From: Richard Sandiford <richard.sandiford@arm.com>
To: Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org>
Cc: Richard Biener <rguenther@suse.de>,
gcc Patches <gcc-patches@gcc.gnu.org>
Subject: Re: [aarch64] Use dup and zip1 for interleaving elements in initializing vector
Date: Fri, 21 Apr 2023 10:17:09 +0100 [thread overview]
Message-ID: <mptv8hpa92i.fsf@arm.com> (raw)
In-Reply-To: <CAAgBjMkiCcrK_GWEZTdcWWxS3d398LmyQDoPpfpkKvwKCvnncQ@mail.gmail.com> (Prathamesh Kulkarni's message of "Fri, 21 Apr 2023 12:57:32 +0530")
Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org> writes:
> Hi,
> I tested the interleave+zip1 for vector init patch and it segfaulted
> during bootstrap while trying to build
> libgfortran/generated/matmul_i2.c.
> Rebuilding with --enable-checking=rtl showed out of bounds access in
> aarch64_unzip_vector_init in following hunk:
>
> + rtvec vec = rtvec_alloc (n / 2);
> + for (int i = 0; i < n; i++)
> + RTVEC_ELT (vec, i) = (even_p) ? XVECEXP (vals, 0, 2 * i)
> + : XVECEXP (vals, 0, 2 * i + 1);
>
> which is incorrect since it allocates n/2 but iterates and stores upto n.
> The attached patch fixes the issue, which passed bootstrap, however
> resulted in following fallout during testsuite run:
>
> 1] sve/acle/general/dupq_[1-4].c tests fail.
> For the following test:
> int32x4_t f(int32_t x)
> {
> return (int32x4_t) { x, 1, 2, 3 };
> }
>
> Code-gen without patch:
> f:
> adrp x1, .LC0
> ldr q0, [x1, #:lo12:.LC0]
> ins v0.s[0], w0
> ret
>
> Code-gen with patch:
> f:
> movi v0.2s, 0x2
> adrp x1, .LC0
> ldr d1, [x1, #:lo12:.LC0]
> ins v0.s[0], w0
> zip1 v0.4s, v0.4s, v1.4s
> ret
>
> It shows, fallback_seq_cost = 20, seq_total_cost = 16
> where seq_total_cost determines the cost for interleave+zip1 sequence
> and fallback_seq_cost is the cost for fallback sequence.
> Altho it shows lesser cost, I am not sure if the interleave+zip1
> sequence is better in this case ?
Debugging the patch, it looks like this is because the fallback sequence
contains a redundant pseudo-to-pseudo move, which is costed as 1
instruction (4 units). The RTL equivalent of the:
movi v0.2s, 0x2
ins v0.s[0], w0
has a similar redundant move, but the cost of that move is subsumed by
the cost of the other arm (the load from LC0), which is costed as 3
instructions (12 units). So we have 12 + 4 for the parallel version
(correct) but 12 + 4 + 4 for the serial version (one instruction too
many).
The reason we have redundant moves is that the expansion code uses
copy_to_mode_reg to force a value into a register. This creates a
new pseudo even if the original value was already a register.
Using force_reg removes the moves and makes the test pass.
So I think the first step is to use force_reg instead of
copy_to_mode_reg in aarch64_simd_dup_constant and
aarch64_expand_vector_init (as a preparatory patch).
> 2] sve/acle/general/dupq_[5-6].c tests fail:
> int32x4_t f(int32_t x0, int32_t x1, int32_t x2, int32_t x3)
> {
> return (int32x4_t) { x0, x1, x2, x3 };
> }
>
> code-gen without patch:
> f:
> fmov s0, w0
> ins v0.s[1], w1
> ins v0.s[2], w2
> ins v0.s[3], w3
> ret
>
> code-gen with patch:
> f:
> fmov s0, w0
> fmov s1, w1
> ins v0.s[1], w2
> ins v1.s[1], w3
> zip1 v0.4s, v0.4s, v1.4s
> ret
>
> It shows fallback_seq_cost = 28, seq_total_cost = 16
The zip verson still wins after the fix above, but by a lesser amount.
It seems like a borderline case.
>
> 3] aarch64/ldp_stp_16.c's cons2_8_float test fails.
