On Thu, 14 Nov 2013, Cong Hou wrote:
> Hi
>
> This patch adds the support to two non-isomorphic operations addsub
> and subadd for SLP vectorizer. More non-isomorphic operations can be
> added later, but the limitation is that operations on even/odd
> elements should still be isomorphic. Once such an operation is
> detected, the code of the operation used in vectorized code is stored
> and later will be used during statement transformation. Two new GIMPLE
> opeartions VEC_ADDSUB_EXPR and VEC_SUBADD_EXPR are defined. And also
> new optabs for them. They are also documented.
>
> The target supports for SSE/SSE2/SSE3/AVX are added for those two new
> operations on floating points. SSE3/AVX provides ADDSUBPD and ADDSUBPS
> instructions. For SSE/SSE2, those two operations are emulated using
> two instructions (selectively negate then add).
>
> With this patch the following function will be SLP vectorized:
>
>
> float a[4], b[4], c[4]; // double also OK.
>
> void subadd ()
> {
> c[0] = a[0] - b[0];
> c[1] = a[1] + b[1];
> c[2] = a[2] - b[2];
> c[3] = a[3] + b[3];
> }
>
> void addsub ()
> {
> c[0] = a[0] + b[0];
> c[1] = a[1] - b[1];
> c[2] = a[2] + b[2];
> c[3] = a[3] - b[3];
> }
>
>
> Boostrapped and tested on an x86-64 machine.
I managed to do this without adding new tree codes or optabs by
vectorizing the above as
c1 = a + b;
c2 = a - b;
c = VEC_PERM <c1, c2, the-proper-mask>
which then matches sse3_addsubv4sf3 if you fix that pattern to
not use vec_merge (or fix PR56766). Doing it this way also
means that the code is vectorizable if you don't have a HW
instruction for that but can do the VEC_PERM efficiently.
So, I'd like to avoid new tree codes and optabs whenever possible
and here I've already proved (with a patch) that it is possible.
Didn't have time to clean it up, and it likely doesn't apply anymore
(and PR56766 blocks it but it even has a patch).
Btw, this was PR56902 where I attached my patch.
Richard.
>
> thanks,
> Cong
>
>
>
>
>
> diff --git a/gcc/ChangeLog b/gcc/ChangeLog
> index 2c0554b..656d5fb 100644
> --- a/gcc/ChangeLog
> +++ b/gcc/ChangeLog
> @@ -1,3 +1,31 @@
> +2013-11-14 Cong Hou <co...@google.com>
> +
> + * tree-vect-slp.c (vect_create_new_slp_node): Initialize
> + SLP_TREE_OP_CODE.
> + (slp_supported_non_isomorphic_op): New function. Check if the
> + non-isomorphic operation is supported or not.
> + (vect_build_slp_tree_1): Consider non-isomorphic operations.
> + (vect_build_slp_tree): Change argument.
> + * tree-vect-stmts.c (vectorizable_operation): Consider the opcode
> + for non-isomorphic operations.
> + * optabs.def (vec_addsub_optab, vec_subadd_optab): New optabs.
> + * tree.def (VEC_ADDSUB_EXPR, VEC_SUBADD_EXPR): New operations.
> + * expr.c (expand_expr_real_2): Add support to VEC_ADDSUB_EXPR and
> + VEC_SUBADD_EXPR.
> + * gimple-pretty-print.c (dump_binary_rhs): Likewise.
> + * optabs.c (optab_for_tree_code): Likewise.
> + * tree-cfg.c (verify_gimple_assign_binary): Likewise.
> + * tree-vectorizer.h (struct _slp_tree): New data member.
> + * config/i386/i386-protos.h (ix86_sse_expand_fp_addsub_operator):
> + New funtion. Expand addsub/subadd operations for SSE2.
> + * config/i386/i386.c (ix86_sse_expand_fp_addsub_operator): Likewise.
> + * config/i386/sse.md (UNSPEC_SUBADD, UNSPEC_ADDSUB): New RTL operation.
