From: Tsukasa OI <research_trasio@irq.a4lg.com>
To: Tsukasa OI <research_trasio@irq.a4lg.com>,
Kito Cheng <kito.cheng@gmail.com>,
Palmer Dabbelt <palmer@dabbelt.com>,
Andrew Waterman <andrew@sifive.com>,
Jim Wilson <jim.wilson.gcc@gmail.com>
Cc: gcc-patches@gcc.gnu.org
Subject: [PATCH 1/1] RISC-V: Make "prefetch.i" built-in usable
Date: Thu, 10 Aug 2023 03:10:57 +0000 [thread overview]
Message-ID: <97c0d824fa5aeaee52a825da7f7a17ae8616c5ab.1691636916.git.research_trasio@irq.a4lg.com> (raw)
In-Reply-To: <cover.1691636916.git.research_trasio@irq.a4lg.com>
From: Tsukasa OI <research_trasio@irq.a4lg.com>
The "__builtin_riscv_zicbop_cbo_prefetchi" built-in function was terribly
broken so that practically unusable. It emitted "prefetch.i" but with no
meaningful arguments.
Though incompatible, this commit completely changes the function prototype
of this built-in and makes it usable. To minimize the functionality issues,
it renames the built-in to "__builtin_riscv_zicbop_prefetch_i".
gcc/ChangeLog:
* config/riscv/riscv-cmo.def: Fix function prototype.
* config/riscv/riscv.md (riscv_prefetchi_<mode>): Fix instruction
prototype. Remove possible prefectch type argument
* doc/extend.texi: Document __builtin_riscv_zicbop_prefetch_i.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/cmo-zicbop-1.c: Reflect new built-in prototype.
* gcc.target/riscv/cmo-zicbop-2.c: Likewise.
---
gcc/config/riscv/riscv-cmo.def | 4 ++--
gcc/config/riscv/riscv.md | 5 ++---
gcc/doc/extend.texi | 7 +++++++
gcc/testsuite/gcc.target/riscv/cmo-zicbop-1.c | 8 +++++---
gcc/testsuite/gcc.target/riscv/cmo-zicbop-2.c | 10 ++++++----
5 files changed, 22 insertions(+), 12 deletions(-)
diff --git a/gcc/config/riscv/riscv-cmo.def b/gcc/config/riscv/riscv-cmo.def
index b92044dc6ff9..2286c8a25544 100644
--- a/gcc/config/riscv/riscv-cmo.def
+++ b/gcc/config/riscv/riscv-cmo.def
@@ -13,8 +13,8 @@ RISCV_BUILTIN (zero_si, "zicboz_cbo_zero", RISCV_BUILTIN_DIRECT_NO_TARGET, RISCV
RISCV_BUILTIN (zero_di, "zicboz_cbo_zero", RISCV_BUILTIN_DIRECT_NO_TARGET, RISCV_VOID_FTYPE_VOID_PTR, zero64),
// zicbop
-RISCV_BUILTIN (prefetchi_si, "zicbop_cbo_prefetchi", RISCV_BUILTIN_DIRECT, RISCV_SI_FTYPE_SI, prefetchi32),
-RISCV_BUILTIN (prefetchi_di, "zicbop_cbo_prefetchi", RISCV_BUILTIN_DIRECT, RISCV_DI_FTYPE_DI, prefetchi64),
+RISCV_BUILTIN (prefetchi_si, "zicbop_prefetch_i", RISCV_BUILTIN_DIRECT_NO_TARGET, RISCV_VOID_FTYPE_VOID_PTR, prefetchi32),
+RISCV_BUILTIN (prefetchi_di, "zicbop_prefetch_i", RISCV_BUILTIN_DIRECT_NO_TARGET, RISCV_VOID_FTYPE_VOID_PTR, prefetchi64),
// zbkc or zbc
RISCV_BUILTIN (clmul_si, "clmul", RISCV_BUILTIN_DIRECT, RISCV_SI_FTYPE_SI_SI, clmul_zbkc32_or_zbc32),
diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md
index 688fd697255b..5658c7b7e113 100644
--- a/gcc/config/riscv/riscv.md
+++ b/gcc/config/riscv/riscv.md
@@ -3273,9 +3273,8 @@
})
(define_insn "riscv_prefetchi_<mode>"
- [(unspec_volatile:X [(match_operand:X 0 "address_operand" "r")
- (match_operand:X 1 "imm5_operand" "i")]
- UNSPECV_PREI)]
+ [(unspec_volatile:X [(match_operand:X 0 "register_operand" "r")]
+ UNSPECV_PREI)]
"TARGET_ZICBOP"
"prefetch.i\t%a0"
)
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index 89c5b4ea2b20..0eb98fc89e3f 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -21575,6 +21575,13 @@ Xgnuzihintpausestate extension, which redefines the @code{pause} instruction to
change architectural state.
