[llvm-bugs] [Bug 28372] New: avx512 JIT backend generates wrong code on <4 x float>

[via llvm-bugs]

https://llvm.org/bugs/show_bug.cgi?id=28372

            Bug ID: 28372
           Summary: avx512 JIT backend generates wrong code on <4 x float>
           Product: tools
           Version: trunk
          Hardware: PC
                OS: Linux
            Status: NEW
          Severity: release blocker
          Priority: P
         Component: lli
          Assignee: unassignedbugs at nondot.org
          Reporter: fwinter at jlab.org
                CC: llvm-bugs at lists.llvm.org
    Classification: Unclassified

Created attachment 16658
  --> https://llvm.org/bugs/attachment.cgi?id=16658&action=edit
exploit program

When compiling the attached module with the JIT engine on an Intel KNL I see
wrong code getting emitted. I attach a complete exploit program which shows the
bug in LLVM trunk. It loads and JIT compiles the module and prints the
assembler. I stumbled on this since the result of an actual calculation was
wrong. So, it's not only the text version of the assembler also the machine
assembler is wrong.

When I execute the exploit program on an Intel KNL the following output is
produced:

CPU name = knl
-sse4a,-avx512bw,cx16,-tbm,xsave,-fma4,-avx512vl,prfchw,bmi2,adx,-xsavec,fsgsbase,avx,avx512cd,avx512pf,-rtm,popcnt,fma,bmi,aes,rdrnd,-xsaves,sse4.1,sse4.2,avx2,avx512er,sse,lzcnt,pclmul,avx512f,f16c,ssse3,mmx,-pku,cmov,-xop,rdseed,movbe,-hle,xsaveopt,-sha,sse2,sse3,-avx512dq,
Assembly:
    .text
    .file    "module_KFxOBX_i4_after.ll"
    .globl    adjmul
    .align    16, 0x90
    .type    adjmul, at function
adjmul:
    .cfi_startproc
    leaq    (%rdi,%r8), %rdx
    addq    %rsi, %r8
    testb    $1, %cl
    cmoveq    %rdi, %rdx
    cmoveq    %rsi, %r8
    movq    %rdx, %rax
    sarq    $63, %rax
    shrq    $62, %rax
    addq    %rdx, %rax
    sarq    $2, %rax
    movq    %r8, %rcx
    sarq    $63, %rcx
    shrq    $62, %rcx
    addq    %r8, %rcx
    sarq    $2, %rcx
    movq    %rax, %rdx
    shlq    $5, %rdx
    leaq    16(%r9,%rdx), %rsi
    orq    $16, %rdx
    movq    16(%rsp), %rdi
    addq    %rdx, %rdi
    addq    8(%rsp), %rdx
    .align    16, 0x90
.LBB0_1:
    vmovaps    -16(%rdx), %xmm0
    vmovaps    (%rdx), %xmm1
    vmovaps    -16(%rdi), %xmm2
    vmovaps    (%rdi), %xmm3
    vmulps    %xmm3, %xmm1, %xmm4
    vmulps    %xmm2, %xmm1, %xmm1
    vfmadd213ss    %xmm4, %xmm0, %xmm2
    vfmsub213ss    %xmm1, %xmm0, %xmm3
    vmovaps    %xmm2, -16(%rsi)
    vmovaps    %xmm3, (%rsi)
    addq    $1, %rax
    addq    $32, %rsi
    addq    $32, %rdi
    addq    $32, %rdx
    cmpq    %rcx, %rax
    jl    .LBB0_1
    retq
.Lfunc_end0:
    .size    adjmul, .Lfunc_end0-adjmul
    .cfi_endproc


    .section    ".note.GNU-stack","", at progbits

end assembly!


The instructions 'vfmadd213ss' are 'Fused Multiply-Add of Scalar
Single-Precision Floating-Point'. Those should be SIMD vector instructions.
Note that the KNL has 16 wide float SIMD, while the exploit module uses only 4.
However, the backend should be able to handle this.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20160630/3aeecba7/attachment-0001.html>