search for: p2align

....file "hello.s" # Start of file scope inline assembly .ident "GCC: (GNU) 6.4.1 20170727 (Red Hat 6.4.1-1) LLVM: 3.9.1" # End of file scope inline assembly .globl foo .p2align 4, 0x90 .type foo, at function foo: # @foo .cfi_startproc # BB#0: # %entry pushq %rbp .Ltmp0: .cfi_def_cfa_offset 16 .Ltmp1: .cfi_offset %rbp, -16 movq %rsp, %rbp .Ltmp2: .cfi_def_cfa_r...

...:** Removing '/Library/Frameworks/ R.framework/Versions/2.1.1/Resources/library/nlme' ** Restoring previous '/Library/Frameworks/R.framework/Versions/2.1.1/ Resources/library/nlme' The downloaded packages are in /private/tmp/RtmpL1j8Sa/downloaded_packages Unknown pseudo-op: .p2align /var/tmp//ccOTBSDa.s:6088:Rest of line ignored. 1st junk character valued 50 (2). /var/tmp//ccOTBSDa.s:6414:Unknown pseudo-op: .p2align /var/tmp//ccOTBSDa.s:6414:Rest of line ignored. 1st junk character valued 50 (2). /var/tmp//ccOTBSDa.s:6608:Unknown pseudo-op: .p2align /var/tmp//ccOTBSDa.s:66...

...ks but isn't optimal. Since we intend to contribute this target back to upstream later on, we'd like to discuss how this should be properly handled. Note that RISC-V also handles alignment as part of relaxation, so it isn't really optional. For example: _start: mv a0, a0 .p2align 2 li a0, 0 The assembler inserts a 3-byte padding (note: this behavior isn't merged yet, see: https://github.com/riscv/riscv-binutils-gdb/pull/88): 00000000 <_start>: 0: 852a mv a0,a0 2: 00 01 00 # R_RISCV_ALIGN...

...I had always thought that it was legal to hoist the load of a global variable outside of the loop as long as it was not declared volatile.... Here is the x86 assembly code generated by gcc 4.5.2. The load of "b" is highlighted: .file "foo.c" .text .p2align 4,,15 .globl foo .type foo, @function foo: * movl b, %ecx* movl $1, %eax movl a, %edx pushl %ebp movl %esp, %ebp .p2align 4,,7 .p2align 3 .L2: addl (%ecx,%eax,4), %edx addl $1, %eax cmpl...

...e same experiment with gcc I get identical code for the two functions: ============================================== _f1:        pushl   %ebp        xorl    %eax, %eax        movl %esp, %ebp        movl    8(%ebp), %edx        testl   %edx, %edx   jle     L5        popl    %ebp        ret        .p2align 4,,7L5:     movl    %edx, %ecx        imull   %edx, %ecx        popl    %ebp     leal    3(%ecx,%ecx,4), %eax        imull   %edx, %eax leal    1(%eax,%ecx,2), %eax        ret        .p2align 4,,15 _f2:         pushl   %ebp        xorl    %eax, %eax        movl    %esp, %ebp        movl    8(%ebp)...

...ough to cause the issue. ----8<--------8<--------8<--------8<--------8<--------8<-------- $ clang --target=arm-linux-gnueabihf -Os -fno-common -S ctor.c \ -o /dev/stdout | grep init_fn $ clang --target=arm-linux-gnueabihf -Os -S ctor.c \ -o /dev/stdout | grep init_fn .p2align 2 @ -- Begin function init_fn .type init_fn,%function .code 32 @ @init_fn init_fn: .size init_fn, .Lfunc_end0-init_fn .long init_fn(target1) .addrsig_sym init_fn $ clang --target=arm-linux-gnueabihf -fno-commo...

...>> here .s file: * the code that i want to ask is in red color.* >>>>> >>>>> .text >>>>> .intel_syntax noprefix >>>>> .file "matn_o3.ll" >>>>> .section .rodata,"a", at progbits >>>>> .p2align 6 >>>>> .LCPI0_0: >>>>> .quad 8 # 0x8 >>>>> .quad 9 # 0x9 >>>>> .quad 10 # 0xa >>>>> .quad 11 # 0xb >>>>> .quad 12...

...nd stores it then once to 'a'. /Jonas int a = 1; void b() {   do     if (a)       a++;   while (a != 0); } bin/clang -O3 -march=z13 -mllvm -unroll-count=1         .text         .file   "testfun.i"         .globl  b                       # -- Begin function b         .p2align        4         .type   b, at function b:                                      # @b # %bb.0:                                # %entry         lrl     %r0, a .LBB0_1:                                # %do.body                                         # =>This Inner Loop Header: Depth=1        ...

...y_fn_idx[] I replace them with __declspec(selectany) , but I'm not sure they have same meanings. some random generated code: .text .intel_syntax noprefix .def call; .scl 2; .type 32; .endef .globl call # -- Begin function call .p2align 4, 0x90 call: # @call .seh_proc call # BB#0: # %entry .p2align 1, 0x90 .Lxray_sled_0: .ascii "\353\t" nop word ptr [rax + rax + 512] sub rsp, 16 .seh_stackalloc 16 .seh_endprologue...

Hi Dimitry, Thanks for your kind response! Thanks for the commit message of Jung's patch, I found that the bug had been fixed in OpenJDK 12 by Zhengyu https://bugs.openjdk.java.net/browse/JDK-8205965 But only backported to 11. So Jung could backport it for OpenJDK 8, thanks a lot! But I argue that the root cause might be in the compiler side, why clang-3.9.1, gcc-6.4.1 couldn't

...lt;--------8<--------8<--------8<--------8<-------- >> $ clang --target=arm-linux-gnueabihf -Os -fno-common -S ctor.c \ >> -o /dev/stdout | grep init_fn >> $ clang --target=arm-linux-gnueabihf -Os -S ctor.c \ >> -o /dev/stdout | grep init_fn >> .p2align 2 @ -- Begin function init_fn >> .type init_fn,%function >> .code 32 @ @init_fn >> init_fn: >> .size init_fn, .Lfunc_end0-init_fn >> .long init_fn(target1) >> .addrsig_sym i...

