search for: cmpq

...gument registers are clobbered. */ - call *sys_call_table(, %rax, 8) + call *(%r11, %rax, 8) .Lentry_SYSCALL_64_after_fastpath_call: movq %rax, RAX(%rsp) @@ -334,7 +337,8 @@ ENTRY(stub_ptregs_64) * RAX stores a pointer to the C function implementing the syscall. * IRQs are on. */ - cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) + leaq .Lentry_SYSCALL_64_after_fastpath_call(%rip), %r11 + cmpq %r11, (%rsp) jne 1f /* @@ -1172,7 +1176,8 @@ ENTRY(error_entry) movl %ecx, %eax /* zero extend */ cmpq %rax, RIP+8(%rsp) je .Lbstep_iret - cmpq $.Lgs_change, RIP+8(%rsp) +...

...8) >> .Lentry_SYSCALL_64_after_fastpath_call: >> >> movq %rax, RAX(%rsp) >> @@ -334,7 +337,8 @@ ENTRY(stub_ptregs_64) >> * RAX stores a pointer to the C function implementing the syscall. >> * IRQs are on. >> */ >> - cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) >> + leaq .Lentry_SYSCALL_64_after_fastpath_call(%rip), %r11 >> + cmpq %r11, (%rsp) >> jne 1f >> >> /* >> @@ -1172,7 +1176,8 @@ ENTRY(error_entry) >> movl %ecx, %eax...

...8) >> .Lentry_SYSCALL_64_after_fastpath_call: >> >> movq %rax, RAX(%rsp) >> @@ -334,7 +337,8 @@ ENTRY(stub_ptregs_64) >> * RAX stores a pointer to the C function implementing the syscall. >> * IRQs are on. >> */ >> - cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) >> + leaq .Lentry_SYSCALL_64_after_fastpath_call(%rip), %r11 >> + cmpq %r11, (%rsp) >> jne 1f >> >> /* >> @@ -1172,7 +1176,8 @@ ENTRY(error_entry) >> movl %ecx, %eax...

...xCA5FCA5FCA5FCA5F, %rbp movabsq $0xCA5FCA5FCA5FCA5F, %rbx # can also be movq %rbp, %rbx etc. movabsq $0xCA5FCA5FCA5FCA5F, %r12 movabsq $0xCA5FCA5FCA5FCA5F, %r13 movabsq $0xCA5FCA5FCA5FCA5F, %r14 movabsq $0xCA5FCA5FCA5FCA5F, %r15 callq foo movabsq $0xCA5FCA5FCA5FCA5F, %rax cmpq %rax, %rbp jne .LBB1_5 movabsq $0xCA5FCA5FCA5FCA5F, %rax cmpq %rax, %rbx jne .LBB1_5 movabsq $0xCA5FCA5FCA5FCA5F, %rax cmpq %rax, %r12 jne .LBB1_5 movabsq $0xCA5FCA5FCA5FCA5F, %rax cmpq %rax, %r13 jne .LBB1_5 movabsq $0xCA5FCA5FCA5FCA5F,...

...*sys_call_table(, %rax, 8) > + call *(%r11, %rax, 8) > .Lentry_SYSCALL_64_after_fastpath_call: > > movq %rax, RAX(%rsp) > @@ -334,7 +337,8 @@ ENTRY(stub_ptregs_64) > * RAX stores a pointer to the C function implementing the syscall. > * IRQs are on. > */ > - cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) > + leaq .Lentry_SYSCALL_64_after_fastpath_call(%rip), %r11 > + cmpq %r11, (%rsp) > jne 1f > > /* > @@ -1172,7 +1176,8 @@ ENTRY(error_entry) > movl %ecx, %eax /* zero extend */ > cmpq %rax, RIP+8(%rsp) > je .Lb...

...cify the preferred branch, correct ? I see nothing in the specs for "branch" or "switch". And __buildin_expect does nothing, that I am sure of. Unfortunately llvm has this knack for ordering my one most crucial part of code exactly the opposite I want to, it does: (x86_64) cmpq %r15, (%rax,%rdx) jne LBB0_3 Ltmp18: leaq 8(%rax,%rdx), %rcx jmp LBB0_4 LBB0_3: addq $8, %rcx LBB0_4: when I want, cmpq %r15, (%rax,%rdx) jeq LBB0_3 addq $8, %rcx jmp LBB0_4 LBB0_3: leaq 8(%rax,%rdx), %rcx LBB0_4: since that saves me executing a jump 99.9% of the time. Is there anyt...

