Re: [14/n] Vectorise conversions between differently-sized integer vectors
On Wed, Nov 6, 2019 at 1:45 PM Richard Sandiford wrote: > > Richard Biener writes: > > On Fri, Oct 25, 2019 at 2:51 PM Richard Sandiford > > wrote: > >> > >> This patch adds AArch64 patterns for converting between 64-bit and > >> 128-bit integer vectors, and makes the vectoriser and expand pass > >> use them. > > > > So on GIMPLE we'll see > > > > v4si _1; > > v4di _2; > > > > _1 = (v4si) _2; > > > > then, correct? Likewise for float conversions. > > > > I think that's "new", can you add to tree-cfg.c:verify_gimple_assign_unary > > verification that the number of lanes of the LHS and the RHS match please? > > Ah, yeah. How's this? Tested as before. OK. Thanks, Richard. > Richard > > > 2019-11-06 Richard Sandiford > > gcc/ > * tree-cfg.c (verify_gimple_assign_unary): Handle conversions > between vector types. > * tree-vect-stmts.c (vectorizable_conversion): Extend the > non-widening and non-narrowing path to handle standard > conversion codes, if the target supports them. > * expr.c (convert_move): Try using the extend and truncate optabs > for vectors. > * optabs-tree.c (supportable_convert_operation): Likewise. > * config/aarch64/iterators.md (Vnarroqw): New iterator. > * config/aarch64/aarch64-simd.md (2) > (trunc2): New patterns. > > gcc/testsuite/ > * gcc.dg/vect/bb-slp-pr69907.c: Do not expect BB vectorization > to fail for aarch64 targets. > * gcc.dg/vect/no-scevccp-outer-12.c: Expect the test to pass > on aarch64 targets. > * gcc.dg/vect/vect-double-reduc-5.c: Likewise. > * gcc.dg/vect/vect-outer-4e.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_5.c: New test. > * gcc.target/aarch64/vect_mixed_sizes_6.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_7.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_8.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_9.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_10.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_11.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_12.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_13.c: Likewise. > > Index: gcc/tree-cfg.c > === > --- gcc/tree-cfg.c 2019-09-05 08:49:30.829739618 +0100 > +++ gcc/tree-cfg.c 2019-11-06 12:44:22.832365429 + > @@ -3553,6 +3553,24 @@ verify_gimple_assign_unary (gassign *stm > { > CASE_CONVERT: >{ > + /* Allow conversions between vectors with the same number of elements, > + provided that the conversion is OK for the element types too. */ > + if (VECTOR_TYPE_P (lhs_type) > + && VECTOR_TYPE_P (rhs1_type) > + && known_eq (TYPE_VECTOR_SUBPARTS (lhs_type), > +TYPE_VECTOR_SUBPARTS (rhs1_type))) > + { > + lhs_type = TREE_TYPE (lhs_type); > + rhs1_type = TREE_TYPE (rhs1_type); > + } > + else if (VECTOR_TYPE_P (lhs_type) || VECTOR_TYPE_P (rhs1_type)) > + { > + error ("invalid vector types in nop conversion"); > + debug_generic_expr (lhs_type); > + debug_generic_expr (rhs1_type); > + return true; > + } > + > /* Allow conversions from pointer type to integral type only if >there is no sign or zero extension involved. >For targets were the precision of ptrofftype doesn't match that > Index: gcc/tree-vect-stmts.c > === > --- gcc/tree-vect-stmts.c 2019-11-06 12:44:10.896448608 + > +++ gcc/tree-vect-stmts.c 2019-11-06 12:44:22.832365429 + > @@ -4869,7 +4869,9 @@ vectorizable_conversion (stmt_vec_info s >switch (modifier) > { > case NONE: > - if (code != FIX_TRUNC_EXPR && code != FLOAT_EXPR) > + if (code != FIX_TRUNC_EXPR > + && code != FLOAT_EXPR > + && !CONVERT_EXPR_CODE_P (code)) > return false; >if (supportable_convert_operation (code, vectype_out, vectype_in, > , )) > Index: gcc/expr.c > === > --- gcc/expr.c 2019-11-06 12:29:17.394677341 + > +++ gcc/expr.c 2019-11-06 12:44:22.828365457 + > @@ -250,6 +250,31 @@ convert_move (rtx to, rtx from, int unsi > >if (VECTOR_MODE_P (to_mode) || VECTOR_MODE_P (from_mode)) > { > + if (GET_MODE_UNIT_PRECISION (to_mode) > + > GET_MODE_UNIT_PRECISION (from_mode)) > + { > + optab op = unsignedp ? zext_optab : sext_optab; > + insn_code icode = convert_optab_handler (op, to_mode, from_mode); > + if (icode != CODE_FOR_nothing) > + { > + emit_unop_insn (icode, to, from, > + unsignedp ?