...ne .LBB0_1 .LBB0_2: # %for.end ret .Ltmp0: .size foo, .Ltmp0-foo .cfi_endproc .section ".note.GNU-stack","", at progbits For comparison, GCC has only one load in the loop: .text .p2align 4,,15 .globl foo .type foo, @function foo: .LFB0: .cfi_startproc xorl %eax, %eax testl %edx, %edx jle .L3 movl (%rdi), %r8d xorl %ecx, %ecx .p2align 4,,10 .p2align 3 .L4: movl (%rsi), %edi...

...mpiled your code (1.c) with LLVM r308173 with the 5 patches applied, and it generated assembly like this. Now it contains store to c(%rip). It tries to store a(%rip) + b(%rip) to c(%rip). I wish this translation is now correct. ``` 73 .globl hoo # -- Begin function hoo 74 .p2align 4, 0x90 75 .type hoo, at function 76 hoo: # @hoo 77 .cfi_startproc 78 # BB#0: 79 movq a(%rip), %rax 80 movq cnt(%rip), %rcx 81 cmpq $0, i_hasval(%rip) 82 sete %sil 83 xorl %edx, %edx 84 .p2align 4, 0x90 85 .LBB1_1:...

On Tue, Dec 13, 2011 at 5:59 AM, Brent Walker <brenthwalker at gmail.com> wrote: > The following seemingly identical functions, get compiled to quite > different machine code.  The first is correctly optimized (the > computation of var y is nicely moved into the else branch of the "if" > statement), which the second one is not (the full computation of var y > is

...B#2: xorl %eax, %eax ret .data .globl _DA # @DA .align 8 _DA: .quad 4599075939470750515 # double 3.000000e-01 .comm _Y,800,3 # @Y .comm _X,800,3 # @X gcc -S -O3 -o test2.s test.c -march=native result: .file "test.c" .text .p2align 4,,15 .globl _f .def _f; .scl 2; .type 32; .endef _f: pushl %ebp movddup _DA, %xmm2 movl %esp, %ebp xorl %eax, %eax .p2align 4,,10 L2: movapd _Y(%eax), %xmm0 movapd _X(%eax), %xmm1 mulpd %xmm2, %xmm1 subpd %xmm1, %xmm0 movapd %xmm0, _Y(%eax) addl $16, %eax cmpl $800, %eax jne L2 xorw...

...t;, "~{rbx}"() #0 ret void } define internal void @foo() #0 { call void asm sideeffect "movl %r14d, %r15d", "~{r15}"() #0 ret void } and its generated assembly code when IPRA enabled: .section __TEXT,__text,regular,pure_instructions .macosx_version_min 10, 12 .p2align 4, 0x90 _foo: ## @foo .cfi_startproc ## BB#0: ## InlineAsm Start movl %r14d, %r15d ## InlineAsm End retq .cfi_endproc .globl _bar .p2align 4, 0x90 _bar: ## @bar .cfi_startproc ## BB#0: pushq %r15 Ltmp0: .cfi_def_cfa_offset 16 push...

...t %esi, -12 movb 16(%ebp), %al movb 12(%ebp), %cl movb 8(%ebp), %dl movl _scscx, %esi movb %dl, (%esi) movl _scscx, %edx movb %cl, 1(%edx) movl _scscx, %ecx movb %al, 2(%ecx) xorl %eax, %eax popl %esi popl %ebp retl .cfi_endproc .comm _pp,3,0 .section __DATA,__data .globl _scscx .p2align 3 _scscx: .long _pp Again, the _scscx is loaded three times instead of reusing a register, which is suboptimal. NOW, if I replace the original code by this: int pp[3]; int *scscx = pp; int tst( int i, int j, int k ) { scscx[0] = i; scscx[1] = j; scscx[2] = k; return 0; } I get the f...

...plied, >> and it generated assembly like this. Now it contains store to c(%rip). >> It tries to store a(%rip) + b(%rip) to c(%rip). I wish this translation is >> now correct. >> >> ``` >> 73 .globl hoo # -- Begin function hoo >> 74 .p2align 4, 0x90 >> 75 .type hoo, at function >> 76 hoo: # @hoo >> 77 .cfi_startproc >> 78 # BB#0: >> 79 movq a(%rip), %rax >> 80 movq cnt(%rip), %rcx >> 81 cmpq $0, i_hasval(%rip) >> 82 sete %sil >> 83...

I'm learning the xray library and try if it can be built on windows, in xray_fdr_logging_impl.h line 152 , comment written as // Using pthread_once(...) to initialize the thread-local data structures but at line 175, 183, code written as thread_local pthread_key_t key; // Ensure that we only actually ever do the pthread initialization once. thread_local bool UNUSED Unused = [] {

...# %for.end > ret > .Ltmp0: > .size foo, .Ltmp0-foo > .cfi_endproc > .section ".note.GNU-stack","", at progbits > > > For comparison, GCC has only one load in the loop: > > .text > .p2align 4,,15 > .globl foo > .type foo, @function > foo: > .LFB0: > .cfi_startproc > xorl %eax, %eax > testl %edx, %edx > jle .L3 > movl (%rdi), %r8d > xorl %ecx, %ecx > .p2align 4,,10 >...