[llvm-bugs] [Bug 32077] New: Missing optimisation: Type conversion not vectorised in simple additive reduction

[via llvm-bugs]

https://bugs.llvm.org/show_bug.cgi?id=32077

            Bug ID: 32077
           Summary: Missing optimisation: Type conversion not vectorised
                    in simple additive reduction
           Product: new-bugs
           Version: trunk
          Hardware: PC
                OS: Linux
            Status: NEW
          Severity: enhancement
          Priority: P
         Component: new bugs
          Assignee: unassignedbugs at nondot.org
          Reporter: drraph at gmail.com
                CC: llvm-bugs at lists.llvm.org

Consider:

double f(double x[]) {
  float p = 1.0;
  for (int i = 0; i < 16; i++)
    p += x[i];
  return p;
}

clang/llvm with -O3 -march=core-avx2 -ffast-math gives:

.LCPI0_0:
        .quad   4607182418800017408     # double 1
f:                                      # @f
        vmovsd  xmm0, qword ptr [rdi]   # xmm0 = mem[0],zero
        vaddsd  xmm0, xmm0, qword ptr [rip + .LCPI0_0]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 8]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 16]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 24]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 32]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 40]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 48]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 56]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 64]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 72]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 80]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 88]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 96]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 104]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 112]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        vaddsd  xmm0, xmm0, qword ptr [rdi + 120]
        vcvtsd2ss       xmm0, xmm0, xmm0
        vcvtss2sd       xmm0, xmm0, xmm0
        ret


However more efficient would be:

f:
        vcvtpd2ps xmm0, YMMWORD PTR [rdi]                       #4.5
        vcvtpd2ps xmm1, YMMWORD PTR [32+rdi]                    #4.5
        vcvtpd2ps xmm2, YMMWORD PTR [64+rdi]                    #4.5
        vcvtpd2ps xmm3, YMMWORD PTR [96+rdi]                    #4.5
        vaddps    xmm4, xmm0, xmm1                              #2.11
        vaddps    xmm5, xmm2, xmm3                              #2.11
        vaddps    xmm6, xmm4, xmm5                              #2.11
        vmovhlps  xmm7, xmm6, xmm6                              #2.11
        vaddps    xmm8, xmm6, xmm7                              #2.11
        vshufps   xmm9, xmm8, xmm8, 245                         #2.11
        vaddss    xmm10, xmm8, xmm9                             #2.11
        vaddss    xmm0, xmm10, DWORD PTR .L_2il0floatpacket.0[rip] #2.11
        vcvtss2sd xmm0, xmm0, xmm0                              #5.10
        vzeroupper                                              #5.10
        ret                                                     #5.10
.L_2il0floatpacket.0:
        .long   0x3f800000

-- 
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/20170227/4534e2c3/attachment.html>