https://gcc.gnu.org/bugzilla/show_bug.cgi?id=121412
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Known to work|15.1.1 |
CC
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=121412
--- Comment #5 from ktkachov at gcc dot gnu.org ---
Comment on attachment 62057
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=62057
Second sleeffoo.i reproducer
>#pragma GCC aarch64 "arm_sve.h"
>typedef svfl
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=121412
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Summary|AArch64 SVE VLS vs VLA ICE |[16 Regression] AArch64
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=121412
--- Comment #1 from ktkachov at gcc dot gnu.org ---
Created attachment 62057
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=62057&action=edit
Second sleeffoo.i reproducer
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
Created attachment 62056
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=62056&action=edi
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
CC: acoplan at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
We have some C++ code that implements various reversed memcpy-like
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=121034
--- Comment #4 from ktkachov at gcc dot gnu.org ---
(In reply to Richard Biener from comment #3)
> Should be fixed now.
Looks like it. Thanks for the quick fix!
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
CC: rguenth at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
Reduced testcase:
int b, e;
char c, d
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=121034
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Known to work||15.1.0
Known to fail
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120999
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Ever confirmed|0 |1
Last reconfirmed
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
When using the NBSL SVE2 instruction to generate a NOR operation GCC
-optimization
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
#include
uint64_t foo(svbool_t p) {
return svcntp_b64
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120632
--- Comment #2 from ktkachov at gcc dot gnu.org ---
[tag] [reply] [−]descriptionktkac...@gcc.gnu.org 2025-03-18 08:54:08 UTC
Tamar and I have been discussing this offline but now that we have a reproducer
with all public sources here's
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120687
--- Comment #2 from ktkachov at gcc dot gnu.org ---
I similarly see this generates ~200 lines of assembly for aarch64 compared to
~20 with Clang so I'd mark it as target-independent.
I think I remember a bug in the past about the need for
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119187
--- Comment #9 from ktkachov at gcc dot gnu.org ---
(In reply to Tamar Christina from comment #8)
> (In reply to ktkachov from comment #7)
> > Could this be extended to scale Neon intrinsics code to SVE by
> > re-vectorising an
, missed-optimization
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
Building and running GROMACS in the same way as in
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120447
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Status|NEW |ASSIGNED
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120447
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Last reconfirmed|2025-05-27 00:00:00 |2025-5-30
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120276
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Status|ASSIGNED|RESOLVED
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120276
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||rsandifo at gcc dot
Severity: normal
Priority: P3
Component: middle-end
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
int a;
char b[1];
int c[18];
void d(char *);
void e() {
int f;
char *g;
a = 0
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120276
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||jschmitz at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120276
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Known to fail||16.0
Target Milestone
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120157
--- Comment #4 from ktkachov at gcc dot gnu.org ---
(In reply to ktkachov from comment #2)
> (In reply to Tamar Christina from comment #1)
> > (In reply to ktkachov from comment #0)
> > > Not sure if this is a target-specific
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120157
--- Comment #2 from ktkachov at gcc dot gnu.org ---
(In reply to Tamar Christina from comment #1)
> (In reply to ktkachov from comment #0)
> > Not sure if this is a target-specific issue or not. For input:
> > int f11(float *x, f
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
CC: tnfchris at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
Not sure if this is a target-specific
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120067
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||ktkachov at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120027
--- Comment #1 from ktkachov at gcc dot gnu.org ---
Note Clang is working on improving some of the cases on their side
https://github.com/llvm/llvm-project/pull/137956
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
Some cases:
#include
#define UXT(SZ, TY) \
svuint##SZ##_t uxt##TY##_z_##SZ(svuint##SZ
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119974
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Resolution|--- |INVALID
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
A testcase:
#include
int foo(double *x, double val, int n)
{
double *endp = x + n;
uint64_t
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119706
--- Comment #11 from ktkachov at gcc dot gnu.org ---
(In reply to GCC Commits from comment #10)
> The releases/gcc-14 branch has been updated by Richard Biener
> :
>
> https://gcc.gnu.org/g:2bb4a431eace7e77562e686ecc9c9504045da003
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119706
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Known to fail||15.0
Target Milestone
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119706
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Status|UNCONFIRMED |NEW
Ever confirmed|0
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119187
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||ktkachov at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119351
--- Comment #11 from ktkachov at gcc dot gnu.org ---
(In reply to Jakub Jelinek from comment #10)
> Has this worked in GCC 14? If so, has it been bisected what commit caused
> this (or made a bug no longer latent)?
Yes,
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119572
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||ktkachov at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97286
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||rsandifo at gcc dot gnu.org
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119442
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Summary|[14/15 Regression] |[14 Regression] Regression
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119442
--- Comment #2 from ktkachov at gcc dot gnu.org ---
Patch at https://gcc.gnu.org/pipermail/gcc-patches/2025-March/679115.html
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119442
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Status|UNCONFIRMED |ASSIGNED
Severity: normal
Priority: P3
Component: middle-end
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
The testcase is nonsense in itself but is heavily reduced from a real
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119351
--- Comment #5 from ktkachov at gcc dot gnu.org ---
(In reply to Tamar Christina from comment #4)
> While looking at the codegen it looks like GROMACS has a lot of loops that
> get vectorized now and it's showing some inefficien
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119384
--- Comment #1 from ktkachov at gcc dot gnu.org ---
> We have a workload for aarch64 using the SIMDe translation error
Oops, this should say "SIMDe translation layer"
Priority: P3
Component: middle-end
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
We have a workload for aarch64 using the SIMDe translation error that results
in slower code than
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119351
--- Comment #1 from ktkachov at gcc dot gnu.org ---
> -DCMAKE_C_COMPILER=$COMPILERBIN -DCMAKE_CXX_COMPILER=$COMPILERXXBIN
$COMPILERBIN and $COMPILERXXBIN should point to the gcc and g++ executables
: wrong-code
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
CC: acoplan at gcc dot gnu.org, tnfchris at gcc dot gnu.org
Target Milestone
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
Example source:
#include
#define PACK_8_TO_64( a, b, c, d, e, f, g, h )\
(((uint64_t)a&
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119046
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Status|ASSIGNED|RESOLVED
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119046
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Assignee|unassigned at gcc dot gnu.org |ktkachov at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119046
--- Comment #2 from ktkachov at gcc dot gnu.org ---
(In reply to Tamar Christina from comment #1)
> The late-combine pass was supposed to handle these. probably worth a look
> into why it's not folding them in.
