[Bug libstdc++/115040] Missed optimization opportunity in std::find of std::vector elements
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115040 --- Comment #9 from AK --- Thanks for merging the patch!
[Bug libstdc++/115040] Missed optimization opportunity in std::find of std::vector elements
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115040 --- Comment #6 from AK --- The duplicate part of https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88545, the first loop, will get fixed with Jonathan's patch.
[Bug libstdc++/88545] std::find compile to memchr in trivial random access cases (patch)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88545
--- Comment #10 from AK ---
With this patch find of int8_t gets converted to memchr.
Using testcase from https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115040 as
example. With the patch posted in
https://gcc.gnu.org/pipermail/gcc-patches/2024-June/653731.html
```
bool find_epi8(const std::vector& v) {
return std::find(v.begin(), v.end(), 42) != v.end();
}
```
$ gcc -O3 -ftree-vectorize -march=pantherlake test.cpp -S -o test.s
```
.globl _Z9find_epi8RKSt6vectorIaSaIaEE
.type _Z9find_epi8RKSt6vectorIaSaIaEE, @function
_Z9find_epi8RKSt6vectorIaSaIaEE:
.LFB1535:
.cfi_startproc
pushq %rbx
.cfi_def_cfa_offset 16
.cfi_offset 3, -16
movq 8(%rdi), %rbx
movq (%rdi), %rdi
testq %rdi, %rdi
je .L2
movq %rbx, %rdx
subq %rdi, %rdx
xorl %eax, %eax
testq %rdx, %rdx
jle .L1
movl $42, %esi
call memchr
movq %rax, %rdx
cmpq %rax, %rbx
setne %al
testq %rdx, %rdx
setne %dl
andl %edx, %eax
.L1:
popq %rbx
.cfi_remember_state
.cfi_def_cfa_offset 8
ret
.p2align 4,,10
.p2align 3
.L2:
.cfi_restore_state
cmpq $3, %rbx
jg .L4
cmpq $2, %rbx
je .L10
cmpq $3, %rbx
je .L6
xorl %eax, %eax
cmpq $1, %rbx
jne .L1
.L7:
cmpb $42, (%rdi)
sete %al
cmpq %rdi, %rbx
setne %dl
andl %edx, %eax
popq %rbx
.cfi_def_cfa_offset 8
ret
.L10:
.cfi_restore_state
xorl %edx, %edx
movl $1, %edi
.L5:
cmpb $42, (%rdx)
movl $1, %eax
jne .L7
popq %rbx
.cfi_remember_state
.cfi_def_cfa_offset 8
ret
.L6:
.cfi_restore_state
cmpb $42, 0
movl $1, %eax
je .L1
movl $2, %edi
movl $1, %edx
jmp .L5
.cfi_endproc
.section .text.unlikely
.cfi_startproc
.type _Z9find_epi8RKSt6vectorIaSaIaEE.cold, @function
_Z9find_epi8RKSt6vectorIaSaIaEE.cold:
.LFSB1535:
.L4:
.cfi_def_cfa_offset 16
.cfi_offset 3, -16
movzbl 0, %eax
ud2
.cfi_endproc
.LFE1535:
.text
.size _Z9find_epi8RKSt6vectorIaSaIaEE, .-_Z9find_epi8RKSt6vectorIaSaIaEE
.section .text.unlikely
.size _Z9find_epi8RKSt6vectorIaSaIaEE.cold,
.-_Z9find_epi8RKSt6vectorIaSaIaEE.cold
```
[Bug libstdc++/88545] std::find compile to memchr in trivial random access cases (patch)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88545 --- Comment #7 from AK --- Is there a plan to push a patch for this?
[Bug libstdc++/88545] std::find compile to memchr in trivial random access cases (patch)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88545 --- Comment #6 from AK --- > We can use memchr to find a char in a range of signed char, or even to find > an int in a range of signed char, as long as we're careful about values. +1, this approach should fix the bug i reported https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115040
[Bug libstdc++/88545] std::find compile to memchr in trivial random access cases (patch)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88545 AK changed: What|Removed |Added CC||hiraditya at msn dot com --- Comment #5 from AK --- > I think we're going to remove the manual loop unrolling in __find_if for GCC > 15, which should allow the compiler to optimize it better, potentially > auto-vectorizing. That might make memchr less advantageous, but I think it's > worth doing anyway. And even for code-size flags (-Os) memchr still gives best of both worlds as auto-vectorizing increases the size.
[Bug tree-optimization/115041] New: Missed optimization opportunity in std::find of std::vector elements
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115041
Bug ID: 115041
Summary: Missed optimization opportunity in std::find of
std::vector elements
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
https://gcc.godbolt.org/z/s3hv15935
```
#include
#include
#include
bool find_epi8(const std::vector& v) {
return std::find(v.begin(), v.end(), 42) != v.end();
}
bool find_epi32(const std::vector& v) {
return std::find(v.begin(), v.end(), 42) != v.end();
}
```
$ gcc -O3 -ftree-vectorize -march=pantherlake
```
find_epi8(std::vector > const&):
mov rcx, QWORD PTR [rdi+8]
mov rdx, QWORD PTR [rdi]
mov rsi, rcx
sub rsi, rdx
mov rax, rsi
sar rax, 2
testrax, rax
jle .L2
lea rax, [rdx+rax*4]
jmp .L8
.L3:
cmp BYTE PTR [rdx+1], 42
je .L23
cmp BYTE PTR [rdx+2], 42
je .L24
cmp BYTE PTR [rdx+3], 42
je .L25
add rdx, 4
cmp rdx, rax
je .L26
.L8:
cmp BYTE PTR [rdx], 42
jne .L3
.L21:
cmp rcx, rdx
setne al
ret
.L26:
mov rsi, rcx
sub rsi, rdx
.L2:
cmp rsi, 2
je .L9
cmp rsi, 3
je .L10
cmp rsi, 1
je .L11
xor eax, eax
ret
.L10:
cmp BYTE PTR [rdx], 42
je .L21
add rdx, 1
.L9:
cmp BYTE PTR [rdx], 42
je .L21
add rdx, 1
.L11:
cmp BYTE PTR [rdx], 42
seteal
cmp rcx, rdx
setne dl
and eax, edx
ret
.L23:
add rdx, 1
cmp rcx, rdx
setne al
ret
.L24:
add rdx, 2
cmp rcx, rdx
setne al
ret
.L25:
add rdx, 3
cmp rcx, rdx
setne al
ret
find_epi32(std::vector > const&):
mov rcx, QWORD PTR [rdi+8]
mov rdx, QWORD PTR [rdi]
mov rax, rcx
sub rax, rdx
mov rsi, rax
sar rax, 4
sar rsi, 2
testrax, rax
jle .L28
sal rax, 4
add rax, rdx
jmp .L34
.L29:
cmp DWORD PTR [rdx+4], 42
je .L48
cmp DWORD PTR [rdx+8], 42
je .L49
cmp DWORD PTR [rdx+12], 42
je .L50
add rdx, 16
cmp rdx, rax
je .L51
.L34:
cmp DWORD PTR [rdx], 42
jne .L29
.L47:
cmp rcx, rdx
setne al
ret
.L51:
mov rsi, rcx
sub rsi, rdx
sar rsi, 2
.L28:
cmp rsi, 2
je .L35
cmp rsi, 3
je .L36
cmp rsi, 1
je .L37
xor eax, eax
ret
.L36:
cmp DWORD PTR [rdx], 42
je .L47
add rdx, 4
.L35:
cmp DWORD PTR [rdx], 42
je .L47
add rdx, 4
.L37:
cmp DWORD PTR [rdx], 42
seteal
cmp rcx, rdx
setne dl
and eax, edx
ret
.L48:
add rdx, 4
cmp rcx, rdx
setne al
ret
.L49:
add rdx, 8
cmp rcx, rdx
setne al
ret
.L50:
add rdx, 12
cmp rcx, rdx
setne al
ret
```
clang lowers both the calls to (w)memchr
[Bug tree-optimization/107263] Memcpy not elided when initializing struct
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107263 AK changed: What|Removed |Added CC||hiraditya at msn dot com --- Comment #3 from AK --- Seems like a duplicate of #59863 ?
