search for: bb0_2

...4 addu $gp, $2, $25 sw $7, 76($sp) sw $6, 72($sp) sw $5, 68($sp) lw $3, %got(__stack_chk_guard)($gp) lw $1, 0($3) sw $1, 56($sp) sw $4, 52($sp) sw $zero, 48($sp) // i sw $zero, 44($sp) // val sw $zero, 40($sp) // sum addiu $1, $sp, 68 sw $1, 16($sp) // arg_ptr1 sw $zero, 48($sp) b $BB0_2 addiu $2, $zero, 40 $BB0_1: # in Loop: Header=BB0_2 Depth=1 lw $1, 0($4) // $1 = *arg_ptr sw $1, 44($sp) // val lw $4, 40($sp) // sum addu $1, $4, $1 sw $1, 40($sp) // sum += val lw $1, 48($sp) addiu $1, $1, 1 sw $1, 48($sp) $BB0_2:...

...2($sp) > sw $5, 68($sp) > lw $3, %got(__stack_chk_guard)($gp) > lw $1, 0($3) > sw $1, 56($sp) > sw $4, 52($sp) > sw $zero, 48($sp) // i > sw $zero, 44($sp) // val > sw $zero, 40($sp) // sum > addiu $1, $sp, 68 > sw $1, 16($sp) // arg_ptr1 > sw $zero, 48($sp) > b $BB0_2 > addiu $2, $zero, 40 > $BB0_1: # in Loop: Header=BB0_2 Depth=1 > lw $1, 0($4) // $1 = *arg_ptr > sw $1, 44($sp) // val > lw $4, 40($sp) // sum > addu $1, $4, $1 > sw $1, 40($sp) // sum += val > lw $1, 48($sp) > addiu $1, $1, 1 > sw $1...

...m is not restricted to the NVPTX64 target. Below is a reduced example: __attribute__((global)) void foo(int n, int *output) { for (int i = 0; i < n; i += 3) { output[i] = i * i; } } Without widening, the loop body in the PTX (a low-level assembly-like language generated by NVPTX64) is: BB0_2: // =>This Inner Loop Header: Depth=1 mul.lo.s32 %r5, %r6, %r6; st.u32 [%rd4], %r5; add.s32 %r6, %r6, 3; add.s64 %rd4, %rd4, 12; setp.lt.s32 %p2, %r6, %r3; @%p2 bra BB0_2; in whi...

Which part of the generated code do you think is not correct? Could you be more specific? I compiled this program with clang and ran it on a mips board. It returns the expected result (21). On Tue, Feb 19, 2013 at 4:15 AM, Jonathan <gamma_chen at yahoo.com.tw> wrote: > I check the Mips backend for the following C code fragment compile result. > It seems not correct. Is it my

I check the Mips backend for the following C code fragment compile result. It seems not correct. Is it my misunderstand or it's a bug. //ch8_3.cpp #include <stdarg.h> int sum_i(int amount, ...) { int i = 0; int val = 0; int sum = 0; va_list vl; va_start(vl, amount); for (i = 0; i < amount; i++) { val = va_arg(vl, int); sum += val; } va_end(vl);

...8 swi r3, r19, 24 swi r0, r19, 28 lwi r4, r19, 16 xor r3, r4, r3 lwi r4, r19, 20 or r3, r4, r3 addik r4, r0, 0 addik r5, r0, 1 swi r5, r19, 32 beqid r3, ($BB0_2) swi r4, r19, 36 lwi r3, r19, 36 swi r3, r19, 32 $BB0_2: lwi r3, r19, 32 add r1, r19, r0 lwi r19, r1, 4 rtsd r15, 8 addik r1, r1, 40 .end main Which is very similar to t...

...this snippit: while (n--) *s++ = (char) c; I get this (for the Microblaze): swi r19, r1, 0 add r3, r0, r0 cmp r3, r3, r7 beqid r3, ($BB0_3) brid ($BB0_1) add r19, r1, r0 add r3, r5, r0 $BB0_2: addi r4, r3, 1 addi r7, r7, -1 add r8, r0, r0 sbi r6, r3, 0 cmp r8, r8, r7 bneid r8, ($BB0_2) brid ($BB0_3) add r3, r4, r0 $BB0_3: Notice that the label $BB0_1 is missing. If I disab...

