diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index 47f8b18..0fa1847 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -4376,13 +4376,57 @@ (match_operator:V2DI 1 "" [(match_operand:V2DI 2 "register_operand") (match_operand:V2DI 3 "vector_operand")]))] - "TARGET_SSE4_1" + "TARGET_SSE2" { - bool ok = ix86_expand_int_vec_cmp (operands); + bool ok; + if (!TARGET_SSE4_1) + { + rtx ops[4]; + ops[0] = gen_reg_rtx (V4SImode); + ops[2] = gen_lowpart (V4SImode, force_reg (V2DImode, operands[2])); + ops[3] = gen_lowpart (V4SImode, force_reg (V2DImode, operands[3])); + ops[1] = gen_rtx_fmt_ee (GET_CODE (operands[1]), V4SImode, + ops[2], ops[3]); + ok = ix86_expand_int_vec_cmp (ops); + + rtx tmp1 = gen_reg_rtx (V4SImode); + emit_insn (gen_sse2_pshufd (tmp1, ops[0], GEN_INT (0xb1))); + + rtx tmp2 = gen_reg_rtx (V4SImode); + emit_insn (gen_andv4si3 (tmp2, tmp1, ops[0])); + + emit_move_insn (operands[0], gen_lowpart (V2DImode, tmp2)); + } + else + ok = ix86_expand_int_vec_cmp (operands); gcc_assert (ok); DONE; }) +(define_expand "vec_cmpeqv1tiv1ti" + [(set (match_operand:V1TI 0 "register_operand") + (match_operator:V1TI 1 "" + [(match_operand:V1TI 2 "register_operand") + (match_operand:V1TI 3 "vector_operand")]))] + "TARGET_SSE2" +{ + rtx dst = gen_reg_rtx (V2DImode); + rtx op1 = gen_lowpart (V2DImode, force_reg (V1TImode, operands[2])); + rtx op2 = gen_lowpart (V2DImode, force_reg (V1TImode, operands[3])); + rtx cmp = gen_rtx_fmt_ee (GET_CODE (operands[1]), V2DImode, op1, op2); + emit_insn (gen_vec_cmpeqv2div2di (dst, cmp, op1, op2)); + + rtx tmp1 = gen_reg_rtx (V4SImode); + rtx tmp2 = gen_lowpart (V4SImode, dst); + emit_insn (gen_sse2_pshufd (tmp1, tmp2, GEN_INT (0x4e))); + + rtx tmp3 = gen_reg_rtx (V4SImode); + emit_insn (gen_andv4si3 (tmp3, tmp2, tmp1)); + + emit_move_insn (operands[0], gen_lowpart (V1TImode, tmp3)); + DONE; +}) + (define_expand "vcond" [(set (match_operand:V_512 0 "register_operand") (if_then_else:V_512 diff --git a/gcc/testsuite/gcc.target/i386/sse2-v1ti-veq.c b/gcc/testsuite/gcc.target/i386/sse2-v1ti-veq.c new file mode 100644 index 0000000..8bbda06 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/sse2-v1ti-veq.c @@ -0,0 +1,12 @@ +/* { dg-do compile { target { ! ia32 } } } */ +/* { dg-options "-O2 -msse2" } */ +typedef unsigned __int128 uv1ti __attribute__ ((__vector_size__ (16))); +typedef unsigned long long uv2di __attribute__ ((__vector_size__ (16))); +typedef unsigned int uv4si __attribute__ ((__vector_size__ (16))); + +uv1ti eq_v1ti(uv1ti x, uv1ti y) { return x == y; } +uv2di eq_v2di(uv2di x, uv2di y) { return x == y; } +uv4si eq_v4si(uv4si x, uv4si y) { return x == y; } + +/* { dg-final { scan-assembler-times "pcmpeq" 3 } } */ +/* { dg-final { scan-assembler "pshufd" } } */ diff --git a/gcc/testsuite/gcc.target/i386/sse2-v1ti-vne.c b/gcc/testsuite/gcc.target/i386/sse2-v1ti-vne.c new file mode 100644 index 0000000..cb47147 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/sse2-v1ti-vne.c @@ -0,0 +1,13 @@ +/* { dg-do compile { target { ! ia32 } } } */ +/* { dg-options "-O2 -msse2" } */ +typedef unsigned __int128 uv1ti __attribute__ ((__vector_size__ (16))); +typedef unsigned long long uv2di __attribute__ ((__vector_size__ (16))); +typedef unsigned int uv4si __attribute__ ((__vector_size__ (16))); + +uv1ti eq_v1ti(uv1ti x, uv1ti y) { return x != y; } +uv2di eq_v2di(uv2di x, uv2di y) { return x != y; } +uv4si eq_v4si(uv4si x, uv4si y) { return x != y; } + +/* { dg-final { scan-assembler-times "pcmpeq" 6 } } */ +/* { dg-final { scan-assembler-times "pxor" 3 } } */ +/* { dg-final { scan-assembler "pshufd" } } */