> + (vec_subadd_v4sf3, vec_subadd_v2df3, vec_subadd_<mode>3,
> + vec_addsub_v4sf3, vec_addsub_v2df3, vec_addsub_<mode>3):
> + Expand addsub/subadd operations for SSE/SSE2/SSE3/AVX.
> + * doc/generic.texi (VEC_ADDSUB_EXPR, VEC_SUBADD_EXPR): New doc.
> + * doc/md.texi (vec_addsub_@var{m}3, vec_subadd_@var{m}3): New doc.
> +
> 2013-11-12 Jeff Law <l...@redhat.com>
>
> * tree-ssa-threadedge.c (thread_around_empty_blocks): New
> diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
> index fdf9d58..b02b757 100644
> --- a/gcc/config/i386/i386-protos.h
> +++ b/gcc/config/i386/i386-protos.h
> @@ -117,6 +117,7 @@ extern rtx ix86_expand_adjust_ufix_to_sfix_si (rtx, rtx
> *);
> extern enum ix86_fpcmp_strategy ix86_fp_comparison_strategy (enum rtx_code);
> extern void ix86_expand_fp_absneg_operator (enum rtx_code, enum machine_mode,
> rtx[]);
> +extern void ix86_sse_expand_fp_addsub_operator (bool, enum
> machine_mode, rtx[]);
> extern void ix86_expand_copysign (rtx []);
> extern void ix86_split_copysign_const (rtx []);
> extern void ix86_split_copysign_var (rtx []);
> diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
> index 5287b49..76f38f5 100644
> --- a/gcc/config/i386/i386.c
> +++ b/gcc/config/i386/i386.c
> @@ -18702,6 +18702,51 @@ ix86_expand_fp_absneg_operator (enum rtx_code
> code, enum machine_mode mode,
> emit_insn (set);
> }
>
> +/* Generate code for addsub or subadd on fp vectors for sse/sse2. The flag
> + SUBADD indicates if we are generating code for subadd or addsub. */
> +
> +void
> +ix86_sse_expand_fp_addsub_operator (bool subadd, enum machine_mode mode,
> + rtx operands[])
> +{
> + rtx mask;
> + rtx neg_mask32 = GEN_INT (0x80000000);
> + rtx neg_mask64 = GEN_INT ((HOST_WIDE_INT)1 << 63);
> +
> + switch (mode)
> + {
> + case V4SFmode:
> + if (subadd)
> + mask = gen_rtx_CONST_VECTOR (V4SImode, gen_rtvec (4,
> + neg_mask32, const0_rtx, neg_mask32, const0_rtx));
> + else
> + mask = gen_rtx_CONST_VECTOR (V4SImode, gen_rtvec (4,
> + const0_rtx, neg_mask32, const0_rtx, neg_mask32));
> + break;
> +
> + case V2DFmode:
> + if (subadd)
> + mask = gen_rtx_CONST_VECTOR (V2DImode, gen_rtvec (2,
> + neg_mask64, const0_rtx));
> + else
> + mask = gen_rtx_CONST_VECTOR (V2DImode, gen_rtvec (2,
> + const0_rtx, neg_mask64));
> + break;
> +
> + default:
> + gcc_unreachable ();
> + }
> +
> + rtx tmp = gen_reg_rtx (mode);
> + convert_move (tmp, mask, false);
> +
> + rtx tmp2 = gen_reg_rtx (mode);
> + tmp2 = expand_simple_binop (mode, XOR, tmp, operands[2],
> + tmp2, 0, OPTAB_DIRECT);
> + expand_simple_binop (mode, PLUS, operands[1], tmp2,
> + operands[0], 0, OPTAB_DIRECT);
> +}
> +
> /* Expand a copysign operation. Special case operand 0 being a constant. */
>
> void
> diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
> index 7bb2d77..4369b2e 100644
> --- a/gcc/config/i386/sse.md
> +++ b/gcc/config/i386/sse.md
