search for: retl

...t.p.northover at gmail.com> wrote: > Hi Dmitry, > > On 7 October 2014 10:50, Dmitry Borisenkov <d.borisenkov at samsung.com> wrote: >> fpfail.s:26: Error: invalid instruction suffix for `ret' >> >> I downloaded Intel manual and haven’t found any mention of retl instruction, > > "retl" is the AT&T syntax for the normal "ret" instruction in the > Intel manual, which makes it mostly undocumented. Are you sure about that? I don't recall ever seeing retl before. A while back a reference for AT&T was mentioned and, as...

...h %st(1) fucompp fnstsw %ax # kill: AX<def> AX<kill> EAX<def> # kill: AH<def> AH<kill> EAX<kill> sahf sete %al movzbl %al, %eax retl .Ltmp0: .size main, .Ltmp0-main .cfi_endproc .type g, at object # @g .section .rodata,"a", at progbits .globl g .align 8 g: .quad 1 # 0x1 .size g, 8 .section &quot...

On Fri, Sep 5, 2014 at 9:32 AM, Robert Lougher <rob.lougher at gmail.com> wrote: > Unfortunately, another team, while doing internal testing has seen the > new path generating illegal insertps masks. A sample here: > > vinsertps $256, %xmm0, %xmm13, %xmm4 # xmm4 = xmm0[0],xmm13[1,2,3] > vinsertps $256, %xmm1, %xmm0, %xmm6 # xmm6 = xmm1[0],xmm0[1,2,3] >

...- > > test: # @test > vxorps %xmm2, %xmm2, %xmm2 > vmovss %xmm0, %xmm2, %xmm2 > vblendps $4, %xmm0, %xmm2, %xmm0 # xmm0 = xmm2[0,1],xmm0[2],xmm2[3] > vinsertps $48, %xmm1, %xmm0, %xmm0 # xmm0 = xmm0[0,1,2],xmm1[0] > retl > > test2: # @test2 > vinsertps $48, %xmm1, %xmm0, %xmm0 # xmm0 = xmm0[0,1,2],xmm1[0] > vxorps %xmm1, %xmm1, %xmm1 > vblendps $13, %xmm0, %xmm1, %xmm0 # xmm0 = xmm0[0],xmm1[1],xmm0[2,3] > retl > > llc -march=x86-64 -mat...

...# @test >> vxorps %xmm2, %xmm2, %xmm2 >> vmovss %xmm0, %xmm2, %xmm2 >> vblendps $4, %xmm0, %xmm2, %xmm0 # xmm0 = xmm2[0,1],xmm0[2],xmm2[3] >> vinsertps $48, %xmm1, %xmm0, %xmm0 # xmm0 = xmm0[0,1,2],xmm1[0] >> retl >> >> test2: # @test2 >> vinsertps $48, %xmm1, %xmm0, %xmm0 # xmm0 = xmm0[0,1,2],xmm1[0] >> vxorps %xmm1, %xmm1, %xmm1 >> vblendps $13, %xmm0, %xmm1, %xmm0 # xmm0 = xmm0[0],xmm1[1],xmm0[2,3] >> retl >> &...

...but the only thing I can't figure out is how to call these funclets, they look like: Catch: "?catch$3@?0?m3 at 4HA": LBB4_3: # %BasicBlock26 pushl %ebp pushl %eax addl $12, %ebp movl %esp, -28(%ebp) movl $LBB4_5, %eax addl $4, %esp popl %ebp retl # CATCHRET cleanup: "?dtor$2@?0?m2 at 4HA": LBB3_2: pushl %ebp subl $8, %esp addl $12, %ebp movl %ebp, %eax movl %esp, %ecx movl %eax, 4(%ecx) movl $1, (%ecx) calll m2$Fin addl $8, %esp popl %ebp retl # CLEANUPRET What d...

