From: Andrea Corallo <andrea.corallo@arm.com>
To: <gcc-patches@gcc.gnu.org>
Cc: <kyrylo.tkachov@arm.com>, <Richard.Earnshaw@arm.com>,
"Stam Markianos-Wright" <stam.markianos-wright@arm.com>
Subject: [PATCH 04/10] arm: Stop vadcq, vsbcq intrinsics from overwriting the FPSCR NZ flags
Date: Fri, 28 Apr 2023 13:29:56 +0200 [thread overview]
Message-ID: <20230428113002.482343-4-andrea.corallo@arm.com> (raw)
In-Reply-To: <20230428113002.482343-1-andrea.corallo@arm.com>
From: Stam Markianos-Wright <stam.markianos-wright@arm.com>
Hi all,
We noticed that calls to the vadcq and vsbcq intrinsics, both of
which use __builtin_arm_set_fpscr_nzcvqc to set the Carry flag in
the FPSCR, would produce the following code:
```
< r2 is the *carry input >
vmrs r3, FPSCR_nzcvqc
bic r3, r3, #536870912
orr r3, r3, r2, lsl #29
vmsr FPSCR_nzcvqc, r3
```
when the MVE ACLE instead gives a different instruction sequence of:
```
< Rt is the *carry input >
VMRS Rs,FPSCR_nzcvqc
BFI Rs,Rt,#29,#1
VMSR FPSCR_nzcvqc,Rs
```
the bic + orr pair is slower and it's also wrong, because, if the
*carry input is greater than 1, then we risk overwriting the top two
bits of the FPSCR register (the N and Z flags).
This turned out to be a problem in the header file and the solution was
to simply add a `& 1x0u` to the `*carry` input: then the compiler knows
that we only care about the lowest bit and can optimise to a BFI.
Ok for trunk?
Thanks,
Stam Markianos-Wright
gcc/ChangeLog:
* config/arm/arm_mve.h (__arm_vadcq_s32): Fix arithmetic.
(__arm_vadcq_u32): Likewise.
(__arm_vadcq_m_s32): Likewise.
(__arm_vadcq_m_u32): Likewise.
(__arm_vsbcq_s32): Likewise.
(__arm_vsbcq_u32): Likewise.
(__arm_vsbcq_m_s32): Likewise.
(__arm_vsbcq_m_u32): Likewise.
---
gcc/config/arm/arm_mve.h | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
index 1262d668121..8778216304b 100644
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -16055,7 +16055,7 @@ __extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vadcq_s32 (int32x4_t __a, int32x4_t __b, unsigned * __carry)
{
- __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | (*__carry << 29));
+ __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | ((*__carry & 0x1u) << 29));
int32x4_t __res = __builtin_mve_vadcq_sv4si (__a, __b);
*__carry = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
return __res;
@@ -16065,7 +16065,7 @@ __extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vadcq_u32 (uint32x4_t __a, uint32x4_t __b, unsigned * __carry)
{
- __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | (*__carry << 29));
+ __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | ((*__carry & 0x1u) << 29));
uint32x4_t __res = __builtin_mve_vadcq_uv4si (__a, __b);
*__carry = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
return __res;
@@ -16075,7 +16075,7 @@ __extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vadcq_m_s32 (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, unsigned * __carry, mve_pred16_t __p)
{
- __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | (*__carry << 29));
+ __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | ((*__carry & 0x1u) << 29));
int32x4_t __res = __builtin_mve_vadcq_m_sv4si (__inactive, __a, __b, __p);
*__carry = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
return __res;
@@ -16085,7 +16085,7 @@ __extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vadcq_m_u32 (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, unsigned * __carry, mve_pred16_t __p)
{
- __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | (*__carry << 29));
+ __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | ((*__carry & 0x1u) << 29));
uint32x4_t __res = __builtin_mve_vadcq_m_uv4si (__inactive, __a, __b, __p);
*__carry = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
return __res;
@@ -16131,7 +16131,7 @@ __extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vsbcq_s32 (int32x4_t __a, int32x4_t __b, unsigned * __carry)
{
- __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | (*__carry << 29));