> @@ -25,6 +25,8 @@
>
> ;; SSE3
> UNSPEC_LDDQU
> + UNSPEC_SUBADD
> + UNSPEC_ADDSUB
>
> ;; SSSE3
> UNSPEC_PSHUFB
> @@ -1508,6 +1510,80 @@
> (set_attr "prefix" "orig,vex")
> (set_attr "mode" "<MODE>")])
>
> +(define_expand "vec_subadd_v4sf3"
> + [(set (match_operand:V4SF 0 "register_operand")
> + (unspec:V4SF
> + [(match_operand:V4SF 1 "register_operand")
> + (match_operand:V4SF 2 "nonimmediate_operand")] UNSPEC_SUBADD))]
> + "TARGET_SSE"
> +{
> + if (TARGET_SSE3)
> + emit_insn (gen_sse3_addsubv4sf3 (operands[0], operands[1], operands[2]));
> + else
> + ix86_sse_expand_fp_addsub_operator (true, V4SFmode, operands);
> + DONE;
> +})
> +
> +(define_expand "vec_subadd_v2df3"
> + [(set (match_operand:V2DF 0 "register_operand")
> + (unspec:V2DF
> + [(match_operand:V2DF 1 "register_operand")
> + (match_operand:V2DF 2 "nonimmediate_operand")] UNSPEC_SUBADD))]
> + "TARGET_SSE2"
> +{
> + if (TARGET_SSE3)
> + emit_insn (gen_sse3_addsubv2df3 (operands[0], operands[1], operands[2]));
> + else
> + ix86_sse_expand_fp_addsub_operator (true, V2DFmode, operands);
> + DONE;
> +})
> +
> +(define_expand "vec_subadd_<mode>3"
> + [(set (match_operand:VF_256 0 "register_operand")
> + (unspec:VF_256
> + [(match_operand:VF_256 1 "register_operand")
> + (match_operand:VF_256 2 "nonimmediate_operand")] UNSPEC_SUBADD))]
> + "TARGET_AVX"
> +{
> + emit_insn (gen_avx_addsub<mode>3 (operands[0], operands[1], operands[2]));
> + DONE;
> +})
> +
> +(define_expand "vec_addsub_v4sf3"
> + [(set (match_operand:V4SF 0 "register_operand")
> + (unspec:V4SF
> + [(match_operand:V4SF 1 "register_operand")
> + (match_operand:V4SF 2 "nonimmediate_operand")] UNSPEC_SUBADD))]
> + "TARGET_SSE"
> +{
> + ix86_sse_expand_fp_addsub_operator (false, V4SFmode, operands);
> + DONE;
> +})
> +
> +(define_expand "vec_addsub_v2df3"
> + [(set (match_operand:V2DF 0 "register_operand")
> + (unspec:V2DF
> + [(match_operand:V2DF 1 "register_operand")
> + (match_operand:V2DF 2 "nonimmediate_operand")] UNSPEC_SUBADD))]
> + "TARGET_SSE2"
> +{
> + ix86_sse_expand_fp_addsub_operator (false, V2DFmode, operands);
> + DONE;
> +})
> +
> +(define_expand "vec_addsub_<mode>3"
> + [(set (match_operand:VF_256 0 "register_operand")
> + (unspec:VF_256
> + [(match_operand:VF_256 1 "register_operand")
> + (match_operand:VF_256 2 "nonimmediate_operand")] UNSPEC_ADDSUB))]
> + "TARGET_AVX"
> +{
> + rtx tmp = gen_reg_rtx (<MODE>mode);
> + emit_insn (gen_neg<mode>2 (tmp, operands[2]));
> + emit_insn (gen_avx_addsub<mode>3 (operands[0], operands[1], tmp));
> + DONE;
> +})
> +
> (define_insn "avx_addsubv4df3"
> [(set (match_operand:V4DF 0 "register_operand" "=x")
> (vec_merge:V4DF
> diff --git a/gcc/doc/generic.texi b/gcc/doc/generic.texi
> index f2dd0ff..0870d6f 100644
> --- a/gcc/doc/generic.texi
> +++ b/gcc/doc/generic.texi
> @@ -1715,6 +1715,8 @@ a value from @code{enum annot_expr_kind}.