> Test case:
> void cons2_8_float(float *x, float val0, float val1)
> {
> #pragma GCC unroll(8)
> for (int i = 0; i < 8 * 2; i += 2) {
> x[i + 0] = val0;
> x[i + 1] = val1;
> }
> }
>
> which is lowered to:
> void cons2_8_float (float * x, float val0, float val1)
> {
> vector(4) float _86;
>
> <bb 2> [local count: 119292720]:
> _86 = {val0_11(D), val1_13(D), val0_11(D), val1_13(D)};
> MEM <vector(4) float> [(float *)x_10(D)] = _86;
> MEM <vector(4) float> [(float *)x_10(D) + 16B] = _86;
> MEM <vector(4) float> [(float *)x_10(D) + 32B] = _86;
> MEM <vector(4) float> [(float *)x_10(D) + 48B] = _86;
> return;
> }
>
> code-gen without patch:
> cons2_8_float:
> dup v0.4s, v0.s[0]
> ins v0.s[1], v1.s[0]
> ins v0.s[3], v1.s[0]
> stp q0, q0, [x0]
> stp q0, q0, [x0, 32]
> ret
>
> code-gen with patch:
> cons2_8_float:
> dup v1.2s, v1.s[0]
> dup v0.2s, v0.s[0]
> zip1 v0.4s, v0.4s, v1.4s
> stp q0, q0, [x0]
> stp q0, q0, [x0, 32]
> ret
>
> It shows fallback_seq_cost = 28, seq_total_cost = 16
>
> I think the test fails because it doesn't match:
> ** dup v([0-9]+)\.4s, .*
>
> Shall it be OK to amend the test assuming code-gen with patch is better ?
Yeah, the new code seems like an improvement.
> 4] aarch64/pr109072_1.c s32x4_3 test fails:
> For the following test:
> int32x4_t s32x4_3 (int32_t x, int32_t y)
> {
> int32_t arr[] = { x, y, y, y };
> return vld1q_s32 (arr);
> }
>
> code-gen without patch:
> s32x4_3:
> dup v0.4s, w1
> ins v0.s[0], w0
> ret
>
> code-gen with patch:
> s32x4_3:
> fmov s1, w1
> fmov s0, w0
> ins v0.s[1], v1.s[0]
> dup v1.2s, v1.s[0]
> zip1 v0.4s, v0.4s, v1.4s
> ret
>
> It shows fallback_seq_cost = 20, seq_total_cost = 16
> I am not sure how interleave+zip1 cost is lesser than fallback seq
> cost for this case.
> I assume that the fallback sequence is better here ?
The fix for 1] works for this case too.
Thanks,
Richard
next prev parent reply other threads:[~2023-04-21 9:17 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-11-29 14:39 Prathamesh Kulkarni
2022-11-29 15:13 ` Andrew Pinski
2022-11-29 17:06 ` Prathamesh Kulkarni
2022-12-05 10:52 ` Richard Sandiford
2022-12-05 11:20 ` Richard Sandiford
2022-12-06 1:31 ` Prathamesh Kulkarni
2022-12-26 4:22 ` Prathamesh Kulkarni
2023-01-12 15:51 ` Richard Sandiford
2023-02-01 9:36 ` Prathamesh Kulkarni
2023-02-01 16:26 ` Richard Sandiford
2023-02-02 14:51 ` Prathamesh Kulkarni
2023-02-02 15:20 ` Richard Sandiford
2023-02-03 1:40 ` Prathamesh Kulkarni
2023-02-03 3:02 ` Prathamesh Kulkarni
2023-02-03 15:17 ` Richard Sandiford
2023-02-04 6:49 ` Prathamesh Kulkarni
2023-02-06 12:13 ` Richard Sandiford
2023-02-11 9:12 ` Prathamesh Kulkarni
2023-03-10 18:08 ` Richard Sandiford
2023-03-13 7:33 ` Richard Biener
2023-04-03 16:33 ` Prathamesh Kulkarni
2023-04-04 18:05 ` Richard Sandiford
2023-04-06 10:26 ` Prathamesh Kulkarni
2023-04-06 10:34 ` Richard Sandiford
2023-04-06 11:21 ` Prathamesh Kulkarni
2023-04-12 8:59 ` Richard Sandiford
2023-04-21 7:27 ` Prathamesh Kulkarni
2023-04-21 9:17 ` Richard Sandiford [this message]
2023-04-21 15:15 ` Prathamesh Kulkarni
2023-04-23 1:53 ` Prathamesh Kulkarni
2023-04-24 9:29 ` Richard Sandiford
2023-05-04 11:47 ` Prathamesh Kulkarni
2023-05-11 19:07 ` Richard Sandiford
2023-05-13 9:10 ` Prathamesh Kulkarni
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=mptv8hpa92i.fsf@arm.com \
--to=richard.sandiford@arm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=prathamesh.kulkarni@linaro.org \
--cc=rguenther@suse.de \
/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).