[Bug middle-end/59863] const array in function is placed on stack
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=59863 AK changed: What|Removed |Added CC||hiraditya at msn dot com --- Comment #9 from AK --- *** Bug 114342 has been marked as a duplicate of this bug. ***
[Bug middle-end/114342] suboptimal codegen of vector::vector(range)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114342 AK changed: What|Removed |Added Resolution|--- |DUPLICATE Version|unknown |14.0 Status|NEW |RESOLVED --- Comment #3 from AK --- I see. marking as duplicate. Thanks for clarifying! *** This bug has been marked as a duplicate of bug 59863 ***
[Bug c++/114342] New: suboptimal codegen of vector::vector(range)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114342
Bug ID: 114342
Summary: suboptimal codegen of vector::vector(range)
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
#include
#include
std::vector td() {
int arr[]{-5, 10, 15, -5, 10, 15, -5, 10, 15, -5, 10, 15, -5, 10, 15, -5, 10,
15, -5, 10, 15,-5, 10, 15 -5, 10, 15, -5, 10, 15, -5, 10, 15, -5, 10, 15, -5,
10, 15, -5, 10, 15, -5, 10,-5, 10, 15, -5, 10, 15, -5, 10, 15, -5, 10, 15, -5,
10, 15, -5, 10,-5, 10, 15, -5, 10, 15, -5, 10, 15, -5, 10, 15, -5, 10, 15, -5,
10,-5, 10, 15, -5, 10, 15, -5, 10, 15, -5, 10, 15, -5, 10, 15, -5, 10,-5, 10,
15, -5, 10, 15, -5, 10, 15, -5, 10, 15, -5, 10, 15, -5, 10,};
auto b = std::ranges::begin(arr);
auto e = std::ranges::end(arr);
std::vector dd(b, e);
return dd;
}
What is the reason for calling `rep movsq` twice?
$ gcc -O3 -std=c++23
```
td():
pushrbp
mov esi, OFFSET FLAT:.LC0
mov ecx, 55
pxorxmm0, xmm0
pushrbx
mov rbx, rdi
sub rsp, 456
mov QWORD PTR [rbx+16], 0
mov rbp, rsp
movups XMMWORD PTR [rbx], xmm0
mov rdi, rbp
rep movsq
mov eax, DWORD PTR [rsi]
mov DWORD PTR [rdi], eax
mov edi, 444
calloperator new(unsigned long)
lea rdx, [rax+444]
mov QWORD PTR [rbx], rax
lea rdi, [rax+8]
mov rsi, rbp
mov QWORD PTR [rbx+16], rdx
mov rcx, QWORD PTR [rsp]
and rdi, -8
mov QWORD PTR [rax], rcx
mov rcx, QWORD PTR [rsp+436]
mov QWORD PTR [rax+436], rcx
sub rax, rdi
sub rsi, rax
add eax, 444
shr eax, 3
mov ecx, eax
mov rax, rbx
rep movsq
mov QWORD PTR [rbx+8], rdx
add rsp, 456
pop rbx
pop rbp
ret
mov rbp, rax
jmp .L2
td() [clone .cold]:
.L2:
mov rdi, QWORD PTR [rbx]
mov rsi, QWORD PTR [rbx+16]
sub rsi, rdi
testrdi, rdi
je .L3
calloperator delete(void*, unsigned long)
.L3:
mov rdi, rbp
call_Unwind_Resume
```
https://godbolt.org/z/5333db8Px
[Bug c++/111806] g++ generates better code for variant at -Os compared to -O3
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111806 --- Comment #1 from AK --- It seems like we could 'sink' the 4 common instructions (of .L2) at -O3 L2: add rsp, 48 xor eax, eax pop rbx ret Or is it due to some kind of tail duplication?
[Bug c++/111806] New: g++ generates better code for variant at -Os compared to -O3
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111806
Bug ID: 111806
Summary: g++ generates better code for variant at
-Os compared to -O3
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
#include
#include
#include
int foo() {
std::variant v {"abc"};
std::cout << std::get<0>(v);
return 0;
}
g++ -O3 -std=c++20 -g0 -fno-exceptions
foo():
.LFB2484:
pushrbx
mov eax, 25185
mov edx, 3
mov edi, OFFSET FLAT:_ZSt4cout
sub rsp, 48
lea rbx, [rsp+16]
mov WORD PTR [rsp+16], ax
mov rsi, rbx
mov QWORD PTR [rsp], rbx
mov BYTE PTR [rsp+18], 99
mov QWORD PTR [rsp+8], 3
mov BYTE PTR [rsp+19], 0
mov BYTE PTR [rsp+32], 0
callstd::basic_ostream >&
std::__ostream_insert >(std::basic_ostream >&, char const*, long)
cmp BYTE PTR [rsp+32], 0
je .L5
.L2:
add rsp, 48
xor eax, eax
pop rbx
ret
.L5:
mov rdi, QWORD PTR [rsp]
cmp rdi, rbx
je .L2
mov rax, QWORD PTR [rsp+16]
lea rsi, [rax+1]
calloperator delete(void*, unsigned long)
add rsp, 48
xor eax, eax
pop rbx
ret
.LFE2484:
g++ -Os -std=c++20 -g0 -fno-exceptions
foo():
.LFB2463:
pushrbx
mov edx, 3
mov edi, OFFSET FLAT:_ZSt4cout
sub rsp, 48
lea rbx, [rsp+24]
mov WORD PTR [rsp+24], 25185
mov rsi, rbx
mov QWORD PTR [rsp+8], rbx
mov BYTE PTR [rsp+26], 99
mov QWORD PTR [rsp+16], 3
mov BYTE PTR [rsp+27], 0
mov BYTE PTR [rsp+40], 0
callstd::basic_ostream >&
std::__ostream_insert >(std::basic_ostream >&, char const*, long)
cmp BYTE PTR [rsp+40], 0
jne .L2
mov rdi, QWORD PTR [rsp+8]
cmp rdi, rbx
je .L2
mov rax, QWORD PTR [rsp+24]
lea rsi, [rax+1]
calloperator delete(void*, unsigned long)
.L2:
add rsp, 48
xor eax, eax
pop rbx
ret
.LFE2463:
https://godbolt.org/z/3xKh35Mrv
[Bug c++/111805] New: suboptimal codegen of variant
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111805
Bug ID: 111805
Summary: suboptimal codegen of variant
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
#include
#include
std::string foo() {
std::variant v {"abc"};
return std::get<0>(v);
}
g++-13.2 -O2 -std=c++20
foo[abi:cxx11]():
lea rdx, [rdi+16]
mov BYTE PTR [rdi+18], 99
mov rax, rdi
mov QWORD PTR [rdi], rdx
mov edx, 25185
mov WORD PTR [rdi+16], dx
mov QWORD PTR [rdi+8], 3
mov BYTE PTR [rdi+19], 0
ret
clang++ -O2 -std=c++20
foo():# @foo()
mov rax, rdi
mov byte ptr [rdi], 6
mov dword ptr [rdi + 1], 6513249
ret
https://godbolt.org/z/nTv5rYanM
[Bug target/111420] relocation truncated to fit: R_RISCV_JAL against `.L12287'
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111420 --- Comment #6 from AK --- To confirm what Andrew mentioned, the release build (-O3) built successfully.
[Bug target/111420] relocation truncated to fit: R_RISCV_JAL against `.L12287'
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111420 AK changed: What|Removed |Added Status|UNCONFIRMED |RESOLVED Resolution|--- |MOVED --- Comment #5 from AK --- Created: https://sourceware.org/bugzilla/show_bug.cgi?id=30855
[Bug target/111420] relocation truncated to fit: R_RISCV_JAL against `.L12287'
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111420 --- Comment #4 from AK --- good catch. By mistake i built at -O0, i wanted to build at -O3.
