[Bug tree-optimization/18562] New: SSE constant vector initialization produces dead constant values on stack

[uros at gcc dot gnu dot org]

Compiling this testcase with '-O2 -msse' an unoptimal code is produced. 'val1'
is merged into vector at compile time, but it is still loaded onto stack. Gcc
does not detect that 'val1' value on stack is sitting there unused.

#include <xmmintrin.h>
#include <stdio.h>

int main(void) {
        float val1 = 1.3f;
        float result[4];
        __m128 A;

        A = _mm_load1_ps(&val1);
        _mm_storeu_ps(result, A);

        printf("%f %f %f %f\n", result[0], result[1], result[2], result[3]);
        return 0;
}

This code is produced:
...
.LC2:                       <- merged vector
        .long   1067869798
        .long   0
        .long   0
        .long   0
        .text
        .p2align 4,,15
.globl main
        .type   main, @function
main:
        pushl   %ebp
        movl    %esp, %ebp
        subl    $72, %esp
        movss   .LC2, %xmm0           <- vector is loaded into %xmm0
        andl    $-16, %esp
        subl    $16, %esp
        movl    $0x3fa66666, -4(%ebp) <- 'val1' is put on stack here
        shufps  $0, %xmm0, %xmm0
        movl    $.LC1, (%esp)
        movups  %xmm0, -20(%ebp)
        flds    -8(%ebp)
        fstpl   28(%esp)
        flds    -12(%ebp)
        fstpl   20(%esp)
        flds    -16(%ebp)
        fstpl   12(%esp)
        flds    -20(%ebp)
        fstpl   4(%esp)
        call    printf
        xorl    %eax, %eax
        leave
        ret

Even worser situation arises with:

int main(void) {
        float val1[4] = {1.3f, 1.4f, 1.5f, 1.6f};
        float result[4];
        __m128 A;

        A = _mm_loadu_ps(val1);
        _mm_storeu_ps(result, A);

        printf("%f %f %f %f\n", result[0], result[1], result[2], result[3]);
        return 0;

Following asm code is produced:
main:
        pushl   %ebp
        movl    %esp, %ebp
        subl    $72, %esp
        andl    $-16, %esp
        movl    $0x3fa66666, -16(%ebp)
        subl    $16, %esp
        movl    $0x3fb33333, -12(%ebp)
        movl    $0x3fc00000, -8(%ebp)
        movl    $0x3fcccccd, -4(%ebp)
        movups  -16(%ebp), %xmm0
        movups  %xmm0, -32(%ebp)
        flds    -20(%ebp)
        fstpl   28(%esp)
        flds    -24(%ebp)
        fstpl   20(%esp)
        flds    -28(%ebp)
        fstpl   12(%esp)
        flds    -32(%ebp)
        fstpl   4(%esp)
        movl    $.LC4, (%esp)
        call    printf
        xorl    %eax, %eax
        leave
        ret

The constant values are not merged into vector at compile time, the vector is
built on the stack and then loaded into %xmm register. Value on stack is again
left unused after vector initialization.

Uros.

-- 
           Summary: SSE constant vector initialization produces dead
                    constant values on stack
           Product: gcc
           Version: 4.0.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P2
         Component: tree-optimization
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: uros at gcc dot gnu dot org
                CC: gcc-bugs at gcc dot gnu dot org
 GCC build triplet: i686-pc-linux-gnu
  GCC host triplet: i686-pc-linux-gnu
GCC target triplet: i686-pc-linux-gnu


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=18562