...---- compiled with gcc 4.9.1 and clang 3.5 with clang3.5 + #define ITER the_func contains masses of code the code in main is also sometimes different (not just inlined) to the_func clang -DITER -O2 clang -DITER -O3 gives: the_func: leaq 12(%rdi), %rcx leaq 4(%rdi), %rax cmpq %rax, %rcx cmovaq %rcx, %rax movq %rdi, %rsi notq %rsi addq %rax, %rsi shrq $2, %rsi incq %rsi xorl %edx, %edx movabsq $9223372036854775800, %rax # imm = 0x7FFFFFFFFFFFFFF8 andq %rsi, %rax pxor %xmm0, %xmm0...

...oline) * spill RDI and restore it in a second-stage trampoline. */ pushq %rdi - movq $entry_SYSCALL_64_stage2, %rdi + movabsq $entry_SYSCALL_64_stage2, %rdi JMP_NOSPEC %rdi END(entry_SYSCALL_64_trampoline) @@ -1275,7 +1275,8 @@ ENTRY(error_entry) movl %ecx, %eax /* zero extend */ cmpq %rax, RIP+8(%rsp) je .Lbstep_iret - cmpq $.Lgs_change, RIP+8(%rsp) + leaq .Lgs_change(%rip), %rcx + cmpq %rcx, RIP+8(%rsp) jne .Lerror_entry_done /* @@ -1480,10 +1481,10 @@ ENTRY(nmi) * resume the outer NMI. */ - movq $repeat_nmi, %rdx + leaq repeat_nmi(%rip), %rdx cmpq 8(%rsp), %...

...%rbx # can also be movq %rbp, %rbx etc. > > movabsq $0xCA5FCA5FCA5FCA5F, %r12 > > movabsq $0xCA5FCA5FCA5FCA5F, %r13 > > movabsq $0xCA5FCA5FCA5FCA5F, %r14 > > movabsq $0xCA5FCA5FCA5FCA5F, %r15 > > callq foo > > movabsq $0xCA5FCA5FCA5FCA5F, %rax > > cmpq %rax, %rbp > > jne .LBB1_5 > > movabsq $0xCA5FCA5FCA5FCA5F, %rax > > cmpq %rax, %rbx > > jne .LBB1_5 > > movabsq $0xCA5FCA5FCA5FCA5F, %rax > > cmpq %rax, %r12 > > jne .LBB1_5 > > movabsq $0xCA5FCA5FCA5FCA5F, %rax > >...

> cmpq %rbx, %r14 > jne .LBB0_1 > > LLVM can perform compare-jump fusion, it already does in certain cases, but > not in the case above. We can remove the cmp above if we were to perform > the following transformation: Do you mean branch-fusion (https://en.wikichip.org/wiki/macro-operati...

...workarea/llvm-r318298/dbuild/bin/llc .cfi_startproc # BB#0: # %entry pushq %rax .cfi_def_cfa_offset 16 movl $i, %eax .p2align 4, 0x90 .LBB0_1: # %while.cond # =>This Inner Loop Header: Depth=1 cmpq %rax, %rsi ja .LBB0_4 # BB#2: # %while.body # in Loop: Header=BB0_1 Depth=1 movq (%rdi), %rcx movq %rcx, (%rsi) movq 8(%rdi), %rcx movq %rcx, (%rsi) addq $6, %rdi addq $6, %rsi cmpq %rdx, %rsi jb .LBB0_1 # BB#3:...

...Example which can be optimized via cmp/jmp fusion. // clang -O3 -S test.c extern void g(int); void f(int *p, long long n) { do { g(*p++); } while (--n); } LLVM currently generates the following sequence for x86_64 targets: LBB0_1: movl (%r15,%rbx,4), %edi callq g addq $1, %rbx cmpq %rbx, %r14 jne .LBB0_1 LLVM can perform compare-jump fusion, it already does in certain cases, but not in the case above. We can remove the cmp above if we were to perform the following transformation: 1.0) Initialize the induction variable, %rbx, to be 'n' instead of zero. 1.1) Negate t...