...4]: + * they return the two file descriptors in %o0 and %o1. + */ + +#include <asm/unistd.h> + + .globl pipe + .type pipe,#function + .align 4 +pipe: + mov __NR_pipe, %g1 + or %o0, 0, %g4 + t 0x6d + bcc %xcc, 1f + nop + sethi %hi(errno), %g4 + or %g4, %lo(errno), %g4 + st %o0,[%g4] + retl + mov -1, %o0 +1: + st %o0,[%g4] + st %o1,[%g4+4] + retl + mov 0, %o0 + + .size pipe,.-pipe diff --git a/usr/klibc/arch/sparc64/setjmp.S b/usr/klibc/arch/sparc64/setjmp.S new file mode 100644 index 0000000..75a6a68 --- /dev/null +++ b/usr/klibc/arch/sparc64/setjmp.S @@ -0,0 +1,55 @@ +! +! setjm...

...# @test >>> vxorps %xmm2, %xmm2, %xmm2 >>> vmovss %xmm0, %xmm2, %xmm2 >>> vblendps $4, %xmm0, %xmm2, %xmm0 # xmm0 = xmm2[0,1],xmm0[2],xmm2[3] >>> vinsertps $48, %xmm1, %xmm0, %xmm0 # xmm0 = xmm0[0,1,2],xmm1[0] >>> retl >>> >>> test2: # @test2 >>> vinsertps $48, %xmm1, %xmm0, %xmm0 # xmm0 = xmm0[0,1,2],xmm1[0] >>> vxorps %xmm1, %xmm1, %xmm1 >>> vblendps $13, %xmm0, %xmm1, %xmm0 # xmm0 = xmm0[0],xmm1[1],xmm0[2,3] >&g...

...option to clang. The main caveats to bear in mind for 16-bit code which was previously built with gcc/gas are: • We do not support the explicit 'data32' and 'addr32' prefixes in asm. The data32 prefix is almost never needed. If you use the correct suffix on an instruction (retl vs. retw, for example), then you should never need to use 'data32'. The addr32 prefix *is* needed by GNU binutils, because *even* when given an explicit address which is greater than 64KiB, it'll just give you a warning about truncation, and emit the instruction with a 1...

...file descriptors in %o0 and %o1. */ +#include <machine/asm.h> #include <asm/unistd.h> .globl pipe @@ -15,9 +16,8 @@ pipe: or %o0, 0, %g4 t 0x10 bcc 1f - nop - sethi %hi(errno), %g4 - or %g4, %lo(errno), %g4 + PIC_PROLOGUE(%g1,%g4) + SET(errno,%g1,%g4) st %o0,[%g4] retl mov -1, %o0 diff --git a/usr/klibc/arch/sparc/syscall.S b/usr/klibc/arch/sparc/syscall.S index c0273f77..52a8583b 100644 --- a/usr/klibc/arch/sparc/syscall.S +++ b/usr/klibc/arch/sparc/syscall.S @@ -4,14 +4,16 @@ * Common system-call stub; %g1 already set to syscall number */ +#include &l...

...ebp, -8 movl %esp, %ebp .cfi_def_cfa_register %ebp pushl %esi .cfi_offset %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...

...# @main # BB#0: subl $28, %esp leal 20(%esp), %eax movl %eax, 8(%esp) leal 24(%esp), %eax movl %eax, 4(%esp) movl $.L.str, (%esp) calll __isoc99_scanf movl 20(%esp), %eax * orl 24(%esp), %eax* addl $28, %esp retl As seen, optimization happened at IR level itself reflected in .s file. *GCC output for the same:* suyog at suyog-Inspiron-N5010:~$ gcc -S -O2 1.c main: .LFB23: .cfi_startproc pushl %ebp .cfi_def_cfa_offset 8 .cfi_offset 5, -8 movl %esp, %ebp .cfi_def_cfa_register...