> @tindex VEC_PACK_TRUNC_EXPR
> @tindex VEC_PACK_SAT_EXPR
> @tindex VEC_PACK_FIX_TRUNC_EXPR
> +@tindex VEC_ADDSUB_EXPR
> +@tindex VEC_SUBADD_EXPR
>
> @table @code
> @item VEC_LSHIFT_EXPR
> @@ -1795,6 +1797,12 @@ value, it is taken from the second operand. It
> should never evaluate to
> any other value currently, but optimizations should not rely on that
> property. In contrast with a @code{COND_EXPR}, all operands are always
> evaluated.
> +
> +@item VEC_ADDSUB_EXPR
> +@itemx VEC_SUBADD_EXPR
> +These nodes represent add/sub and sub/add operations on even/odd elements
> +of two vectors respectively. The three operands must be vectors of the same
> +size and number of elements.
> @end table
>
>
> diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi
> index 1a06e3d..d9726d2 100644
> --- a/gcc/doc/md.texi
> +++ b/gcc/doc/md.texi
> @@ -4885,6 +4885,12 @@ with N signed/unsigned elements of size S@.
> Operand 2 is a constant. Shift
> the high/low elements of operand 1, and put the N/2 results of size 2*S in
> the
> output vector (operand 0).
>
> +@cindex @code{vec_addsub_@var{m}3} instruction pattern
> +@cindex @code{vec_subadd_@var{m}3} instruction pattern
> +@item @samp{vec_addsub_@var{m}3}, @samp{vec_subadd_@var{m}3}
> +Perform add/sub or sub/add on even/odd elements of two vectors. Each
> +operand is a vector with N elements of size S@.
> +
> @cindex @code{mulhisi3} instruction pattern
> @item @samp{mulhisi3}
> Multiply operands 1 and 2, which have mode @code{HImode}, and store
> diff --git a/gcc/expr.c b/gcc/expr.c
> index 28b4332..997cfe2 100644
> --- a/gcc/expr.c
> +++ b/gcc/expr.c
> @@ -8743,6 +8743,8 @@ expand_expr_real_2 (sepops ops, rtx target, enum
> machine_mode tmode,
> case BIT_AND_EXPR:
> case BIT_IOR_EXPR:
> case BIT_XOR_EXPR:
> + case VEC_ADDSUB_EXPR:
> + case VEC_SUBADD_EXPR:
> goto binop;
>
> case LROTATE_EXPR:
> diff --git a/gcc/gimple-pretty-print.c b/gcc/gimple-pretty-print.c
> index 6842213..e5c7a93 100644
> --- a/gcc/gimple-pretty-print.c
> +++ b/gcc/gimple-pretty-print.c
> @@ -355,6 +355,8 @@ dump_binary_rhs (pretty_printer *buffer, gimple
> gs, int spc, int flags)
> case VEC_PACK_FIX_TRUNC_EXPR:
> case VEC_WIDEN_LSHIFT_HI_EXPR:
> case VEC_WIDEN_LSHIFT_LO_EXPR:
> + case VEC_ADDSUB_EXPR:
> + case VEC_SUBADD_EXPR:
> for (p = get_tree_code_name (code); *p; p++)
> pp_character (buffer, TOUPPER (*p));
> pp_string (buffer, " <");
> diff --git a/gcc/optabs.c b/gcc/optabs.c
> index 164e4dd..a725117 100644
> --- a/gcc/optabs.c
> +++ b/gcc/optabs.c
> @@ -547,6 +547,12 @@ optab_for_tree_code (enum tree_code code, const_tree
> type,
> return TYPE_UNSIGNED (type) ?