[Bug c/111420] relocation truncated to fit: R_RISCV_JAL against `.L12287'
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111420 --- Comment #1 from AK --- I got this error while building clang (ninja clang) on a riscv machine. root@lpi4a:~# gcc -v Using built-in specs. COLLECT_GCC=gcc COLLECT_LTO_WRAPPER=/usr/libexec/gcc/riscv64-linux-gnu/13/lto-wrapper Target: riscv64-linux-gnu Configured with: ../src/configure -v --with-pkgversion='Debian 13.1.0-6' --with-bugurl=file:///usr/share/doc/gcc-13/README.Bugs --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --prefix=/usr --with-gcc-major-version-only --program-suffix=-13 --program-prefix=riscv64-linux-gnu- --enable-shared --enable-linker-build-id --libexecdir=/usr/libexec --without-included-gettext --enable-threads=posix --libdir=/usr/lib --enable-nls --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --with-default-libstdcxx-abi=new --enable-gnu-unique-object --disable-libitm --disable-libquadmath --disable-libquadmath-support --enable-plugin --enable-default-pie --with-system-zlib --enable-libphobos-checking=release --with-target-system-zlib=auto --enable-objc-gc=auto --enable-multiarch --disable-werror --disable-multilib --with-arch=rv64gc --with-abi=lp64d --enable-checking=release --build=riscv64-linux-gnu --host=riscv64-linux-gnu --target=riscv64-linux-gnu --with-build-config=bootstrap-lto-lean --enable-link-serialization=32 Thread model: posix Supported LTO compression algorithms: zlib zstd gcc version 13.1.0 (Debian 13.1.0-6) -- root@lpi4a:~# uname -a Linux lpi4a 5.10.113-g7b352f5ac2ba #1 SMP PREEMPT Wed Apr 12 12:06:11 UTC 2023 riscv64 GNU/Linux
[Bug c/111420] New: relocation truncated to fit: R_RISCV_JAL against `.L12287'
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111420 Bug ID: 111420 Summary: relocation truncated to fit: R_RISCV_JAL against `.L12287' Product: gcc Version: unknown Status: UNCONFIRMED Severity: normal Priority: P3 Component: c Assignee: unassigned at gcc dot gnu.org Reporter: hiraditya at msn dot com Target Milestone: --- CGBuiltin.cpp:(.text._ZN5clang7CodeGen15CodeGenFunction20EmitRISCVBuiltinExprEjPKNS_8CallExprENS0_15ReturnValueSlotE+0x10d0): relocation truncated to fit: R_RISCV_JAL against `.L12287' command: : && /usr/bin/c++ -fPIC -fPIC -fno-semantic-interposition -fvisibility-inlines-hidden -Werror=date-time -fno-lifetime-dse -Wall -Wextra -Wno-unused-parameter -Wwrite-strings -Wcast-qual -Wno-missing-field-initializers -pedantic -Wno-long-long -Wimplicit-fallthrough -Wno-maybe-uninitialized -Wno-nonnull -Wno-class-memaccess -Wno-redundant-move -Wno-pessimizing-move -Wno-noexcept-type -Wdelete-non-virtual-dtor -Wsuggest-override -Wno-comment -Wno-misleading-indentation -Wctad-maybe-unsupported -fdiagnostics-color -ffunction-sections -fdata-sections -fno-common -Woverloaded-virtual -fno-strict-aliasing -Wl,-z,defs -Wl,-z,nodelete -Wl,-rpath-link,/media/root/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/build/./lib -Wl,--gc-sections -shared -Wl,-soname,libclangCodeGen.so.18git -o lib/libclangCodeGen.so.18git tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/ABIInfo.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/ABIInfoImpl.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/BackendUtil.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGAtomic.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGBlocks.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGBuiltin.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGCUDANV.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGCUDARuntime.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGCXX.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGCXXABI.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGCall.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGClass.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGCleanup.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGCoroutine.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGDebugInfo.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGDecl.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGDeclCXX.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGException.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGExpr.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGExprAgg.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGExprCXX.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGExprComplex.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGExprConstant.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGExprScalar.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGGPUBuiltin.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGHLSLRuntime.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGLoopInfo.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGNonTrivialStruct.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGObjC.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGObjCGNU.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGObjCMac.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGObjCRuntime.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGOpenCLRuntime.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGOpenMPRuntime.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGOpenMPRuntimeGPU.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGRecordLayoutBuilder.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGStmt.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGStmtOpenMP.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGVTT.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CGVTables.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CodeGenABITypes.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CodeGenAction.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CodeGenFunction.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CodeGenModule.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CodeGenPGO.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CodeGenTBAA.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/CodeGenTypes.cpp.o tools/clang/lib/CodeGen/CMakeFiles/obj.clangCodeGen.dir/Cons
[Bug tree-optimization/111393] ICE: Segmentation fault src/gcc/toplev.cc:314
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111393 --- Comment #9 from AK --- i think it is okay to close this bug as this doesn't seem to be related to gcc.
[Bug tree-optimization/111393] ICE: Segmentation fault src/gcc/toplev.cc:314
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111393 --- Comment #8 from AK --- > this does seem like a HW issue. Are you sure you have a decent RISCV machine > without any memory issues? > I suspect ninja is building with all of the cores which pushes the memory > usage high. possible. I have the https://sipeed.com/licheepi4a (licheepi 4a board) > Maybe lower the clock speed of the CPU you are using. will do. thanks
[Bug tree-optimization/111393] ICE: Segmentation fault src/gcc/toplev.cc:314
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111393 --- Comment #5 from AK --- Created attachment 55890 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=55890&action=edit GlobalModuleIndex.cpp preprocessed files Everytime the crash is in a different file. it could be just because of memory issues.
[Bug tree-optimization/111393] ICE: Segmentation fault src/gcc/toplev.cc:314
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111393 --- Comment #3 from AK --- gcc -v COLLECT_GCC=gcc COLLECT_LTO_WRAPPER=/usr/libexec/gcc/riscv64-linux-gnu/13/lto-wrapper Target: riscv64-linux-gnu Configured with: ../src/configure -v --with-pkgversion='Debian 13.1.0-6' --with-bugurl=file:///usr/share/doc/gcc-13/README.Bugs --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --prefix=/usr --with-gcc-major-version-only --program-suffix=-13 --program-prefix=riscv64-linux-gnu- --enable-shared --enable-linker-build-id --libexecdir=/usr/libexec --without-included-gettext --enable-threads=posix --libdir=/usr/lib --enable-nls --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --with-default-libstdcxx-abi=new --enable-gnu-unique-object --disable-libitm --disable-libquadmath --disable-libquadmath-support --enable-plugin --enable-default-pie --with-system-zlib --enable-libphobos-checking=release --with-target-system-zlib=auto --enable-objc-gc=auto --enable-multiarch --disable-werror --disable-multilib --with-arch=rv64gc --with-abi=lp64d --enable-checking=release --build=riscv64-linux-gnu --host=riscv64-linux-gnu --target=riscv64-linux-gnu --with-build-config=bootstrap-lto-lean --enable-link-serialization=32 Thread model: posix Supported LTO compression algorithms: zlib zstd gcc version 13.1.0 (Debian 13.1.0-6) root@lpi4a:/media/root/d2fc9f48-c166-4a9
[Bug tree-optimization/111393] ICE: Segmentation fault src/gcc/toplev.cc:314
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111393
--- Comment #1 from AK ---
oot/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/build# ninja clang
check-clang
[100/845] Building CXX object
tools/clang/lib/Serialization/CMakeFiles/obj.clangSerialization.dir/GlobalModuleIndex.cpp.o
FAILED:
tools/clang/lib/Serialization/CMakeFiles/obj.clangSerialization.dir/GlobalModuleIndex.cpp.o
/usr/bin/c++ -DGTEST_HAS_RTTI=0 -D_DEBUG -D_GLIBCXX_ASSERTIONS -D_GNU_SOURCE
-D_LIBCPP_ENABLE_HARDENED_MODE -D__STDC_CONSTANT_MACROS -D__STDC_FORMAT_MACROS
-D__STDC_LIMIT_MACROS
-I/media/root/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/build/tools/clang/lib/Serialization
-I/media/root/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/clang/lib/Serialization
-I/media/root/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/clang/include
-I/media/root/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/build/tools/clang/include
-I/media/root/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/build/include
-I/media/root/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/llvm/include
-fPIC -fno-semantic-interposition -fvisibility-inlines-hidden -Werror=date-time
-fno-lifetime-dse -Wall -Wextra -Wno-unused-parameter -Wwrite-strings
-Wcast-qual -Wno-missing-field-initializers -pedantic -Wno-long-long
-Wimplicit-fallthrough -Wno-maybe-uninitialized -Wno-nonnull
-Wno-class-memaccess -Wno-redundant-move -Wno-pessimizing-move
-Wno-noexcept-type -Wdelete-non-virtual-dtor -Wsuggest-override -Wno-comment
-Wno-misleading-indentation -Wctad-maybe-unsupported -fdiagnostics-color
-ffunction-sections -fdata-sections -fno-common -Woverloaded-virtual
-fno-strict-aliasing -fno-exceptions -funwind-tables -fno-rtti -UNDEBUG
-std=c++17 -MD -MT
tools/clang/lib/Serialization/CMakeFiles/obj.clangSerialization.dir/GlobalModuleIndex.cpp.o
-MF
tools/clang/lib/Serialization/CMakeFiles/obj.clangSerialization.dir/GlobalModuleIndex.cpp.o.d
-o
tools/clang/lib/Serialization/CMakeFiles/obj.clangSerialization.dir/GlobalModuleIndex.cpp.o
-c
/media/root/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/clang/lib/Serialization/GlobalModuleIndex.cpp
In file included from
/media/root/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/llvm/include/llvm/ADT/DenseMapInfo.h:20,
from
/media/root/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/llvm/include/llvm/ADT/DenseMap.h:17,
from
/media/root/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/clang/include/clang/Serialization/GlobalModuleIndex.h:18,
from
/media/root/d2fc9f48-c166-4a9e-9868-133a1db7af88/llvm-project/clang/lib/Serialization/GlobalModuleIndex.cpp:13:
/usr/include/c++/13/tuple: In instantiation of ‘struct std::_Tuple_impl<0,
clang::ModuleFileExtensionReader*,
std::default_delete >’:
/usr/include/c++/13/tuple:1232:11: required from ‘class
std::tuple >’
/usr/include/c++/13/bits/unique_ptr.h:232:27: required from ‘class
std::__uniq_ptr_impl >’
/usr/include/c++/13/bits/unique_ptr.h:239:12: required from ‘struct
std::__uniq_ptr_data, true, true>’
/usr/include/c++/13/bits/unique_ptr.h:283:33: required from ‘class
std::unique_ptr’
/usr/include/c++/13/bits/stl_vector.h:367:35: required from
‘std::_Vector_base<_Tp, _Alloc>::~_Vector_base() [with _Tp =
std::unique_ptr; _Alloc =
std::allocator >]’
/usr/include/c++/13/bits/stl_vector.h:528:7: required from here
/usr/include/c++/13/tuple:269:7: internal compiler error: Segmentation fault
269 | _M_head(_Tuple_impl& __t) noexcept { return _Base::_M_head(__t);
}
| ^~~
0x85d7c5 crash_signal
../../src/gcc/toplev.cc:314
0xa0d5e0 profile_count::operator==(profile_count const&) const
../../src/gcc/profile-count.h:865
0xa0d5e0 profile_count::apply_probability(profile_probability) const
../../src/gcc/profile-count.h:1104
0xa0d5e0 edge_def::count() const
../../src/gcc/basic-block.h:639
0xa0d5e0 eliminate_tail_call
../../src/gcc/tree-tailcall.cc:982
0xa0d5e0 optimize_tail_call
../../src/gcc/tree-tailcall.cc:1053
0xa0d5e0 tree_optimize_tail_calls_1
../../src/gcc/tree-tailcall.cc:1193
Please submit a full bug report, with preprocessed source (by using
-freport-bug).
