++++ gcc/config/riscv/riscv.h | 5 +++ gcc/config/riscv/riscv.opt | 8 +++++ gcc/doc/invoke.texi | 22 ++++++++++++ .../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, 93 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..7482f51b8dc 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 vector_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_vector_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, /* vector_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, /* vector_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, /* vector_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, /* vector_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, /* vector_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, /* vector_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, /* vector_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, /* vector_unaligned_access */ false, /* use_divmod_expansion */ false, /* overlap_op_by_pieces */ RISCV_FUSE_NOTHING, /* fusible_ops */ @@ -9536,6 +9549,12 @@ riscv_override_options_internal (struct gcc_options *opts) riscv_slow_unaligned_access_p = (cpu->tune_param->slow_unaligned_access || TARGET_STRICT_ALIGN); + /* By default, when -mno-vector-strict-align is not specified, do not allow + unaligned vector memory accesses except if -mtune's setting explicitly + allows it. */ + riscv_vector_unaligned_access_p = rvv_vector_strict_align == 0 || + cpu->tune_param->vector_unaligned_access; + /* 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..57910eecd3e 100644 --- a/gcc/config/riscv/riscv.h +++ b/gcc/config/riscv/riscv.h @@ -934,6 +934,10 @@ 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 \ + riscv_vector_unaligned_access_p + #define LOGICAL_OP_NON_SHORT_CIRCUIT 0 /* Control the assembler format that we output. */ @@ -1161,6 +1165,7 @@ 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_vector_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..edc569e9780 100644 --- a/gcc/config/riscv/riscv.opt +++ b/gcc/config/riscv/riscv.opt @@ -128,6 +128,14 @@ mstrict-align Target Mask(STRICT_ALIGN) Save Do not generate unaligned memory accesses. +mscalar-strict-align +Target Mask(STRICT_ALIGN) Save +Do not generate unaligned scalar memory accesses. + +mvector-strict-align +Target Var(rvv_vector_strict_align) Init(1) +Do not create element-misaligned vector memory accesses. + Enum Name(code_model) Type(enum riscv_code_model) Known code models (for use with the -mcmodel= option): diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi index c9d8f6b37b6..0091a0f4057 100644 --- a/gcc/doc/invoke.texi +++ b/gcc/doc/invoke.texi @@ -31099,6 +31099,28 @@ Do not or do generate unaligned memory accesses. The default is set depending on whether the processor we are optimizing for supports fast unaligned access or not. +@opindex mscalar-strict-align +@opindex mno-scalar-strict-align +@item -mscalar-strict-align +@itemx -mno-scalar-strict-align +Do not or do generate unaligned memory accesses. The default is set depending +on whether the processor we are optimizing for supports fast unaligned access +or not. This is an alias for @option{-mstrict-align}. + +@opindex mvector-strict-align +@opindex mno-vector-strict-align +@item -mvector-strict-align +@itemx -mno-vector-strict-align +Do not or do generate unaligned vector memory accesses. The default is set +to off unless the processor we are optimizing for explicitly supports +element-misaligned vector memory access. + +@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 mcmodel=medlow @item -mcmodel=medlow Generate code for the medium-low code model. The program and its statically 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..754f84ae0a0 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 -mno-vector-strict-align" } */ 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..d0a0f4208ee 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 -mno-vector-strict-align" } */ #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..5a779a9ee75 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 -mno-vector-strict-align" } */ #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..e7e4e841bb8 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 -mno-vector-strict-align" } */ #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..0e5b4522de5 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 -mno-vector-strict-align" } */ #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..5276e0b2f6c 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 -mno-vector-strict-align" } */ #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..5184a295e16 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 -mno-vector-strict-align" } */ #include diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp index f0f6da52275..e887efbb8f3 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 "-mno-vector-strict-align" + } } else { foreach item [add_options_for_riscv_v ""] { lappend DEFAULT_VECTCFLAGS $item -- 2.45.0