...// these 4 lines is crc >>= 1; // rather poor! } return ~crc; } See <https://godbolt.org/z/eYJeWt> (-O1) and <https://godbolt.org/z/zeExHm> (-O2) crc32be: # @crc32be xor eax, eax test esi, esi jne .LBB0_2 jmp .LBB0_5 .LBB0_4: # in Loop: Header=BB0_2 Depth=1 add rdi, 1 test esi, esi je .LBB0_5 .LBB0_2: # =>This Loop Header: Depth=1 add esi, -1 movzx edx, byte ptr [rdi] shl edx, 24 xor edx, eax mov ecx,...

...oii // BB#0: // %entry cbz w0, .LBB0_5 // BB#1: // %for.body.lr.ph mov w8, wzr cmp w0, #0 // =0 cinc w9, w0, lt asr w9, w9, #1 adrp x10, globalvar .LBB0_2: // %for.body // =>This Inner Loop Header: Depth=1 cmp w8, w9 b.hs .LBB0_4 // BB#3: // %if.then // in Loop: Header=BB0_2 Depth=1...

...+ .LCPI0_6] >>>>> .p2align 4, 0x90 >>>>> .LBB0_1: # %.preheader26 >>>>> # =>This Loop Header: Depth=1 >>>>> # Child Loop BB0_2 Depth 2 >>>>> # Child Loop BB0_3 Depth >>>>> 3 >>>>> # Child Loop BB0_5 Depth >>>>> 3 >>>>> xor r11d, r11d >>>>> .p2a...

...bz w0, .LBB0_5 >> // BB#1: // %for.body.lr.ph >> mov w8, wzr >> cmp w0, #0 // =0 >> cinc w9, w0, lt >> asr w9, w9, #1 >> adrp x10, globalvar >> .LBB0_2: // %for.body >> // =>This Inner Loop Header: Depth=1 >> cmp w8, w9 >> b.hs .LBB0_4 >> // BB#3: // %if.then >>...

...;> } >> return ~crc; >> } >> >> See <https://godbolt.org/z/eYJeWt> (-O1) and <https://godbolt.org/z/zeExHm> >> (-O2) >> >> crc32be: # @crc32be >> xor eax, eax >> test esi, esi >> jne .LBB0_2 >> jmp .LBB0_5 >> .LBB0_4: # in Loop: Header=BB0_2 Depth=1 >> add rdi, 1 >> test esi, esi >> je .LBB0_5 >> .LBB0_2: # =>This Loop Header: Depth=1 >> add esi, -1 >> movzx edx, byte ptr [...

...oii // BB#0:                                // %entry         cbz     w0, .LBB0_5 // BB#1:                                // %for.body.lr.ph         mov      w8, wzr         cmp      w0, #0                 // =0         cinc     w9, w0, lt         asr     w9, w9, #1         adrp    x10, globalvar .LBB0_2:                                // %for.body                                         // =>This Inner Loop Header: Depth=1         cmp      w8, w9         b.hs    .LBB0_4 // BB#3:                                // %if.then                                         //   in Loop: Header=BB0_2 Depth=1...

...l16(memcpy)($17) addiu $16, $fp, 1248 move $4, $16 addiu $6, $zero, 400 jalr $25 move $gp, $17 lw $1, %got($main.b)($17) addiu $5, $1, %lo($main.b) lw $25, %call16(memcpy)($17) addiu $17, $fp, 848 move $4, $17 jalr $25 addiu $6, $zero, 400 sw $zero, 820($fp) sw $zero, 844($fp) addiu $2, $fp, 420 b $BB0_2 addiu $3, $fp, 20 $BB0_1: -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20161015/2da75a6d/attachment.html>

...t; See <https://godbolt.org/z/eYJeWt> (-O1) and < >> https://godbolt.org/z/zeExHm> >> >> (-O2) >> >> >> >> crc32be: # @crc32be >> >> xor eax, eax >> >> test esi, esi >> >> jne .LBB0_2 >> >> jmp .LBB0_5 >> >> .LBB0_4: # in Loop: Header=BB0_2 Depth=1 >> >> add rdi, 1 >> >> test esi, esi >> >> je .LBB0_5 >> >> .LBB0_2: # =>This Loop Header: Depth=1 >> >>...