Please include the complete backtrace with any bug report.
See for instructions.
[Bug tree-optimization/111393] New: ICE: Segmentation fault src/gcc/toplev.cc:314
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111393 Bug ID: 111393 Summary: ICE: Segmentation fault src/gcc/toplev.cc:314 Product: gcc Version: unknown Status: UNCONFIRMED Severity: normal Priority: P3 Component: tree-optimization Assignee: unassigned at gcc dot gnu.org Reporter: hiraditya at msn dot com Target Milestone: --- riscv64-gnu-linux (version Debian 13.1) building llvm-project (GlobalModuleIndex.cpp) crashed with ICE. src/gcc/toplev.cc:314 profile_count::operator==(proile_count const&) const ../../src/gcc/profile-count.h:865 profile_count::apply_probability(proile_probability) const ../../src/gcc/profile-count.h:1104
[Bug c++/110909] New: Suboptimal codegen in vector copy assignment
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110909
Bug ID: 110909
Summary: Suboptimal codegen in vector copy assignment
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
#include
using Container = std::vector;
int copy_assignment(const Container &v1, Container &v2) {
v2 = v1;
return 0;
}
I'd expect this to only generate a memcpy. but i'm not sure why memmoves are
generated?
$ gcc -std=c++2a -O3 -fno-exceptions
copy_assignment(std::vector > const&, std::vector >&):
cmp rsi, rdi
je .L21
pushr13
pushr12
pushrbp
mov rbp, rdi
pushrbx
mov rbx, rsi
sub rsp, 8
mov rax, QWORD PTR [rdi+8]
mov r13, QWORD PTR [rdi]
mov rdx, QWORD PTR [rsi+16]
mov rdi, QWORD PTR [rsi]
mov r12, rax
sub r12, r13
sub rdx, rdi
cmp rdx, r12
jb .L25
mov rcx, QWORD PTR [rsi+8]
mov rdx, rcx
sub rdx, rdi
cmp rdx, r12
jnb .L26
cmp rdx, 4
jle .L12
mov rsi, r13
callmemmove
mov rcx, QWORD PTR [rbx+8]
mov rdi, QWORD PTR [rbx]
mov rax, QWORD PTR [rbp+8]
mov r13, QWORD PTR [rbp+0]
mov rdx, rcx
sub rdx, rdi
.L13:
lea rsi, [r13+0+rdx]
sub rax, rsi
mov rdx, rax
cmp rax, 4
jle .L14
mov rdi, rcx
callmemmove
mov rax, QWORD PTR [rbx]
add rax, r12
.L8:
mov QWORD PTR [rbx+8], rax
add rsp, 8
xor eax, eax
pop rbx
pop rbp
pop r12
pop r13
ret
.L21:
xor eax, eax
ret
.L25:
movabs rax, 9223372036854775804
cmp rax, r12
jb .L27
mov rdi, r12
calloperator new(unsigned long)
mov rbp, rax
cmp r12, 4
jle .L5
mov rdx, r12
mov rsi, r13
mov rdi, rax
callmemcpy
.L6:
mov rdi, QWORD PTR [rbx]
testrdi, rdi
je .L7
mov rsi, QWORD PTR [rbx+16]
sub rsi, rdi
calloperator delete(void*, unsigned long)
.L7:
lea rax, [rbp+0+r12]
mov QWORD PTR [rbx], rbp
mov QWORD PTR [rbx+16], rax
jmp .L8
.L26:
cmp r12, 4
jle .L10
mov rdx, r12
mov rsi, r13
callmemmove
mov rax, QWORD PTR [rbx]
add rax, r12
jmp .L8
.L14:
lea rax, [rdi+r12]
jne .L8
mov edx, DWORD PTR [rsi]
mov DWORD PTR [rcx], edx
jmp .L8
.L12:
jne .L13
mov esi, DWORD PTR [r13+0]
mov DWORD PTR [rdi], esi
jmp .L13
.L10:
lea rax, [rdi+r12]
jne .L8
mov edx, DWORD PTR [r13+0]
mov DWORD PTR [rdi], edx
jmp .L8
.L5:
mov eax, DWORD PTR [r13+0]
mov DWORD PTR [rbp+0], eax
jmp .L6
.L27:
callstd::__throw_bad_array_new_length()
Ideally, the above C++ code should translate to an equivalent of the following
C++ code:
using Container = std::vector;
int copy_assignment(const Container &v1, Container &v2) {
v2.reserve(v1.size());
std::memcpy(&v2[0], &v1[0], v1.size()*sizeof(int));
// change the size: v2.size() = v1.size()
return 0;
}
[Bug c++/110137] implement clang -fassume-sane-operator-new
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110137 --- Comment #3 from AK --- 1. clang also has noalias on nothrow versions of operator new. will `-fassume-sane-operator-new` enable that as well? 2. as per: http://eel.is/c++draft/basic.stc.dynamic#allocation-2 """If the request succeeds, the value returned by a replaceable allocation function is a non-null pointer value ([basic.compound]) p0 different from any previously returned value p1, unless that value p1 was subsequently passed to a replaceable deallocation function.""" Does this mean that all successful new allocations can be assumed to be a noalias as long as the pointer wasn't passed to a deallocation function? In that case when possible, can the compiler `infer` from a bottom-up analysis that an allocation is a noalias?
[Bug tree-optimization/110819] Missed optimization: when vector's size is 0 but vector::reserve has been called.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110819 --- Comment #2 from AK --- > When compiled with clang, libstdc++'s std::vector uses __builtin_operator_new > which always has the -fassume-sane-operator-new semantics, and so can be > optimized. yes clang optimizes with libstdc++ as well. what can be done in gcc for it to detect that the new+delete pair can be optimized away?
[Bug c++/110819] New: Missed optimization: when vector size is 0 but vector::reserve has been called.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110819
Bug ID: 110819
Summary: Missed optimization: when vector size is 0 but
vector::reserve has been called.
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
#include
void f(int);
void use_idx_const_size_reserve() {
std::vector v;
v.reserve(10);
auto s = v.size();
for (std::vector::size_type i = 0; i < s; i++)
f(v[i]);
}
$ g++ -O3
use_idx_const_size_reserve():
sub rsp, 8
mov edi, 40
calloperator new(unsigned long)
mov esi, 40
add rsp, 8
mov rdi, rax
jmp operator delete(void*, unsigned long)
$ clang++ -O3 -stdlib=libc++
use_idx_const_size_reserve():# @use_idx_const_size_reserve()
ret
[Bug libstdc++/109442] Dead local copy of std::vector not removed from function
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109442 --- Comment #17 from AK --- With recent changes in libc++ (https://reviews.llvm.org/D147741) clang optimizes away the new-delete pair. https://godbolt.org/z/a6PG54Pvb $ clang++ -O3 -stdlib=libc++ -fno-exceptions vat1(std::__1::vector >): # @vat1(std::__1::vector >) sub rsp, 24 xorps xmm0, xmm0 movaps xmmword ptr [rsp], xmm0 mov qword ptr [rsp + 16], 0 mov rax, qword ptr [rdi + 8] sub rax, qword ptr [rdi] je .LBB0_2 js .LBB0_3 .LBB0_2: mov eax, 10 add rsp, 24 ret .LBB0_3: mov rdi, rsp call std::__1::vector >::__throw_length_error[abi:v17]() const .L.str: .asciz "vector" .L.str.1: .asciz "length_error was thrown in -fno-exceptions mode with message \"%s\"" Previously clang couldn't even convert the copy to a memmove and would generate a raw loop e.g., https://godbolt.org/z/G8ax1o5bc .LBB0_6: # =>This Inner Loop Header: Depth=1 movups xmm0, xmmword ptr [r15 + 4*rdi] movups xmm1, xmmword ptr [r15 + 4*rdi + 16] movups xmmword ptr [rax + 4*rdi], xmm0 movups xmmword ptr [rax + 4*rdi + 16], xmm1 add rdi, 8 cmp rsi, rdi jne .LBB0_6 cmp rbx, rsi jne .LBB0_8 jmp .LBB0_9 .LBB0_3:
[Bug c++/109443] missed optimization of std::vector access (Related to issue 35269)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109443
--- Comment #17 from AK ---
Even after vector::size() is hoisted, the codegen is sub-optimal compared to
iterator version.