> vec_pack_ufix_trunc_optab : vec_pack_sfix_trunc_optab;
>
> + case VEC_ADDSUB_EXPR:
> + return vec_addsub_optab;
> +
> + case VEC_SUBADD_EXPR:
> + return vec_subadd_optab;
> +
> default:
> break;
> }
> diff --git a/gcc/optabs.def b/gcc/optabs.def
> index 6b924ac..3a09c52 100644
> --- a/gcc/optabs.def
> +++ b/gcc/optabs.def
> @@ -281,6 +281,8 @@ OPTAB_D (vec_widen_umult_lo_optab,
> "vec_widen_umult_lo_$a")
> OPTAB_D (vec_widen_umult_odd_optab, "vec_widen_umult_odd_$a")
> OPTAB_D (vec_widen_ushiftl_hi_optab, "vec_widen_ushiftl_hi_$a")
> OPTAB_D (vec_widen_ushiftl_lo_optab, "vec_widen_ushiftl_lo_$a")
> +OPTAB_D (vec_addsub_optab, "vec_addsub_$a3")
> +OPTAB_D (vec_subadd_optab, "vec_subadd_$a3")
>
> OPTAB_D (sync_add_optab, "sync_add$I$a")
> OPTAB_D (sync_and_optab, "sync_and$I$a")
> diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
> index 09c7f20..efd6c24 100644
> --- a/gcc/testsuite/ChangeLog
> +++ b/gcc/testsuite/ChangeLog
> @@ -1,3 +1,10 @@
> +2013-11-14 Cong Hou <co...@google.com>
> +
> + * lib/target-supports.exp (check_effective_target_vect_addsub):
> + New target.
> + * gcc.dg/vect/vect-addsub-float.c: New test.
> + * gcc.dg/vect/vect-addsub-double.c: New test.
> +
> 2013-11-12 Balaji V. Iyer <balaji.v.i...@intel.com>
>
> * gcc.dg/cilk-plus/cilk-plus.exp: Added a check for LTO before running
> diff --git a/gcc/testsuite/gcc.dg/vect/vect-addsub-double.c
> b/gcc/testsuite/gcc.dg/vect/vect-addsub-double.c
> new file mode 100644
> index 0000000..5399dde
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/vect/vect-addsub-double.c
> @@ -0,0 +1,51 @@
> +/* { dg-require-effective-target vect_addsub } */
> +/* { dg-additional-options "-fdump-tree-slp-details" } */
> +
> +#include "tree-vect.h"
> +
> +double a[4], b[4], c[4];
> +
> +void subadd ()
> +{
> + c[0] = a[0] - b[0];
> + c[1] = a[1] + b[1];
> + c[2] = a[2] - b[2];
> + c[3] = a[3] + b[3];
> +}
> +
> +void addsub ()
> +{
> + c[0] = a[0] + b[0];
> + c[1] = a[1] - b[1];
> + c[2] = a[2] + b[2];
> + c[3] = a[3] - b[3];
> +}
> +
> +int main()
> +{
> + int i;
> + for (i = 0; i < 4; ++i)
> + {
> + a[i] = (i + 1.2) / 3.4;
> + b[i] = (i + 5.6) / 7.8;
> + }
> +
> + subadd ();
> +
> + if (c[0] != a[0] - b[0]
> + || c[1] != a[1] + b[1]
> + || c[2] != a[2] - b[2]
> + || c[3] != a[3] + b[3])
> + abort ();
> +
> + addsub ();
> +
> + if (c[0] != a[0] + b[0]
> + || c[1] != a[1] - b[1]
> + || c[2] != a[2] + b[2]
> + || c[3] != a[3] - b[3])
> + abort ();
> +}
> +
> +/* { dg-final { scan-tree-dump-times "basic block vectorized" 2 "slp" } } */
> +/* { dg-final { cleanup-tree-dump "slp" } } */
> diff --git a/gcc/testsuite/gcc.dg/vect/vect-addsub-float.c
> b/gcc/testsuite/gcc.dg/vect/vect-addsub-float.c
> new file mode 100644
> index 0000000..5b780f3
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/vect/vect-addsub-float.c
> @@ -0,0 +1,51 @@
> +/* { dg-require-effective-target vect_addsub } */
> +/* { dg-additional-options "-fdump-tree-slp-details" } */
> +
> +#include "tree-vect.h"
