i386: Add STV support for DImode and SImode rotations by constant.

This patch implements scalar-to-vector (STV) support for DImode and SImode
rotations by constant bit counts.  Scalar rotations are almost always
optimal on x86, requiring only one or two instructions, but it is also
possible to implement these efficiently with SSE2, requiring only one
or two instructions for SImode rotations and at most 3 instructions for
DImode rotations.  This allows GCC to STV rotations with a small or no
penalty if there are other (net) benefits to converting a chain.  An
example of the benefits is shown below, which is based upon the BLAKE2
cryptographic hash function:

unsigned long long a,b,c,d;

unsigned long rot(unsigned long long x, int y)
{
  return (x<<y) | (x>>(64-y));
}

void foo()
{
  d = rot(d ^ a,32);
  c = c + d;
  b = rot(b ^ c,24);
  a = a + b;
  d = rot(d ^ a,16);
  c = c + d;
  b = rot(b ^ c,63);
}

where with -m32 -O2 -msse2

Before (59 insns, 247 bytes):

foo:	pushl   %edi
        xorl    %edx, %edx
        pushl   %esi
        pushl   %ebx
        subl    $16, %esp
        movq    a, %xmm1
        movq    d, %xmm0
        movq    b, %xmm2
        pxor    %xmm1, %xmm0
        psrlq   $32, %xmm0
        movd    %xmm0, %eax
        movd    %edx, %xmm0
        movd    %eax, %xmm3
        punpckldq       %xmm0, %xmm3
        movq    c, %xmm0
        paddq   %xmm3, %xmm0
        pxor    %xmm0, %xmm2
        movd    %xmm2, %ecx
        psrlq   $32, %xmm2
        movd    %xmm2, %ebx
        movl    %ecx, %eax
        shldl   $24, %ebx, %ecx
        shldl   $24, %eax, %ebx
        movd    %ebx, %xmm4
        movd    %ecx, %xmm2
        punpckldq       %xmm4, %xmm2
        movdqa  .LC0, %xmm4
        pand    %xmm4, %xmm2
        paddq   %xmm2, %xmm1
        movq    %xmm1, a
        pxor    %xmm3, %xmm1
        movd    %xmm1, %esi
        psrlq   $32, %xmm1
        movd    %xmm1, %edi
        movl    %esi, %eax
        shldl   $16, %edi, %esi
        shldl   $16, %eax, %edi
        movd    %esi, %xmm1
        movd    %edi, %xmm3
        punpckldq       %xmm3, %xmm1
        pand    %xmm4, %xmm1
        movq    %xmm1, d
        paddq   %xmm1, %xmm0
        movq    %xmm0, c
        pxor    %xmm2, %xmm0
        movd    %xmm0, 8(%esp)
        psrlq   $32, %xmm0
        movl    8(%esp), %eax
        movd    %xmm0, 12(%esp)
        movl    12(%esp), %edx
        shrdl   $1, %edx, %eax
        xorl    %edx, %edx
        movl    %eax, b
        movl    %edx, b+4
        addl    $16, %esp
        popl    %ebx
        popl    %esi
        popl    %edi
        ret

After (32 insns, 165 bytes):
        movq    a, %xmm1
        xorl    %edx, %edx
        movq    d, %xmm0
        movq    b, %xmm2
        movdqa  .LC0, %xmm4
        pxor    %xmm1, %xmm0
        psrlq   $32, %xmm0
        movd    %xmm0, %eax
        movd    %edx, %xmm0
        movd    %eax, %xmm3
        punpckldq       %xmm0, %xmm3
        movq    c, %xmm0
        paddq   %xmm3, %xmm0
        pxor    %xmm0, %xmm2
        pshufd  $68, %xmm2, %xmm2
        psrldq  $5, %xmm2
        pand    %xmm4, %xmm2
        paddq   %xmm2, %xmm1
        movq    %xmm1, a
        pxor    %xmm3, %xmm1
        pshuflw $147, %xmm1, %xmm1
        pand    %xmm4, %xmm1
        movq    %xmm1, d
        paddq   %xmm1, %xmm0
        movq    %xmm0, c
        pxor    %xmm2, %xmm0
        pshufd  $20, %xmm0, %xmm0
        psrlq   $1, %xmm0
        pshufd  $136, %xmm0, %xmm0
        pand    %xmm4, %xmm0
        movq    %xmm0, b
        ret

2023-07-01  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog
	* config/i386/i386-features.cc (compute_convert_gain): Provide
	gains/costs for ROTATE and ROTATERT (by an integer constant).
	(general_scalar_chain::convert_rotate): New helper function to
	convert a DImode or SImode rotation by an integer constant into
	SSE vector form.
	(general_scalar_chain::convert_insn): Call the new convert_rotate
	for ROTATE and ROTATERT.
	(general_scalar_to_vector_candidate_p): Consider ROTATE and
	ROTATERT to be candidates if the second operand is an integer
	constant, valid for a rotation (or shift) in the given mode.
	* config/i386/i386-features.h (general_scalar_chain): Add new
	helper method convert_rotate.

gcc/testsuite/ChangeLog
	* gcc.target/i386/rotate-6.c: New test case.
	* gcc.target/i386/sse2-stv-1.c: Likewise.

0 files changed, 0 insertions, 0 deletions