```
void use_idx_const_size(std::vector v) {
auto s = v.size();
for (std::vector::size_type i = 0; i < s; i++)
f(v[i]);
}
```
$ g++ -O3
use_idx_const_size(std::vector >):
pushr12
pushrbp
pushrbx
mov rdx, QWORD PTR [rdi+8]
mov rax, QWORD PTR [rdi]
mov r12, rdx
sub r12, rax
sar r12, 2
cmp rax, rdx
je .L1
mov rbp, rdi
xor ebx, ebx
jmp .L3
.L6:
mov rax, QWORD PTR [rbp+0]
.L3:
mov edi, DWORD PTR [rax+rbx*4]
add rbx, 1
callf(int)
cmp rbx, r12
jb .L6
.L1:
pop rbx
pop rbp
pop r12
ret
It seems compiler is assuming that vector `v` is not loop-invariant?
[Bug target/100811] Consider not omitting frame pointers by default on targets with many registers
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100811 --- Comment #8 from AK --- Should we enable frame-pointers by default for RISCV64 as well?
[Bug target/100811] Consider not omitting frame pointers by default on targets with many registers
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100811 AK changed: What|Removed |Added CC||hiraditya at msn dot com --- Comment #4 from AK --- On AArch64 (typically mobile platforms) app developers typically would enable frame pointers by default because it helps with crash reporting.
[Bug c++/87628] Redundant check of pointer when operator delete is called
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=87628 --- Comment #6 from AK --- Opened a bug for clang as well: https://github.com/llvm/llvm-project/issues/62783
[Bug c++/87628] Redundant check of pointer when operator delete is called
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=87628 --- Comment #5 from AK --- As per: https://en.cppreference.com/w/cpp/memory/new/operator_delete """ In all cases, if ptr is a null pointer, the standard library deallocation functions do nothing. If the pointer passed to the standard library deallocation function was not obtained from the corresponding standard library allocation function, the behavior is undefined. """ So it should be fine to remove the check `if(p)`
[Bug tree-optimization/109441] missed optimization when all elements of vector are known
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109441 --- Comment #3 from AK --- > But IMHO it's academic, right? yes. i was just messing with vector codegen. But in case all the elements of a vector/array are same, maybe the loop can be replaced with equivalent computation?
[Bug tree-optimization/35269] missed optimization of std::vector access.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=35269 AK changed: What|Removed |Added CC||hiraditya at msn dot com --- Comment #2 from AK --- I posted a revised version of this bug here: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109443
[Bug tree-optimization/109443] missed optimization of std::vector access (Related to issue 35269)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109443 --- Comment #1 from AK --- Link to issue: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=35269 where I derived the testcase from.
[Bug tree-optimization/109443] New: missed optimization of std::vector access (Related to issue 35269)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109443
Bug ID: 109443
Summary: missed optimization of std::vector access (Related to
issue 35269)
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
here is slightly modified code example from issue #35269. Both accesses are
similar bug different code is generated. the function `h` has better codegen
than `g` for some reason.
$ g++ -O3 -std=c++20 -fno-exceptions
void f(int);
void g(std::vector v)
{
for (std::vector::size_type i = 0; i < v.size(); i++)
f( v[ i ] );
}
void h(std::vector v)
{
for (std::vector::const_iterator i = v.begin(); i != v.end(); ++i)
f( *i );
}
g(std::vector >):
mov rdx, QWORD PTR [rdi]
cmp QWORD PTR [rdi+8], rdx
je .L6
pushrbp
mov rbp, rdi
pushrbx
xor ebx, ebx
sub rsp, 8
.L3:
mov edi, DWORD PTR [rdx+rbx*4]
add rbx, 1
callf(int)
mov rdx, QWORD PTR [rbp+0]
mov rax, QWORD PTR [rbp+8]
sub rax, rdx
sar rax, 2
cmp rbx, rax
jb .L3
add rsp, 8
pop rbx
pop rbp
ret
.L6:
ret
h(std::vector >):
pushrbp
pushrbx
sub rsp, 8
mov rbx, QWORD PTR [rdi]
cmp rbx, QWORD PTR [rdi+8]
je .L10
mov rbp, rdi
.L12:
mov edi, DWORD PTR [rbx]
add rbx, 4
callf(int)
cmp QWORD PTR [rbp+8], rbx
jne .L12
.L10:
add rsp, 8
pop rbx
pop rbp
ret
[Bug tree-optimization/109442] New: Dead local copy of std::vector not removed from function
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109442
Bug ID: 109442
Summary: Dead local copy of std::vector not removed from
function
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
T vat1(std::vector v1) {
auto v = v1;
return 10;
}
g++ -O3 -std=c++20 -fno-exceptions
vat1(std::vector >):
mov rax, QWORD PTR [rdi+8]
sub rax, QWORD PTR [rdi]
je .L11
pushrbp
mov rbp, rax
movabs rax, 9223372036854775804
pushrbx
sub rsp, 8
cmp rax, rbp
jb .L15
mov rbx, rdi
mov rdi, rbp
calloperator new(unsigned long)
mov rsi, QWORD PTR [rbx]
mov rdx, QWORD PTR [rbx+8]
mov rdi, rax
sub rdx, rsi
cmp rdx, 4
jle .L16
callmemmove
mov rdi, rax
.L6:
mov rsi, rbp
calloperator delete(void*, unsigned long)
add rsp, 8
mov eax, 10
pop rbx
pop rbp
ret
.L11:
mov eax, 10
ret
.L15:
callstd::__throw_bad_array_new_length()
.L16:
jne .L6
mov eax, DWORD PTR [rsi]
mov DWORD PTR [rdi], eax
jmp .L6
[Bug tree-optimization/109441] missed optimization when all elements of vector are known
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109441
--- Comment #1 from AK ---
I guess a better test case is this:
#include
using namespace std;
using T = int;
T v(std::vector v) {
T s;
std::fill(v.begin(), v.end(), T());
for (auto i = 0; i < v.size(); ++i) {
s += v[i];
}
return s;
}
which has similar effect.
$ g++ -O3 -std=c++17
v(std::vector >):
pushrbp
pushrbx
sub rsp, 8
mov rbp, QWORD PTR [rdi+8]
mov rcx, QWORD PTR [rdi]
cmp rcx, rbp
je .L7
sub rbp, rcx
mov rdi, rcx
xor esi, esi
mov rbx, rcx
mov rdx, rbp
callmemset
mov rdi, rbp
mov edx, 1
mov rcx, rbx
sar rdi, 2
testrbp, rbp
cmovne rdx, rdi
cmp rbp, 12
jbe .L8
mov rax, rdx
pxorxmm0, xmm0
shr rax, 2
sal rax, 4
add rax, rbx
.L4:
movdqu xmm2, XMMWORD PTR [rbx]
add rbx, 16
paddd xmm0, xmm2
cmp rbx, rax
jne .L4
movdqa xmm1, xmm0
psrldq xmm1, 8
paddd xmm0, xmm1
movdqa xmm1, xmm0
psrldq xmm1, 4
paddd xmm0, xmm1
movdeax, xmm0
testdl, 3
je .L1
and rdx, -4
mov esi, edx
.L3:
add eax, DWORD PTR [rcx+rdx*4]
lea edx, [rsi+1]
movsx rdx, edx
cmp rdx, rdi
jnb .L1
add esi, 2
lea r8, [0+rdx*4]
add eax, DWORD PTR [rcx+rdx*4]
movsx rsi, esi
cmp rsi, rdi
jnb .L1
add eax, DWORD PTR [rcx+4+r8]
.L1:
add rsp, 8
pop rbx
pop rbp
ret
.L7:
add rsp, 8
xor eax, eax
pop rbx
pop rbp
ret
.L8:
xor eax, eax
xor esi, esi
xor edx, edx
jmp .L3
[Bug tree-optimization/109441] New: missed optimization when all elements of vector are known
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109441
Bug ID: 109441
Summary: missed optimization when all elements of vector are
known
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
Reference: https://godbolt.org/z/af4x6zhz9
When all elements of vector are 0, then the compiler should be able to remove
the loop and just return 0.