...hey return the two file descriptors in %o0 and %o1. */ +#include <machine/asm.h> #include <asm/unistd.h> .globl pipe @@ -16,8 +17,8 @@ pipe: t 0x10 bcc 1f nop - sethi %hi(errno), %g4 - or %g4, %lo(errno), %g4 + PIC_PROLOGUE(%g1,%g4) + SET(errno,%g1,%g4) st %o0,[%g4] retl mov -1, %o0 diff --git a/usr/klibc/arch/sparc/syscall.S b/usr/klibc/arch/sparc/syscall.S index c0273f7..52a8583 100644 --- a/usr/klibc/arch/sparc/syscall.S +++ b/usr/klibc/arch/sparc/syscall.S @@ -4,14 +4,16 @@ * Common system-call stub; %g1 already set to syscall number */ +#include <...

...file format COFF-i386 Disassembly of section .text: 0000000000000000 _main: 0: 68 00 00 00 00 pushl $0 5: e8 00 00 00 00 calll 0 <_main+0xa> a: 83 c4 04 addl $4, %esp d: 33 c0 xorl %eax, %eax f: c3 retl Thanks, Paul -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20190928/0cdd87a2/attachment.html>

...at trillian:~$ cat ./test.s .text .align 16 .globl main .type main, #function main: save %o6, -96, %o6 sethi %hi(.str), %l0 add %l0, %lo(.str), %o0 call puts nop sethi 0, %i0 restore %g0, %g0, %g0 retl nop .section .rodata.str1.1,"aMS", at progbits,1 .align 2 .type .str,#object .size .str,15 .str: .asciz "this is a test" sakharov at trillian:~$ /opt/SUNWspro/bin/cc test.s -o test /opt/SUNWspro/prod/bin/fbe: "tes...

On Sun, Aug 5, 2018 at 5:49 PM, Dimitry Andric <dimitry at andric.com> wrote: > On 3 Aug 2018, at 13:37, Hans Wennborg via Release-testers <release-testers at lists.llvm.org> wrote: >> >> 7.0.0-rc1 was just tagged (from the branch at r338847). >> >> It's early in the release process, but I'd like to find out what the >> status is of the branch

..._bar: subl $32, %esp movl $1, %eax movl $2, %ecx movl $1, (%esp) movl $2, 4(%esp) movl %eax, 28(%esp) movl %ecx, 24(%esp) calll _foo movl $3, %ecx movl $4, %edx movl $3, (%esp) movl $4, 4(%esp) movl %eax, 20(%esp) movl %ecx, 16(%esp) movl %edx, 12(%esp) calll _foo movl %eax, 8(%esp) addl $32, %esp retl Note how the constants are stored in registers but when saving the parameters on the stack for the call the immediate values are used. The registers are still stored on the stack probably because it's the caller's responsibility once they were used (which seems expected). I think the probl...

...%ecx, 24(%esp) >> calll _foo >> movl $3, %ecx >> movl $4, %edx >> movl $3, (%esp) >> movl $4, 4(%esp) >> movl %eax, 20(%esp) >> movl %ecx, 16(%esp) >> movl %edx, 12(%esp) >> calll _foo >> movl %eax, 8(%esp) >> addl $32, %esp >> retl >> >> Note how the constants are stored in registers but when saving the >> parameters on the stack for the call the immediate values are used. The >> registers are still stored on the stack probably because it's the caller's >> responsibility once they were us...

Hello! Can someone please help me in building debug version of klibc ? I've cloned git://git.kernel.org/pub/scm/libs/klibc/klibc.git , but failed to build it with debug info added "-g" to HOSTCFLAGS in Makefile, but $ make -j KLIBCKERNELSRC=`pwd`/../linux-2.6/usr still strips every debug symbol , and i'm failed to change scripts/Kbuild.klibc and Makefile to remove strip

...24(%esp), %eax >>>> movl %eax, 4(%esp) >>>> movl $.L.str, (%esp) >>>> calll __isoc99_scanf >>>> movl 20(%esp), %eax >>>> * orl 24(%esp), %eax* >>>> addl $28, %esp >>>> retl >>>> >>>> As seen, optimization happened at IR level itself reflected in .s file. >>>> >>>> *GCC output for the same:* >>>> >>>> suyog at suyog-Inspiron-N5010:~$ gcc -S -O2 1.c >>>> >>>> main: >>&g...