Yeah you're rig
Keywords: missed-optimization
Severity: normal
Priority: P3
Component: rtl-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Created attachment 60603
--> https://gcc.gnu.org/bugzi
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
Taken from the LLVM report: https://github.com/llvm/llvm-project/issues/12
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118976
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||ktkachov at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118151
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||ktkachov at gcc dot
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
CC: tnfchris at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
For example, the testcase
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118952
--- Comment #2 from ktkachov at gcc dot gnu.org ---
(In reply to Richard Sandiford from comment #1)
> I think this is essentially the same problem as PR34678.
Thanks, yeah I don't see PR34678 getting generally resolved any time soon.
IRMED
Keywords: wrong-code
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
The __builtin_aarch64_set_fpc
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117978
--- Comment #4 from ktkachov at gcc dot gnu.org ---
(In reply to Richard Sandiford from comment #3)
> I think this would be better done in expand rather than gimple. The gimple
> representation would be a vector load in a 128-bit type, fo
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118852
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||ktkachov at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118852
--- Comment #5 from ktkachov at gcc dot gnu.org ---
(In reply to Tamar Christina from comment #4)
> (In reply to ktkachov from comment #3)
> > FWIW I see this also on aarch64
>
> I filed the AArch64 bug weeks ago
> https://gc
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118490
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Resolution|--- |FIXED
Status
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116445
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||ktkachov at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118490
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Assignee|unassigned at gcc dot gnu.org |soumyaa at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118490
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||ktkachov at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118377
--- Comment #8 from ktkachov at gcc dot gnu.org ---
(In reply to Tejas Belagod from comment #7)
> Sorry for the delay in replying. Though variable-length(VLA) SVE vector
> types behave as GNU vectors for C/C++ operator semantics, th
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118133
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||ktkachov at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117978
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||rsandifo at gcc dot
, missed-optimization
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
When it is known that the predicate on a zero-predicated
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117704
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||ktkachov at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117557
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Status|UNCONFIRMED |NEW
Last reconfirmed
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117554
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Target Milestone|--- |15.0
: aarch64-sve, ice-on-valid-code
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
Building imagick ICEs on aarch64
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
Building the benchmark from SPEC2017 runs into a segfault ICE on aarch64.
Reduced
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117449
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Resolution|--- |FIXED
Status
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117449
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Last reconfirmed||2024-11-05
Target
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117048
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Status|ASSIGNED|RESOLVED
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
I'm not sure how bad this is in real code but spotted the testcase:
#in
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106329
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Assignee|prathamesh3492 at gcc dot gnu.org |unassigned at gcc
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117093
--- Comment #4 from ktkachov at gcc dot gnu.org ---
(In reply to ktkachov from comment #3)
> If we remove the casts:
> uint32x4_t ror32_neon_tgt_gcc_bad(uint32x4_t r) {
> uint32x4_t a = r;
> uint32_t t;
> t = a[0]; a
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117093
--- Comment #3 from ktkachov at gcc dot gnu.org ---
I think it's the VIEW_CONVERT_EXPR that are hurting us (more complete dump
before expand):
_1 = VIEW_CONVERT_EXPR(r_3(D));
t_4 = BIT_FIELD_REF ;
a_5 = VEC_PERM_EXPR <_1, _1, { 1,
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117048
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Status|RESOLVED|ASSIGNED
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
CC: tnfchris at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
This testcase is reduced from a hashing code
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117048
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Known to work||15.0
Resolution
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117050
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Last reconfirmed||2024-10-10
Ever
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117048
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Last reconfirmed||2024-10-09
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117048
--- Comment #1 from ktkachov at gcc dot gnu.org ---
Yeah, there is code in simplify-rtx.cc:3467 to simplify this pattern to a
rotate but it doesn't handle vector operands
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
A testcase derived from a hashing algorithm:
#include
#include
#include
static inline uint64x2_t
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117045
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||ktkachov at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117013
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||ktkachov at gcc dot
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116999
--- Comment #1 from ktkachov at gcc dot gnu.org ---
This is inspired by the LLVM PR
https://github.com/llvm/llvm-project/pull/83
-optimization
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
Example testcase:
#include
#include
svbool_t
foo_s32_le (int32_t
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116934
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Status|UNCONFIRMED |RESOLVED
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116956
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Target Milestone|--- |15.0
Summary
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116934
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
CC||saurabh.jha at arm dot com
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116934
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Target Milestone|--- |15.0
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Target: aarch64
blender from SPEC2017 ICEs with current trunk. The reduced testcase is:
int a;
float *b;
void c() {
for
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111733
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Status|NEW |ASSIGNED
--- Comment #3
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116902
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Target Milestone|--- |15.0
Summary
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
The following C++ testcase ICEs on aarch64 with -O3:
unsigned a;
#include
void i(long b, char c[][4], long d[][4
1 - 100 of 2262 matches
Mail list logo