@enddefbuiltin
+@defbuiltin{void __builtin_riscv_zicbop_prefetch_i (void *@var{addr})}
+Generates the @code{prefetch.i} machine instruction to instruct the hardware
+that a cache block containing @var{addr} is likely to be accessed by an
+instruction fetch in the near future.
+Available if the Zicbop extension is enabled.
+@enddefbuiltin
+
@node RISC-V Vector Intrinsics
@subsection RISC-V Vector Intrinsics
diff --git a/gcc/testsuite/gcc.target/riscv/cmo-zicbop-1.c b/gcc/testsuite/gcc.target/riscv/cmo-zicbop-1.c
index c5d78c1763d3..0d5b58c4fadf 100644
--- a/gcc/testsuite/gcc.target/riscv/cmo-zicbop-1.c
+++ b/gcc/testsuite/gcc.target/riscv/cmo-zicbop-1.c
@@ -13,11 +13,13 @@ void foo (char *p)
__builtin_prefetch (p, 1, 3);
}
-int foo1()
+void foo1 ()
{
- return __builtin_riscv_zicbop_cbo_prefetchi(1);
+ __builtin_riscv_zicbop_prefetch_i(0);
+ __builtin_riscv_zicbop_prefetch_i(&foo);
+ __builtin_riscv_zicbop_prefetch_i((void*)0x111);
}
-/* { dg-final { scan-assembler-times "prefetch.i" 1 } } */
+/* { dg-final { scan-assembler-times "prefetch.i" 3 } } */
/* { dg-final { scan-assembler-times "prefetch.r" 4 } } */
/* { dg-final { scan-assembler-times "prefetch.w" 4 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/cmo-zicbop-2.c b/gcc/testsuite/gcc.target/riscv/cmo-zicbop-2.c
index 6576365b39ca..09655c4b8593 100644
--- a/gcc/testsuite/gcc.target/riscv/cmo-zicbop-2.c
+++ b/gcc/testsuite/gcc.target/riscv/cmo-zicbop-2.c
@@ -13,11 +13,13 @@ void foo (char *p)
__builtin_prefetch (p, 1, 3);
}
-int foo1()
+void foo1 ()
{
- return __builtin_riscv_zicbop_cbo_prefetchi(1);
+ __builtin_riscv_zicbop_prefetch_i(0);
+ __builtin_riscv_zicbop_prefetch_i(&foo);
+ __builtin_riscv_zicbop_prefetch_i((void*)0x111);
}
-/* { dg-final { scan-assembler-times "prefetch.i" 1 } } */
+/* { dg-final { scan-assembler-times "prefetch.i" 3 } } */
/* { dg-final { scan-assembler-times "prefetch.r" 4 } } */
-/* { dg-final { scan-assembler-times "prefetch.w" 4 } } */
+/* { dg-final { scan-assembler-times "prefetch.w" 4 } } */
--
2.41.0
next prev parent reply other threads:[~2023-08-10 3:11 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-10 3:10 [PATCH 0/1] " Tsukasa OI
2023-08-10 3:10 ` Tsukasa OI [this message]
2023-08-28 21:20 ` [PATCH 1/1] " Jeff Law
2023-08-29 2:09 ` Tsukasa OI
2023-08-29 13:47 ` Jeff Law
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=97c0d824fa5aeaee52a825da7f7a17ae8616c5ab.1691636916.git.research_trasio@irq.a4lg.com \
--to=research_trasio@irq.a4lg.com \
--cc=andrew@sifive.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=jim.wilson.gcc@gmail.com \
--cc=kito.cheng@gmail.com \
--cc=palmer@dabbelt.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).