Testcase:
#include
using namespace std;
using T = int;
T v() {
T s;
std::vector v;
v.resize(1000, 0);
for (auto i = 0; i < v.size(); ++i) {
s += v[i];
}
return s;
}
$ g++ -O3 -std=c++17
.LC0:
.string "vector::_M_fill_insert"
v():
push rbx
pxor xmm0, xmm0
mov edx, 1000
xor esi, esi
sub rsp, 48
lea rcx, [rsp+12]
lea rdi, [rsp+16]
mov QWORD PTR [rsp+32], 0
mov DWORD PTR [rsp+12], 0
movaps XMMWORD PTR [rsp+16], xmm0
call std::vector
>::_M_fill_insert(__gnu_cxx::__normal_iterator > >, unsigned long, int const&)
mov rdx, QWORD PTR [rsp+24]
mov rdi, QWORD PTR [rsp+16]
mov rax, rdx
sub rax, rdi
mov rsi, rax
sar rsi, 2
cmp rdx, rdi
je .L99
test rax, rax
mov ecx, 1
cmovne rcx, rsi
cmp rax, 12
jbe .L107
mov rdx, rcx
pxor xmm0, xmm0
mov rax, rdi
shr rdx, 2
sal rdx, 4
add rdx, rdi
.L101:
movdqu xmm2, XMMWORD PTR [rax]
add rax, 16
paddd xmm0, xmm2
cmp rdx, rax
jne .L101
movdqa xmm1, xmm0
psrldq xmm1, 8
paddd xmm0, xmm1
movdqa xmm1, xmm0
psrldq xmm1, 4
paddd xmm0, xmm1
movd ebx, xmm0
test cl, 3
je .L99
and rcx, -4
mov eax, ecx
.L100:
lea edx, [rax+1]
add ebx, DWORD PTR [rdi+rcx*4]
movsx rdx, edx
cmp rdx, rsi
jnb .L99
add eax, 2
lea rcx, [0+rdx*4]
add ebx, DWORD PTR [rdi+rdx*4]
cdqe
cmp rax, rsi
jnb .L99
add ebx, DWORD PTR [rdi+4+rcx]
.L99:
test rdi, rdi
je .L98
mov rsi, QWORD PTR [rsp+32]
sub rsi, rdi
call operator delete(void*, unsigned long)
.L98:
add rsp, 48
mov eax, ebx
pop rbx
ret
.L107:
xor eax, eax
xor ecx, ecx
jmp .L100
mov rbx, rax
jmp .L105
v() [clone .cold]:
[Bug tree-optimization/109440] New: Missed optimization of vector::at when a function is called inside the loop
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109440
Bug ID: 109440
Summary: Missed optimization of vector::at when a function is
called inside the loop
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
#include
#include
using namespace std;
bool bar();
using T = int;
T vat(std::vector v) {
T s;
for (auto i = 0; i < v.size(); ++i) {
if (bar())
s += v.at(i);
}
return s;
}
$ gcc -O2 -fexceptions -fno-unroll-loops
.LC0:
.string "vector::_M_range_check: __n (which is %zu) >= this->size()
(which is %zu)"
vat(std::vector >):
mov rax, QWORD PTR [rdi]
cmp QWORD PTR [rdi+8], rax
je .L9
pushr12
pushrbp
mov rbp, rdi
pushrbx
xor ebx, ebx
jmp .L6
.L14:
mov rax, QWORD PTR [rbp+8]
sub rax, QWORD PTR [rbp+0]
add rbx, 1
sar rax, 2
cmp rbx, rax
jnb .L13
.L6:
callbar()
testal, al
je .L14
mov rcx, QWORD PTR [rbp+0]
mov rdx, QWORD PTR [rbp+8]
sub rdx, rcx
sar rdx, 2
mov rax, rdx
cmp rbx, rdx
jnb .L15
add r12d, DWORD PTR [rcx+rbx*4]
add rbx, 1
cmp rbx, rax
jb .L6
.L13:
mov eax, r12d
pop rbx
pop rbp
pop r12
ret
.L9:
mov eax, r12d
ret
.L15:
mov rsi, rbx
mov edi, OFFSET FLAT:.LC0
xor eax, eax
callstd::__throw_out_of_range_fmt(char const*, ...)
[Bug tree-optimization/108915] invalid pointer access preserved in optimized code
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108915 --- Comment #6 from AK --- For reference, I had opened a related bug in clang: https://github.com/llvm/llvm-project/issues/60967
[Bug c++/109017] ICE on unexpanded pack from C++20 explicit-template-parameter lambda syntax
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109017
AK changed:
What|Removed |Added
CC||hiraditya at msn dot com
--- Comment #1 from AK ---
Example from twitter: https://twitter.com/seanbax/status/1631689332007337985
which had discussion on similar bug.
```
template struct outer1_t {
void g() {
// Compiles for mysterious reasons.
int array[] { [](){
int i = Is2;
return i;
}.template operator()() ... };
}
};
int main() {
// Compiles OKAY when this is commented out.
// ICEs when it's compiled.
outer1_t<1, 5, 10>().g();
}
```
clang issues a compiler error: https://godbolt.org/z/7f6E55svM
```
:6:15: error: initializer contains unexpanded parameter pack 'Is2'
int i = Is2;
```
[Bug tree-optimization/108915] invalid pointer access preserved in optimized code
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108915 AK changed: What|Removed |Added Resolution|INVALID |FIXED --- Comment #4 from AK --- Adding `__attribute__((used))` also fixed it. Does it reflect the same behavior as using `asm` as you suggested?
[Bug c/108915] New: invalid pointer access preserved in optimized code
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108915
Bug ID: 108915
Summary: invalid pointer access preserved in optimized code
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
Testcase has been reduced from u-boot's linker-list macro:
https://github.com/u-boot/u-boot/blob/master/include/linker_lists.h#L127
#include
char* bar() {
static char start_bar[0] __attribute__((aligned(16)))
__attribute__((unused))
__attribute__((section("__u_boot_list_2_1")));
char *p = (char *)start_bar;
for (int i = p[0]; i < p[9]; i++)
printf("asdfasd");
return 0;
}
$ gcc -O3 -fno-unroll-loops -S -o -
.LC0:
.string "asdfasd"
bar:
pushrbx
movsx eax, BYTE PTR start_bar.1[rip+9]
movsx ebx, BYTE PTR start_bar.1[rip]
cmp ebx, eax
jge .L2
.L3:
mov edi, OFFSET FLAT:.LC0
xor eax, eax
add ebx, 1
callprintf
movsx eax, BYTE PTR start_bar.1[rip+9]
cmp eax, ebx
jg .L3
.L2:
xor eax, eax
pop rbx
ret
-
$ clang -O3 -fno-unroll-loops -S -o -
bar:# @bar
xor eax, eax
ret
[Bug libstdc++/107335] call to throw_bad_cast even with -fno-exceptions
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107335 AK changed: What|Removed |Added Status|NEW |RESOLVED Resolution|--- |INVALID --- Comment #7 from AK --- not a bug
[Bug libstdc++/107335] call to throw_bad_cast even with -fno-exceptions
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107335 --- Comment #5 from AK --- Is this the definition of throw_bad_cast? https://github.com/gcc-mirror/gcc/blob/16e2427f50c208dfe07d07f18009969502c25dc8/gcc/cp/rtti.c#L221
[Bug libstdc++/107335] call to throw_bad_cast even with -fno-exceptions
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107335 --- Comment #4 from AK --- I wasn't sure if this is expected. Thanks for clarifying.
[Bug c++/107335] New: call to throw_bad_cast even with -fno-exceptions
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107335
Bug ID: 107335
Summary: call to throw_bad_cast even with -fno-exceptions
Product: gcc
Version: 13.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
Testcase:
#include
void foo() {
std::cout << std::endl;
}
$ g++ -std=c++17 -O3 -fno-exceptions
```asm
foo():
mov rax, QWORD PTR std::cout[rip]
pushrbx
mov rax, QWORD PTR [rax-24]
mov rbx, QWORD PTR std::cout[rax+240]
testrbx, rbx
je .L10
cmp BYTE PTR [rbx+56], 0
je .L5
movsx esi, BYTE PTR [rbx+67]
.L6:
mov edi, OFFSET FLAT:std::cout
callstd::basic_ostream >::put(char)
pop rbx
mov rdi, rax
jmp std::basic_ostream >::flush()
.L5:
mov rdi, rbx
callstd::ctype::_M_widen_init() const
mov rax, QWORD PTR [rbx]
mov esi, 10
mov rax, QWORD PTR [rax+48]
cmp rax, OFFSET FLAT:_ZNKSt5ctypeIcE8do_widenEc
je .L6
mov rdi, rbx
callrax
movsx esi, al
jmp .L6
.L10:
callstd::__throw_bad_cast() <--- call to __throw_bad_cast
_GLOBAL__sub_I_foo():
sub rsp, 8
mov edi, OFFSET FLAT:_ZStL8__ioinit
callstd::ios_base::Init::Init() [complete object constructor]
mov edx, OFFSET FLAT:__dso_handle
mov esi, OFFSET FLAT:_ZStL8__ioinit
mov edi, OFFSET FLAT:_ZNSt8ios_base4InitD1Ev
add rsp, 8
jmp __cxa_atexit
```
[Bug tree-optimization/85611] Suboptimal code generation for (potentially) redundant atomic loads
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=85611 AK changed: What|Removed |Added Status|WAITING |RESOLVED Resolution|--- |INVALID --- Comment #2 from AK --- Don't remember what I was expecting.
[Bug rtl-optimization/107063] New: [X86_64 codegen] Using inc eax instead of inc dword ptr
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107063
Bug ID: 107063
Summary: [X86_64 codegen] Using inc eax instead of inc dword
ptr
Product: gcc
Version: 13.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: rtl-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
int volatile gv = 0;
void foo() {
++gv;
}
$ gcc -Os
foo():
mov eax, DWORD PTR gv[rip]
inc eax
mov DWORD PTR gv[rip], eax
ret
gv:
.zero 4
$ clang -Os
foo():# @foo()
inc dword ptr [rip + gv]
ret
gv:
.long 0
https://godbolt.org/z/vzq4jr5vj
[Bug tree-optimization/107011] instruction with undefined behavior not optimized away
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107011 --- Comment #2 from AK --- ah ok. sorry for the noise.