+ __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | ((*__carry & 0x1u) << 29));
int32x4_t __res = __builtin_mve_vsbcq_sv4si (__a, __b);
*__carry = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
return __res;
@@ -16141,7 +16141,7 @@ __extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vsbcq_u32 (uint32x4_t __a, uint32x4_t __b, unsigned * __carry)
{
- __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | (*__carry << 29));
+ __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | ((*__carry & 0x1u) << 29));
uint32x4_t __res = __builtin_mve_vsbcq_uv4si (__a, __b);
*__carry = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
return __res;
@@ -16151,7 +16151,7 @@ __extension__ extern __inline int32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vsbcq_m_s32 (int32x4_t __inactive, int32x4_t __a, int32x4_t __b, unsigned * __carry, mve_pred16_t __p)
{
- __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | (*__carry << 29));
+ __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | ((*__carry & 0x1u) << 29));
int32x4_t __res = __builtin_mve_vsbcq_m_sv4si (__inactive, __a, __b, __p);
*__carry = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
return __res;
@@ -16161,7 +16161,7 @@ __extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vsbcq_m_u32 (uint32x4_t __inactive, uint32x4_t __a, uint32x4_t __b, unsigned * __carry, mve_pred16_t __p)
{
- __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | (*__carry << 29));
+ __builtin_arm_set_fpscr_nzcvqc((__builtin_arm_get_fpscr_nzcvqc () & ~0x20000000u) | ((*__carry & 0x1u) << 29));
uint32x4_t __res = __builtin_mve_vsbcq_m_uv4si (__inactive, __a, __b, __p);
*__carry = (__builtin_arm_get_fpscr_nzcvqc () >> 29) & 0x1u;
return __res;
--
2.25.1
next prev parent reply other threads:[~2023-04-28 11:32 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-04-28 11:29 [PATCH 01/10] arm: Mve testsuite improvements Andrea Corallo
2023-04-28 11:29 ` [PATCH 02/10] arm: Fix vstrwq* backend + testsuite Andrea Corallo
2023-04-28 16:27 ` Kyrylo Tkachov
2023-05-02 8:21 ` Christophe Lyon
2023-05-02 8:45 ` Andrea Corallo
2023-05-02 10:18 ` Andrea Corallo
2023-04-28 11:29 ` [PATCH 03/10] arm: Mve backend + testsuite fixes 2 Andrea Corallo
2023-04-28 16:40 ` Kyrylo Tkachov
2023-05-02 11:53 ` Andrea Corallo
2023-04-28 11:29 ` Andrea Corallo [this message]
2023-04-28 16:45 ` [PATCH 04/10] arm: Stop vadcq, vsbcq intrinsics from overwriting the FPSCR NZ flags Kyrylo Tkachov
2023-05-03 12:19 ` Stamatis Markianos-Wright
2023-05-03 12:55 ` Kyrylo Tkachov
2023-04-28 11:29 ` [PATCH 05/10] arm: Add vorrq_n overloading into vorrq _Generic Andrea Corallo
2023-04-28 16:47 ` Kyrylo Tkachov
2023-04-28 11:29 ` [PATCH 06/10] arm: Fix overloading of MVE scalar constant parameters on vbicq, vmvnq_m Andrea Corallo
2023-04-28 16:47 ` Kyrylo Tkachov
2023-04-28 11:29 ` [PATCH 07/10] arm: Fix MVE header pointer overloads this time (and a bit more tidying) Andrea Corallo
2023-04-28 16:51 ` Kyrylo Tkachov
2023-04-28 11:30 ` [PATCH 08/10] arm testsuite: Remove reduntant tests Andrea Corallo
2023-04-28 16:52 ` Kyrylo Tkachov
2023-04-28 11:30 ` [PATCH 09/10] arm testsuite: XFAIL or relax registers in some tests Andrea Corallo
2023-04-28 16:54 ` Kyrylo Tkachov
2023-05-02 12:17 ` Stamatis Markianos-Wright
2023-05-02 8:28 ` Christophe Lyon
2023-05-02 9:33 ` Stamatis Markianos-Wright
2023-04-28 11:30 ` [PATCH 10/10] arm testsuite: Shifts and get_FPSCR ACLE optimisation fixes Andrea Corallo
2023-04-28 16:58 ` Kyrylo Tkachov
2023-05-03 12:34 ` Stamatis Markianos-Wright
2023-05-03 12:56 ` Kyrylo Tkachov
2023-04-28 16:27 ` [PATCH 01/10] arm: Mve testsuite improvements Kyrylo Tkachov
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=20230428113002.482343-4-andrea.corallo@arm.com \
--to=andrea.corallo@arm.com \
--cc=Richard.Earnshaw@arm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=kyrylo.tkachov@arm.com \
--cc=stam.markianos-wright@arm.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).