> +
> +float a[4], b[4], c[4];
> +
> +void subadd ()
> +{
> + c[0] = a[0] - b[0];
> + c[1] = a[1] + b[1];
> + c[2] = a[2] - b[2];
> + c[3] = a[3] + b[3];
> +}
> +
> +void addsub ()
> +{
> + c[0] = a[0] + b[0];
> + c[1] = a[1] - b[1];
> + c[2] = a[2] + b[2];
> + c[3] = a[3] - b[3];
> +}
> +
> +int main()
> +{
> + int i;
> + for (i = 0; i < 4; ++i)
> + {
> + a[i] = (i + 1.2) / 3.4;
> + b[i] = (i + 5.6) / 7.8;
> + }
> +
> + subadd ();
> +
> + if (c[0] != a[0] - b[0]
> + || c[1] != a[1] + b[1]
> + || c[2] != a[2] - b[2]
> + || c[3] != a[3] + b[3])
> + abort ();
> +
> + addsub ();
> +
> + if (c[0] != a[0] + b[0]
> + || c[1] != a[1] - b[1]
> + || c[2] != a[2] + b[2]
> + || c[3] != a[3] - b[3])
> + abort ();
> +}
> +
> +/* { dg-final { scan-tree-dump-times "basic block vectorized" 2 "slp" } } */
> +/* { dg-final { cleanup-tree-dump "slp" } } */
> diff --git a/gcc/testsuite/lib/target-supports.exp
> b/gcc/testsuite/lib/target-supports.exp
> index c3d9712..f336f77 100644
> --- a/gcc/testsuite/lib/target-supports.exp
> +++ b/gcc/testsuite/lib/target-supports.exp
> @@ -4099,6 +4099,15 @@ proc check_effective_target_vect_extract_even_odd { } {
> return $et_vect_extract_even_odd_saved
> }
>
> +# Return 1 if the target supports vector addsub and subadd
> operations, 0 otherwise.
> +
> +proc check_effective_target_vect_addsub { } {
> + if { [check_effective_target_sse2] } {
> + return 1
> + }
> + return 0
> +}
> +
> # Return 1 if the target supports vector interleaving, 0 otherwise.
>
> proc check_effective_target_vect_interleave { } {
> diff --git a/gcc/tree-cfg.c b/gcc/tree-cfg.c
> index 601efd6..2bf1b79 100644
> --- a/gcc/tree-cfg.c
> +++ b/gcc/tree-cfg.c
> @@ -3572,6 +3572,23 @@ verify_gimple_assign_binary (gimple stmt)
> return false;
> }
>
> + case VEC_SUBADD_EXPR:
> + case VEC_ADDSUB_EXPR:
> + {
> + if (TREE_CODE (rhs1_type) != VECTOR_TYPE
> + || TREE_CODE (rhs2_type) != VECTOR_TYPE
> + || TREE_CODE (lhs_type) != VECTOR_TYPE)
> + {
> + error ("type mismatch in addsub/subadd expression");
> + debug_generic_expr (lhs_type);
> + debug_generic_expr (rhs1_type);
> + debug_generic_expr (rhs2_type);
> + return true;
> + }
> +
> + return false;
> + }
> +
> case PLUS_EXPR:
> case MINUS_EXPR:
> {
> diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
> index 825f73a..1169d33 100644
> --- a/gcc/tree-vect-slp.c
> +++ b/gcc/tree-vect-slp.c
> @@ -125,6 +125,7 @@ vect_create_new_slp_node (vec<gimple> scalar_stmts)
> SLP_TREE_VEC_STMTS (node).create (0);
> SLP_TREE_CHILDREN (node).create (nops);
> SLP_TREE_LOAD_PERMUTATION (node) = vNULL;
> + SLP_TREE_OP_CODE (node) = ERROR_MARK;
>
> return node;
> }
> @@ -383,8 +384,74 @@ vect_get_and_check_slp_defs (loop_vec_info
> loop_vinfo, bb_vec_info bb_vinfo,
> return true;
> }
>
> +/* Check if the target supports the vector operation that performs the
> + operation of FIRST_STMT_CODE on even elements and the operation as in STMT
> + on odd elements. If yes, set the code of NODE to that of the new
> operation