[Bug tree-optimization/107011] New: instruction with undefined behavior not optimized away
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107011
Bug ID: 107011
Summary: instruction with undefined behavior not optimized away
Product: gcc
Version: 13.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
#include
int main() {
return INT_MIN / -1;
}
$ gcc -O3
main:
mov eax, -2147483648
ret
$ clang -O3
main: # @main
ret
https://godbolt.org/z/393EMqs1E
PS: I reported this bug yesterday as well but for some reason it does not
appear in bugzilla so I'm creating another one.
[Bug tree-optimization/95565] [Feature request] add a flag to only instrument function entry.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=95565 --- Comment #2 from AK --- clang has `-finstrument-function-entry-bare` to this effect: https://reviews.llvm.org/D40276
[Bug tree-optimization/107005] New: gcc not exploiting undefined behavior to optimize away the result of division
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107005
Bug ID: 107005
Summary: gcc not exploiting undefined behavior to optimize away
the result of division
Product: gcc
Version: 13.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
#include
int main() { return INT_MIN / -1; }
gcc -O2
main:
mov eax, -2147483648
ret
clang -O2
main: # @main
ret
https://godbolt.org/z/Tjxx3KGdK
[Bug ipa/106991] new+delete pair not optimized by g++ at -O3 but optimized at -Os
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106991
--- Comment #3 from AK ---
Thanks for identifying the underlying issue @Jan
After modifying the definition of operator delete. gcc does optimize it at -O3
as well.
https://godbolt.org/z/1WPqaWrEr
// source code
#include
#include
int volatile gv = 0;
void* operator new(long unsigned sz ) {
++gv;
return malloc( sz );
}
void operator delete(void *p, unsigned long) noexcept {
--gv;
free(p);
}
class c {
int l;
public:
c() : l(0) {}
int get(){ return l; }
};
int caller( void ){
c *f = new c();
assert( f->get() == 0 );
delete f;
return gv;
}
$ $ g++ -std=c++20 -O3
```
operator new(unsigned long):
mov eax, DWORD PTR gv[rip]
add eax, 1
mov DWORD PTR gv[rip], eax
jmp malloc
operator delete(void*, unsigned long):
mov eax, DWORD PTR gv[rip]
sub eax, 1
mov DWORD PTR gv[rip], eax
jmp free
caller():
mov eax, DWORD PTR gv[rip]
add eax, 1
mov DWORD PTR gv[rip], eax
mov eax, DWORD PTR gv[rip]
sub eax, 1
mov DWORD PTR gv[rip], eax
mov eax, DWORD PTR gv[rip]
ret
gv:
.zero 4
```
[Bug c++/87628] Redundant check of pointer when operator delete is called
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=87628 --- Comment #4 from AK --- Seems like clang now added the check: $ clang++ -Oz -fno-exceptions if_delete(char*): # @if_delete(char*) testrdi, rdi jne operator delete(void*)@PLT # TAILCALL ret
[Bug c++/106991] New: new+delete pair not optimized by g++ at -O3 but optimized at -Os
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106991
Bug ID: 106991
Summary: new+delete pair not optimized by g++ at -O3 but
optimized at -Os
Product: gcc
Version: 13.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
https://godbolt.org/z/PeYcoqTKn
---
#include
#include
int volatile gv = 0;
void* operator new(long unsigned sz ) {
++gv;
return malloc( sz );
}
void operator delete(void *p) noexcept {
--gv;
free(p);
}
class c {
int l;
public:
c() : l(0) {}
int get(){ return l; }
};
int caller( void ){
c *f = new c();
assert( f->get() == 0 );
delete f;
return gv;
}
---
$ g++ -std=c++20 -O3
operator new(unsigned long):
mov eax, DWORD PTR gv[rip]
add eax, 1
mov DWORD PTR gv[rip], eax
jmp malloc
operator delete(void*):
mov eax, DWORD PTR gv[rip]
sub eax, 1
mov DWORD PTR gv[rip], eax
jmp free
caller():
sub rsp, 8
mov eax, DWORD PTR gv[rip]
mov edi, 4
add eax, 1
mov DWORD PTR gv[rip], eax
callmalloc
mov esi, 4
mov rdi, rax
calloperator delete(void*, unsigned long)
mov eax, DWORD PTR gv[rip]
add rsp, 8
ret
gv:
.zero 4
---
$ g++ -std=c++20 -Os
operator new(unsigned long):
mov eax, DWORD PTR gv[rip]
inc eax
mov DWORD PTR gv[rip], eax
jmp malloc
operator delete(void*):
mov eax, DWORD PTR gv[rip]
dec eax
mov DWORD PTR gv[rip], eax
jmp free
caller():
mov eax, DWORD PTR gv[rip]
ret
gv:
.zero 4
[Bug c++/87628] Redundant check of pointer when operator delete is called
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=87628 --- Comment #3 from AK --- Still happening with gcc trunk. https://godbolt.org/z/5K94665GK
[Bug rtl-optimization/82889] Unnecessary sign extension of int32 to int64
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82889 --- Comment #5 from AK --- Link to compiler explorer: https://godbolt.org/z/dGYG4dG15
[Bug rtl-optimization/82889] Unnecessary sign extension of int32 to int64
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82889 --- Comment #4 from AK --- Seems like clang doesn't sign extend. $ clang -O3 -std=c++14 -g0 ``` .text .intel_syntax noprefix .file "example.cpp" .globl lol(int*, int*, unsigned int, unsigned int) # -- Begin function lol(int*, int*, unsigned int, unsigned int) .p2align4, 0x90 .type lol(int*, int*, unsigned int, unsigned int),@function lol(int*, int*, unsigned int, unsigned int): # @lol(int*, int*, unsigned int, unsigned int) .cfi_startproc # %bb.0: # kill: def $edx killed $edx def $rdx and edx, ecx mov r8d, ecx mov ecx, 1 jmp .LBB0_1 .p2align4, 0x90 .LBB0_4:# in Loop: Header=BB0_1 Depth=1 testal, 1 jne .LBB0_5 .LBB0_7:# in Loop: Header=BB0_1 Depth=1 add edx, ecx and edx, r8d inc rcx .LBB0_1:# =>This Inner Loop Header: Depth=1 mov eax, dword ptr [rsi + 4*rdx] testeax, eax js .LBB0_4 # %bb.2:# in Loop: Header=BB0_1 Depth=1 cmp dword ptr [rdi + 4*rax], 42 jne .LBB0_7 # %bb.3: mov eax, 1 ret .LBB0_5: xor eax, eax ret .Lfunc_end0: .size lol(int*, int*, unsigned int, unsigned int), .Lfunc_end0-lol(int*, int*, unsigned int, unsigned int) .cfi_endproc # -- End function .ident "clang version 16.0.0 (https://github.com/llvm/llvm-project.git 5e22ef3198d1686f7978dd150a3eefad4f737bfc)" .section".note.GNU-stack","",@progbits .addrsig ``` $ gcc -O3 -std=c++14 -g0 ``` lol(int*, int*, unsigned int, unsigned int): and edx, ecx mov r8d, 1 mov ecx, ecx jmp .L5 .L10: cmp DWORD PTR [rdi+rax*4], 42 je .L9 .L4: add rdx, r8 add r8, 1 and rdx, rcx .L5: movsx rax, DWORD PTR [rsi+rdx*4] <--- sign extend testeax, eax jns .L10 testal, 1 je .L4 xor eax, eax ret .L9: mov eax, 1 ret ```
[Bug libstdc++/78717] no definition of string::find when lowered to gimple
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78717 --- Comment #3 from AK --- Even with a high inline limit, string::find didn't inline. g++-11.0.2 -O3 -finline-limit=10 -S -o a.s s.cpp cat a.s ``` _Z3fooRKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEES6_i: .LFB1240: .cfi_startproc endbr64 pushq %rbx .cfi_def_cfa_offset 16 .cfi_offset 3, -16 movq8(%rsi), %rcx movslq %edx, %rbx xorl%edx, %edx movq(%rsi), %rsi call _ZNKSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEE4findEPKcmm@PLT cmpq%rax, %rbx popq%rbx .cfi_def_cfa_offset 8 sete%al movzbl %al, %eax ret ```
[Bug other/92396] -ftime-trace support
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92396 AK changed: What|Removed |Added CC||hiraditya at msn dot com --- Comment #12 from AK --- I was building a giant file that takes around 100 minutes. The -ftime-report gave nothing useful to find out hotspots. It is also not clear what we are reporting here as there is no documentation for it in man gcc. The %ages don't add up to 100 and that makes it confusing. I'm wondering if making this task a GSoC project will get more attention?