I was able to get the loop to increment from -999 to 0 using IR directly. That got rid of the cmpq. The carry i was after was able to be obtained using the intrinsic @llvm.uadd.with.overflow.i64, however there is no way to add with carry and have it realise that the resulting *carry out* cannot exceed 1. It actually writes the carry to a byte, and then uses logical operations on it, which slows...

...# %entry >> pushq %rax >> .cfi_def_cfa_offset 16 >> movl $i, %eax >> .p2align 4, 0x90 >> .LBB0_1: # %while.cond >> # =>This Inner Loop Header: >> Depth=1 >> cmpq %rax, %rsi >> ja .LBB0_4 >> # BB#2: # %while.body >> # in Loop: Header=BB0_1 Depth=1 >> movq (%rdi), %rcx >> movq %rcx, (%rsi) >> movq 8(%rdi), %rcx >> movq %rcx, (%rsi) >> addq...

...of this form: > > .text > .align 8 > .long Main_main1_srt-(Main_main1_info)+0 > .long 0 > .quad 4294967299 > .quad 0 > .quad 270582939663 > .globl Main_main1_info > .type Main_main1_info, @object > Main_main1_info: > .Lc1Df: > leaq -8(%rbp),%rax > cmpq %r15,%rax > jb .Lc1Dh Ok. I'd strongly recommend the approach of generating the table inside the prolog of the function. This means you'd get something like this: .text .align 8 .globl Main_main1_info .type Main_main1_info, @object Main_main1_info: .Lc1Df: jmp .Ltmp .long Main_ma...

...8 >> .long Main_main1_srt-(Main_main1_info)+0 >> .long 0 >> .quad 4294967299 >> .quad 0 >> .quad 270582939663 >> .globl Main_main1_info >> .type Main_main1_info, @object >> Main_main1_info: >> .Lc1Df: >> leaq -8(%rbp),%rax >> cmpq %r15,%rax >> jb .Lc1Dh > > Ok. I'd strongly recommend the approach of generating the table inside the prolog of the function. This means you'd get something like this: > This is starting to look very similar to how ARM constant islands work, without the extra ugliness f...

...feedback. Ciao Nat! P.S. In case someone is interested, here is the assembler code and the IR that produced it. Relevant LLVM generated x86_64 assembler portion with -Os ~~~ testq %r12, %r12 je LBB0_5 ## BB#1: movq -8(%r12), %rcx movq (%rcx), %rax movq -8(%rax), %rdx andq %r15, %rdx cmpq %r15, (%rax,%rdx) je LBB0_2 ## BB#3: addq $8, %rcx jmp LBB0_4 LBB0_2: leaq 8(%rdx,%rax), %rcx LBB0_4: movq %r12, %rdi movq %r15, %rsi movq %r14, %rdx callq *(%rcx) movq %rax, %rbx LBB0_5: ~~~ Better/tighter assembler code would be (saves 2 instructions, one jump less) ~~~ testq %r12, %r1...

...eapObjects#InfoTables With TNTC enabled we generate code for closures of this form: .text .align 8 .long Main_main1_srt-(Main_main1_info)+0 .long 0 .quad 4294967299 .quad 0 .quad 270582939663 .globl Main_main1_info .type Main_main1_info, @object Main_main1_info: .Lc1Df: leaq -8(%rbp),%rax cmpq %r15,%rax jb .Lc1Dh [...] .data .globl Main_main1_closure .type Main_main1_closure, @object Main_main1_closure: .quad Main_main1_info .quad 0 Without TNTC we instead generated code of this form: .text .globl Main_main1_entry .type Main_main1_entry, @function Main_main1_entry: .LFB15: lea...

...ip). 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: # =>This Inner Loop Header: Depth=1 86 testb $1, %sil 87 je .LBB1_3 88 # BB#2: # in Loop: Header=BB1_1 Depth=1 89 movq b(%rip), %r...

...ision arithmetic to add-with-carry or subtract-with-borrow through i65/i33. That would remove the need for the overflow intrinsics entirely. Alistair On 13 Jun 2010, at 02:27, Bill Hart wrote: > I was able to get the loop to increment from -999 to 0 using IR > directly. That got rid of the cmpq. > > The carry i was after was able to be obtained using the intrinsic > @llvm.uadd.with.overflow.i64, however there is no way to add with > carry and have it realise that the resulting *carry out* cannot exceed > 1. It actually writes the carry to a byte, and then uses logical >...