> + and return true. Otherwise return false. This enables SLP vectorization
> + for the following code:
>
> -/* Verify if the scalar stmts STMTS are isomorphic, require data
> + a[0] = b[0] + c[0];
> + a[1] = b[1] - c[1];
> + a[2] = b[2] + c[2];
> + a[3] = b[3] - c[3];
> + */
> +
> +static bool
> +slp_supported_non_isomorphic_op (enum tree_code first_stmt_code,
> + gimple stmt,
> + slp_tree *node)
> +{
> + if (!is_gimple_assign (stmt))
> + return false;
> +
> + enum tree_code rhs_code = gimple_assign_rhs_code (stmt);
> + enum tree_code vec_opcode = ERROR_MARK;
> +
> + switch (first_stmt_code)
> + {
> + case PLUS_EXPR:
> + if (rhs_code == MINUS_EXPR)
> + vec_opcode = VEC_ADDSUB_EXPR;
> + break;
> +
> + case MINUS_EXPR:
> + if (rhs_code == PLUS_EXPR)
> + vec_opcode = VEC_SUBADD_EXPR;
> + break;
> +
> + default:
> + return false;
> + }
> +
> + if (vec_opcode == ERROR_MARK)
> + return false;
> +
> + stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
> + tree vectype = STMT_VINFO_VECTYPE (stmt_info);
> + if (!vectype)
> + {
> + vectype = get_vectype_for_scalar_type
> + (TREE_TYPE (gimple_assign_rhs1 (stmt)));
> + gcc_assert (vectype);
> + }
> +
> + optab optab = optab_for_tree_code (vec_opcode, vectype, optab_default);
> + if (!optab)
> + return false;
> +
> + int icode = (int) optab_handler (optab, TYPE_MODE (vectype));
> + if (icode == CODE_FOR_nothing)
> + return false;
> +
> + if (SLP_TREE_OP_CODE (*node) != ERROR_MARK
> + && SLP_TREE_OP_CODE (*node) != vec_opcode)
> + return false;
> +
> + SLP_TREE_OP_CODE (*node) = vec_opcode;
> + return true;
> +}
> +
> +/* Verify if the scalar stmts of NODE are isomorphic, require data
> permutation or are of unsupported types of operation. Return
> true if they are, otherwise return false and indicate in *MATCHES
> which stmts are not isomorphic to the first one. If MATCHES[0]
> @@ -393,11 +460,12 @@ vect_get_and_check_slp_defs (loop_vec_info
> loop_vinfo, bb_vec_info bb_vinfo,
>
> static bool
> vect_build_slp_tree_1 (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo,
> - vec<gimple> stmts, unsigned int group_size,
> + slp_tree *node, unsigned int group_size,
> unsigned nops, unsigned int *max_nunits,
> unsigned int vectorization_factor, bool *matches)
> {
> unsigned int i;
> + vec<gimple> stmts = SLP_TREE_SCALAR_STMTS (*node);
> gimple stmt = stmts[0];
> enum tree_code first_stmt_code = ERROR_MARK, rhs_code = ERROR_MARK;
> enum tree_code first_cond_code = ERROR_MARK;
> @@ -583,7 +651,10 @@ vect_build_slp_tree_1 (loop_vec_info loop_vinfo,
> bb_vec_info bb_vinfo,
> }
> else
> {
> - if (first_stmt_code != rhs_code
> + if ((first_stmt_code != rhs_code
> + && (i % 2 == 0
> + || !slp_supported_non_isomorphic_op (first_stmt_code,
> + stmt, node)))
> && (first_stmt_code != IMAGPART_EXPR
> || rhs_code != REALPART_EXPR)
> && (first_stmt_code != REALPART_EXPR
> @@ -868,7 +939,7 @@ vect_build_slp_tree (loop_vec_info loop_vinfo,
> bb_vec_info bb_vinfo,
> return false;
>