[Bug libstdc++/80331] unused const std::string not optimized away
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=80331 --- Comment #9 from AK --- can't repro this with gcc 12.1 Seems like this is fixed? https://godbolt.org/z/e6n94zK4E
[Bug tree-optimization/105830] call to memcpy when -nostdlib -nodefaultlibs flags provided
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105830 --- Comment #3 from AK --- with -ffreestanding the calls to memcpy did disappear. Thanks.
[Bug tree-optimization/105830] New: call to memcpy when -nostdlib -nodefaultlibs flags provided
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105830
Bug ID: 105830
Summary: call to memcpy when -nostdlib -nodefaultlibs flags
provided
Product: gcc
Version: 12.1.1
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
https://godbolt.org/z/jTEa6ajn3
```
// test.c
// Type your code here, or load an example.
/* Nonzero if either X or Y is not aligned on a "long" boundary. */
#define UNALIGNED(X, Y) \
(((unsigned long)X & (sizeof (unsigned long) - 1)) | ((unsigned long)Y &
(sizeof (unsigned long) - 1)))
#define UNALIGNED1(a) \
((unsigned long)(a) & (sizeof(unsigned long)-1))
/* How many bytes are copied each iteration of the 4X unrolled loop. */
#define BIGBLOCKSIZE(sizeof (unsigned long) * 4)
/* How many bytes are copied each iteration of the word copy loop. */
#define LITTLEBLOCKSIZE (sizeof (unsigned long))
/* Threshhold for punting to the byte copier. */
#define TOO_SMALL(LEN) ((LEN) < BIGBLOCKSIZE)
void * memcpy (void *__restrict dst0,
const void *__restrict src0,
unsigned long len0)
{
unsigned char *dst = dst0;
const unsigned char *src = src0;
/* If the size is small, or either SRC or DST is unaligned,
then punt into the byte copy loop. This should be rare. */
if (len0 >= LITTLEBLOCKSIZE && !UNALIGNED (src, dst))
{
unsigned long *aligned_dst;
const unsigned long *aligned_src;
aligned_dst = (unsigned long*)dst;
aligned_src = (const unsigned long*)src;
/* Copy one long word at a time if possible. */
/* Copy one long word at a time if possible. */
do
{
*aligned_dst++ = *aligned_src++;
len0 -= LITTLEBLOCKSIZE;
} while (len0 >= LITTLEBLOCKSIZE);
/* Pick up any residual with a byte copier. */
dst = (unsigned char*)aligned_dst;
src = (const unsigned char*)aligned_src;
}
for (; len0; len0--)
*dst++ = *src++;
return dst0;
}
// ARM gcc trunk
gcc -O3 -nostdlib -nodefaultlibs -S -o -
memcpy:
push{r3, r4, r5, r6, r7, lr}
cmp r2, #3
mov r4, r2
mov r5, r0
mov r6, r1
bls .L5
orr r3, r0, r1
lslsr3, r3, #30
beq .L9
.L3:
mov r2, r4
mov r1, r6
bl memcpy ; <- call to memcpy
mov r0, r5
pop {r3, r4, r5, r6, r7, pc}
.L9:
subsr7, r2, #4
and r4, r2, #3
bic r7, r7, #3
addsr7, r7, #4
mov r2, r7
add r6, r6, r7
bl memcpy ; <- call to memcpy
addsr0, r5, r7
.L5:
cmp r4, #0
bne .L3
mov r0, r5
pop {r3, r4, r5, r6, r7, pc}
[Bug c++/105796] New: error: no matching function for call with template function
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105796 Bug ID: 105796 Summary: error: no matching function for call with template function Product: gcc Version: 12.1.1 Status: UNCONFIRMED Severity: normal Priority: P3 Component: c++ Assignee: unassigned at gcc dot gnu.org Reporter: hiraditya at msn dot com Target Milestone: --- test.cpp ``` int func(int, char); template int testFunc(int (*)(TArgs..., char)); int x = testFunc(func); ``` With gcc trunk: g++ -std=c++20 test.cpp -c :6:22: error: no matching function for call to 'testFunc(int (&)(int, char))' 6 | int x = testFunc(func); | ~^~ :4:5: note: candidate: 'template int testFunc(int (*)(TArgs ..., char))' 4 | int testFunc(int (*)(TArgs..., char)); | ^~~~ :4:5: note: template argument deduction/substitution failed: :6:22: note: mismatched types 'char' and 'int' 6 | int x = testFunc(func); | ~^~ Compiler returned: 1
[Bug c++/101138] New: Ambiguous code (with operator==) compiled without error
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101138
Bug ID: 101138
Summary: Ambiguous code (with operator==) compiled without
error
Product: gcc
Version: 12.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
$ cat test.cpp
#include
using namespace std;
template
struct D {
template bool operator==(Y a) const {
cout << "f" <
bool operator==(T a, D b) {
cout << "fD" < a, b;
if (a == b)
return 0;
return 1;
}
gcc compiles this code fine, bug clang errors out.
https://godbolt.org/z/c13EExxeY
[Bug tree-optimization/101116] New: missed peephole optimization not of bitwise and
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101116
Bug ID: 101116
Summary: missed peephole optimization not of bitwise and
Product: gcc
Version: 11.1.1
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
$ cat test.c
bool foo(unsigned i) {
return !(i & 1);
}
gcc -O2 test.c -S -o-
foo(unsigned int):
mov eax, edi
not eax
and eax, 1
ret
clang -O2 test.c -S -o-
foo(unsigned int): # @foo(unsigned int)
testb $1, %dil
sete %al
retq
Ref: https://godbolt.org/z/Tndb1dM8Y
[Bug tree-optimization/100004] Dead write not removed when indirection is introduced.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=14 --- Comment #1 from AK --- godbolt link: https://gcc.godbolt.org/z/f7Y6G1svf
[Bug tree-optimization/100004] New: Dead write not removed when indirection is introduced.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=14
Bug ID: 14
Summary: Dead write not removed when indirection is introduced.
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
struct Foo {
int x;
};
struct Bar {
int x;
};
void alias(Foo* foo, Bar* bar) {
foo->x = 5;
foo->x = bar->x;
}
struct Wrap1 {
Foo foo;
};
struct Wrap2 {
Foo foo;
};
void assign_direct(Wrap1* w1, Wrap2* w2)
{
w1->foo.x = 5;
w1->foo.x = w2->foo.x;
}
void assign_via_pointer(Wrap1* w1, Wrap2* w2)
{
Foo* f1 = &w1->foo;
Foo* f2 = &w2->foo;
f1->x = 5;
f1->x = f2->x;
}
$ gcc-arm64 -O2 -std=c++17 -fstrict-aliasing -S -o -
alias(Foo*, Bar*):
ldr w1, [x1]
str w1, [x0]
ret
assign_direct(Wrap1*, Wrap2*):
ldr w1, [x1]
str w1, [x0]
ret
assign_via_pointer(Wrap1*, Wrap2*):
mov w2, 5
str w2, [x0]
ldr w1, [x1]
str w1, [x0]
ret
[Bug libstdc++/59048] operator== between std::string and const char* slower than strcmp
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=59048 AK changed: What|Removed |Added CC||hiraditya at msn dot com --- Comment #17 from AK --- Now that we have string_view, will it be possible to avoid creating a copy?
[Bug tree-optimization/98497] New: [Potential Perf regression] jne to hot branch instead je to cold
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98497
Bug ID: 98497
Summary: [Potential Perf regression] jne to hot branch instead
je to cold
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
In the following code generated by gcc 10.2
```
.L2:
movups xmm3, XMMWORD PTR [rax]
add rax, 16
addps xmm0, xmm3
cmp rax, rdx
je .L6
jmp .L2
matrix_sum_column_major.cold:
.L6:
movaps xmm2, xmm0
# .
```
I think `jne .L2; jmp.L6` should be more efficient as it avoids one instruction
in the hot path.
c code:
```
float matrix_sum_column_major(float* x, int n) {
n = 32767;
float sum = 0;
for (int i = 0; i < n; i++)
for (int j = 0; j < n; j++)
sum += x[j * n + i];
return sum;
}
```
gcc -Ofast -floop-nest-optimize -o -
```
matrix_sum_column_major:
mov eax, 4294836212
lea rdx, [rdi+131056]
pxorxmm1, xmm1
lea rcx, [rdi+rax]
.L3:
mov rax, rdi
pxorxmm0, xmm0
.L2:
movups xmm3, XMMWORD PTR [rax]
add rax, 16
addps xmm0, xmm3
cmp rax, rdx
je .L6
jmp .L2
matrix_sum_column_major.cold:
.L6:
movaps xmm2, xmm0
addss xmm1, DWORD PTR [rax+8]
lea rdx, [rax+131068]
add rdi, 131068
movhlps xmm2, xmm0
addps xmm2, xmm0
movaps xmm0, xmm2
shufps xmm0, xmm2, 85
addps xmm0, xmm2
movss xmm2, DWORD PTR [rax+4]
addss xmm2, DWORD PTR [rax]
addss xmm1, xmm2
addss xmm1, xmm0
cmp rdx, rcx
jne .L3
movaps xmm0, xmm1
ret
```
Link to godbolt: https://gcc.godbolt.org/z/ac7YY1
