From: Jiufu Guo <guojiufu@linux.ibm.com>
To: gcc-patches@gcc.gnu.org
Cc: segher@kernel.crashing.org, dje.gcc@gmail.com, linkw@gcc.gnu.org,
bergner@linux.ibm.com, guojiufu@linux.ibm.com
Subject: [PATCH V5 2/2] rs6000: use mtvsrws to move sf from si p9
Date: Thu, 5 Oct 2023 12:13:46 +0800 [thread overview]
Message-ID: <20231005041346.3625108-2-guojiufu@linux.ibm.com> (raw)
In-Reply-To: <20231005041346.3625108-1-guojiufu@linux.ibm.com>
Hi,
As mentioned in PR108338, on p9, we could use mtvsrws to implement
the bitcast from SI to SF (or lowpart DI to SF).
For example:
*(long long*)buff = di;
float f = *(float*)(buff);
"sldi 9,3,32 ; mtvsrd 1,9 ; xscvspdpn 1,1" is generated.
A better one would be "mtvsrws 1,3 ; xscvspdpn 1,1".
Compare with previous patch:
https://gcc.gnu.org/pipermail/gcc-patches/2023-August/628791.html
According to review comments, this version refines commit message
and words in comments, also updates the test case
Pass bootstrap and regtest on ppc64{,le}.
Is this ok for trunk?
BR,
Jeff (Jiufu Guo)
PR target/108338
gcc/ChangeLog:
* config/rs6000/rs6000.md (movsf_from_si): Update to generate mtvsrws
for P9.
gcc/testsuite/ChangeLog:
* gcc.target/powerpc/pr108338.c: Updated to check mtvsrws for p9.
---
gcc/config/rs6000/rs6000.md | 25 ++++++++++++++++-----
gcc/testsuite/gcc.target/powerpc/pr108338.c | 21 ++++++++++++++---
2 files changed, 37 insertions(+), 9 deletions(-)
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 56bd8bc1147..d6dfb25cea0 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -8283,13 +8283,26 @@ (define_insn_and_split "movsf_from_si"
{
rtx op0 = operands[0];
rtx op1 = operands[1];
- rtx op2 = operands[2];
- rtx op1_di = gen_rtx_REG (DImode, REGNO (op1));
- /* Move SF value to upper 32-bits for xscvspdpn. */
- emit_insn (gen_ashldi3 (op2, op1_di, GEN_INT (32)));
- emit_insn (gen_p8_mtvsrd_sf (op0, op2));
- emit_insn (gen_vsx_xscvspdpn_directmove (op0, op0));
+ /* Move lowpart 32-bits from register for SFmode. */
+ if (TARGET_P9_VECTOR)
+ {
+ /* Using mtvsrws;xscvspdpn. */
+ rtx op0_v = gen_rtx_REG (V4SImode, REGNO (op0));
+ emit_insn (gen_vsx_splat_v4si (op0_v, op1));
+ emit_insn (gen_vsx_xscvspdpn_directmove (op0, op0));
+ }
+ else
+ {
+ rtx op2 = operands[2];
+ rtx op1_di = gen_rtx_REG (DImode, REGNO (op1));
+
+ /* Using sldi;mtvsrd;xscvspdpn. */
+ emit_insn (gen_ashldi3 (op2, op1_di, GEN_INT (32)));
+ emit_insn (gen_p8_mtvsrd_sf (op0, op2));
+ emit_insn (gen_vsx_xscvspdpn_directmove (op0, op0));
+ }
+
DONE;
}
[(set_attr "length"
diff --git a/gcc/testsuite/gcc.target/powerpc/pr108338.c b/gcc/testsuite/gcc.target/powerpc/pr108338.c
index bd83c0b3ad8..5f2f62866ee 100644
--- a/gcc/testsuite/gcc.target/powerpc/pr108338.c
+++ b/gcc/testsuite/gcc.target/powerpc/pr108338.c
@@ -3,9 +3,12 @@
/* { dg-options "-O2 -save-temps" } */
/* Under lp64, parameter 'v' is in DI regs, then bitcast sub DI to SF. */
-/* { dg-final { scan-assembler-times {\mxscvspdpn\M} 1 { target { lp64 && has_arch_pwr8 } } } } */
-/* { dg-final { scan-assembler-times {\mmtvsrd\M} 1 { target { lp64 && has_arch_pwr8 } } } } */
+/* { dg-final { scan-assembler-times {\mxscvspdpn\M} 2 { target { lp64 && has_arch_pwr8 } } } } */
+/* { dg-final { scan-assembler-times {\mmtvsrd\M} 2 { target { lp64 && { has_arch_pwr8 && { ! has_arch_pwr9 } } } } } } */
+/* { dg-final { scan-assembler-times {\mmtvsrd\M} 1 { target { lp64 && has_arch_pwr9 } } } } */
+/* { dg-final { scan-assembler-times {\mmtvsrws\M} 1 { target { lp64 && has_arch_pwr9 } } } } */
/* { dg-final { scan-assembler-times {\mrldicr\M} 1 { target { lp64 && has_arch_pwr8 } } } } */
+/* { dg-final { scan-assembler-times {\msldi\M} 1 { target { lp64 && { has_arch_pwr8 && { ! has_arch_pwr9 } } } } } } */
struct di_sf_sf
{
@@ -22,16 +25,28 @@ sf_from_high32bit_di (struct di_sf_sf v)
#endif
}
+float __attribute__ ((noipa))
+sf_from_low32bit_di (struct di_sf_sf v)
+{
+#ifdef __LITTLE_ENDIAN__
+ return v.f1;
+#else
+ return v.f2;
+#endif
+}
+
int main()
{
struct di_sf_sf v;
v.f1 = v.f2 = 0.0f;
#ifdef __LITTLE_ENDIAN__
+ v.f1 = 1.0f;
v.f2 = 2.0f;
#else
v.f1 = 2.0f;
+ v.f2 = 1.0f;
#endif
- if (sf_from_high32bit_di (v) != 2.0f)
+ if (sf_from_high32bit_di (v) != 2.0f || sf_from_low32bit_di (v) != 1.0f)
__builtin_abort ();
return 0;
}
--
2.25.1
next prev parent reply other threads:[~2023-10-05 4:13 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-05 4:13 [PATCH V5 1/2] rs6000: optimize moving to sf from highpart di Jiufu Guo
2023-10-05 4:13 ` Jiufu Guo [this message]
2023-10-05 16:54 ` [PATCH V5 2/2] rs6000: use mtvsrws to move sf from si p9 David Edelsohn
2023-10-07 8:00 ` Jiufu Guo
2023-10-05 16:52 ` [PATCH V5 1/2] rs6000: optimize moving to sf from highpart di David Edelsohn
2023-10-07 8:01 ` Jiufu Guo
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=20231005041346.3625108-2-guojiufu@linux.ibm.com \
--to=guojiufu@linux.ibm.com \
--cc=bergner@linux.ibm.com \
--cc=dje.gcc@gmail.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=linkw@gcc.gnu.org \
--cc=segher@kernel.crashing.org \
/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).