> if (!vect_build_slp_tree_1 (loop_vinfo, bb_vinfo,
> - SLP_TREE_SCALAR_STMTS (*node), group_size, nops,
> + node, group_size, nops,
> max_nunits, vectorization_factor, matches))
> return false;
>
> diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
> index b0e0fa9..98906f0 100644
> --- a/gcc/tree-vect-stmts.c
> +++ b/gcc/tree-vect-stmts.c
> @@ -3512,7 +3512,13 @@ vectorizable_operation (gimple stmt,
> gimple_stmt_iterator *gsi,
> if (TREE_CODE (gimple_assign_lhs (stmt)) != SSA_NAME)
> return false;
>
> - code = gimple_assign_rhs_code (stmt);
> + /* Check if this slp_node will be vectorized by non-isomorphic operations,
> + in which case the operation on vectors is stored in
> + SLP_TREE_OP_CODE (slp_node). */
> + if (slp_node && SLP_TREE_OP_CODE (slp_node) != ERROR_MARK)
> + code = SLP_TREE_OP_CODE (slp_node);
> + else
> + code = gimple_assign_rhs_code (stmt);
>
> /* For pointer addition, we should use the normal plus for
> the vector addition. */
> diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
> index bbd50e1..19c09ae 100644
> --- a/gcc/tree-vectorizer.h
> +++ b/gcc/tree-vectorizer.h
> @@ -117,6 +117,10 @@ struct _slp_tree {
> scalar elements in one scalar iteration (GROUP_SIZE) multiplied by VF
> divided by vector size. */
> unsigned int vec_stmts_size;
> + /* The operation code used in the vectorized statement if it is not
> + ERROR_MARK. Otherwise the operation is determined by the original
> + statement. */
> + enum tree_code op_code;
> };
>
>
> @@ -157,6 +161,7 @@ typedef struct _slp_instance {
> #define SLP_TREE_VEC_STMTS(S) (S)->vec_stmts
> #define SLP_TREE_NUMBER_OF_VEC_STMTS(S) (S)->vec_stmts_size
> #define SLP_TREE_LOAD_PERMUTATION(S) (S)->load_permutation
> +#define SLP_TREE_OP_CODE(S) (S)->op_code
>
> /* This structure is used in creation of an SLP tree. Each instance
> corresponds to the same operand in a group of scalar stmts in an SLP
> diff --git a/gcc/tree.def b/gcc/tree.def
> index 6763e78..c3eda42 100644
> --- a/gcc/tree.def
> +++ b/gcc/tree.def
> @@ -1256,6 +1256,13 @@ DEFTREECODE (VEC_PACK_FIX_TRUNC_EXPR,
> "vec_pack_fix_trunc_expr", tcc_binary, 2)
> DEFTREECODE (VEC_WIDEN_LSHIFT_HI_EXPR, "widen_lshift_hi_expr", tcc_binary, 2)
> DEFTREECODE (VEC_WIDEN_LSHIFT_LO_EXPR, "widen_lshift_lo_expr", tcc_binary, 2)
>
> +/* Add even/odd elements and sub odd/even elements between two vectors.
> + Operand 0 and operand 1 are two operands.
> + The result of this operation is a vector with the same type of operand
> 0/1.
> + */
> +DEFTREECODE (VEC_ADDSUB_EXPR, "addsub_expr", tcc_binary, 2)
> +DEFTREECODE (VEC_SUBADD_EXPR, "subadd_expr", tcc_binary, 2)
> +
> /* PREDICT_EXPR. Specify hint for branch prediction. The
> PREDICT_EXPR_PREDICTOR specify predictor and PREDICT_EXPR_OUTCOME the
> outcome (0 for not taken and 1 for taken). Once the profile is guessed
>
--
Richard Biener <rguent...@suse.de>
SUSE / SUSE Labs
SUSE LINUX Products GmbH - Nuernberg - AG Nuernberg - HRB 16746
GF: Jeff Hawn, Jennifer Guild, Felix Imend"orffer
