[Bug target/40811] New: unsigned int to float isn't vectorized

[hjl dot tools at gmail dot com]

[hjl@gnu-6 tmp]$ cat x.c
#define N 4
extern unsigned int u4[N] __attribute__ ((aligned(16)));
extern float f4[N] __attribute__ ((aligned(16)));
void
cvt_u4_f4()
{
  int j;
  for (j=0; j<N; j++)
    f4[j]=u4[j];
}
[hjl@gnu-6 tmp]$ /usr/gcc-4.5/bin/gcc -O3  x.c -S  
[hjl@gnu-6 tmp]$ cat x.s
        .file   "x.c"
        .text
        .p2align 4,,15
.globl cvt_u4_f4
        .type   cvt_u4_f4, @function
cvt_u4_f4:
.LFB0:
        .cfi_startproc
        mov     u4(%rip), %eax
        cvtsi2ssq       %rax, %xmm0
        mov     u4+4(%rip), %eax
        movss   %xmm0, f4(%rip)
        cvtsi2ssq       %rax, %xmm0
        mov     u4+8(%rip), %eax
        movss   %xmm0, f4+4(%rip)
        cvtsi2ssq       %rax, %xmm0
        mov     u4+12(%rip), %eax
        movss   %xmm0, f4+8(%rip)
        cvtsi2ssq       %rax, %xmm0
        movss   %xmm0, f4+12(%rip)
        ret
        .cfi_endproc
.LFE0:
        .size   cvt_u4_f4, .-cvt_u4_f4

Icc 11.1 generates:

        .globl cvt_u4_f4
cvt_u4_f4:
..B1.1:                         # Preds ..B1.0
..___tag_value_cvt_u4_f4.1:                                     #6.1
        cvtdq2ps  u4(%rip), %xmm2                               #9.11
        movaps    %xmm2, %xmm1                                  #9.11
        pxor      %xmm0, %xmm0                                  #9.11
        cmpltps   %xmm0, %xmm1                                  #9.11
        andps     _2il0floatpacket.1(%rip), %xmm1               #9.11
        addps     %xmm1, %xmm2                                  #9.11
        movaps    %xmm2, f4(%rip)                               #9.5
        ret                                                     #10.1
        .align    16,0x90
..___tag_value_cvt_u4_f4.2:                                     #
                                # LOE
# mark_end;
        .type   cvt_u4_f4,@function
        .size   cvt_u4_f4,.-cvt_u4_f4
        .data
# -- End  cvt_u4_f4
        .section .rodata, "a"
        .align 16
        .align 16
_2il0floatpacket.1:
        .long   0x4f800000,0x4f800000,0x4f800000,0x4f800000
        .type   _2il0floatpacket.1,@object
        .size   _2il0floatpacket.1,16


-- 
           Summary: unsigned int to float isn't vectorized
           Product: gcc
           Version: 4.5.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: hjl dot tools at gmail dot com


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=40811