Re: [14/n] Vectorise conversions between differently-sized integer vectors
Richard Biener writes: > On Fri, Oct 25, 2019 at 2:51 PM Richard Sandiford > wrote: >> >> This patch adds AArch64 patterns for converting between 64-bit and >> 128-bit integer vectors, and makes the vectoriser and expand pass >> use them. > > So on GIMPLE we'll see > > v4si _1; > v4di _2; > > _1 = (v4si) _2; > > then, correct? Likewise for float conversions. > > I think that's "new", can you add to tree-cfg.c:verify_gimple_assign_unary > verification that the number of lanes of the LHS and the RHS match please? Ah, yeah. How's this? Tested as before. Richard 2019-11-06 Richard Sandiford gcc/ * tree-cfg.c (verify_gimple_assign_unary): Handle conversions between vector types. * tree-vect-stmts.c (vectorizable_conversion): Extend the non-widening and non-narrowing path to handle standard conversion codes, if the target supports them. * expr.c (convert_move): Try using the extend and truncate optabs for vectors. * optabs-tree.c (supportable_convert_operation): Likewise. * config/aarch64/iterators.md (Vnarroqw): New iterator. * config/aarch64/aarch64-simd.md (2) (trunc2): New patterns. gcc/testsuite/ * gcc.dg/vect/bb-slp-pr69907.c: Do not expect BB vectorization to fail for aarch64 targets. * gcc.dg/vect/no-scevccp-outer-12.c: Expect the test to pass on aarch64 targets. * gcc.dg/vect/vect-double-reduc-5.c: Likewise. * gcc.dg/vect/vect-outer-4e.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_5.c: New test. * gcc.target/aarch64/vect_mixed_sizes_6.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_7.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_8.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_9.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_10.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_11.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_12.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_13.c: Likewise. Index: gcc/tree-cfg.c === --- gcc/tree-cfg.c 2019-09-05 08:49:30.829739618 +0100 +++ gcc/tree-cfg.c 2019-11-06 12:44:22.832365429 + @@ -3553,6 +3553,24 @@ verify_gimple_assign_unary (gassign *stm { CASE_CONVERT: { + /* Allow conversions between vectors with the same number of elements, + provided that the conversion is OK for the element types too. */ + if (VECTOR_TYPE_P (lhs_type) + && VECTOR_TYPE_P (rhs1_type) + && known_eq (TYPE_VECTOR_SUBPARTS (lhs_type), +TYPE_VECTOR_SUBPARTS (rhs1_type))) + { + lhs_type = TREE_TYPE (lhs_type); + rhs1_type = TREE_TYPE (rhs1_type); + } + else if (VECTOR_TYPE_P (lhs_type) || VECTOR_TYPE_P (rhs1_type)) + { + error ("invalid vector types in nop conversion"); + debug_generic_expr (lhs_type); + debug_generic_expr (rhs1_type); + return true; + } + /* Allow conversions from pointer type to integral type only if there is no sign or zero extension involved. For targets were the precision of ptrofftype doesn't match that Index: gcc/tree-vect-stmts.c === --- gcc/tree-vect-stmts.c 2019-11-06 12:44:10.896448608 + +++ gcc/tree-vect-stmts.c 2019-11-06 12:44:22.832365429 + @@ -4869,7 +4869,9 @@ vectorizable_conversion (stmt_vec_info s switch (modifier) { case NONE: - if (code != FIX_TRUNC_EXPR && code != FLOAT_EXPR) + if (code != FIX_TRUNC_EXPR + && code != FLOAT_EXPR + && !CONVERT_EXPR_CODE_P (code)) return false; if (supportable_convert_operation (code, vectype_out, vectype_in, , )) Index: gcc/expr.c === --- gcc/expr.c 2019-11-06 12:29:17.394677341 + +++ gcc/expr.c 2019-11-06 12:44:22.828365457 + @@ -250,6 +250,31 @@ convert_move (rtx to, rtx from, int unsi if (VECTOR_MODE_P (to_mode) || VECTOR_MODE_P (from_mode)) { + if (GET_MODE_UNIT_PRECISION (to_mode) + > GET_MODE_UNIT_PRECISION (from_mode)) + { + optab op = unsignedp ? zext_optab : sext_optab; + insn_code icode = convert_optab_handler (op, to_mode, from_mode); + if (icode != CODE_FOR_nothing) + { + emit_unop_insn (icode, to, from, + unsignedp ? ZERO_EXTEND : SIGN_EXTEND); + return; + } + } + + if (GET_MODE_UNIT_PRECISION (to_mode) + < GET_MODE_UNIT_PRECISION (from_mode)) + { + insn_code icode = convert_optab_handler (trunc_optab, + to_mode, from_mode); +
Re: [14/n] Vectorise conversions between differently-sized integer vectors
On Fri, Oct 25, 2019 at 2:51 PM Richard Sandiford wrote: > > This patch adds AArch64 patterns for converting between 64-bit and > 128-bit integer vectors, and makes the vectoriser and expand pass > use them. So on GIMPLE we'll see v4si _1; v4di _2; _1 = (v4si) _2; then, correct? Likewise for float conversions. I think that's "new", can you add to tree-cfg.c:verify_gimple_assign_unary verification that the number of lanes of the LHS and the RHS match please? OK with that change. Thanks, Richard. > > 2019-10-24 Richard Sandiford > > gcc/ > * tree-vect-stmts.c (vectorizable_conversion): Extend the > non-widening and non-narrowing path to handle standard > conversion codes, if the target supports them. > * expr.c (convert_move): Try using the extend and truncate optabs > for vectors. > * optabs-tree.c (supportable_convert_operation): Likewise. > * config/aarch64/iterators.md (Vnarroqw): New iterator. > * config/aarch64/aarch64-simd.md (2) > (trunc2): New patterns. > > gcc/testsuite/ > * gcc.dg/vect/no-scevccp-outer-12.c: Expect the test to pass > on aarch64 targets. > * gcc.dg/vect/vect-double-reduc-5.c: Likewise. > * gcc.dg/vect/vect-outer-4e.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_5.c: New test. > * gcc.target/aarch64/vect_mixed_sizes_6.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_7.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_8.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_9.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_10.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_11.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_12.c: Likewise. > * gcc.target/aarch64/vect_mixed_sizes_13.c: Likewise. > > Index: gcc/tree-vect-stmts.c > === > --- gcc/tree-vect-stmts.c 2019-10-25 13:27:32.877640367 +0100 > +++ gcc/tree-vect-stmts.c 2019-10-25 13:27:36.197616908 +0100 > @@ -4861,7 +4861,9 @@ vectorizable_conversion (stmt_vec_info s >switch (modifier) > { > case NONE: > - if (code != FIX_TRUNC_EXPR && code != FLOAT_EXPR) > + if (code != FIX_TRUNC_EXPR > + && code != FLOAT_EXPR > + && !CONVERT_EXPR_CODE_P (code)) > return false; >if (supportable_convert_operation (code, vectype_out, vectype_in, > , )) > Index: gcc/expr.c > === > --- gcc/expr.c 2019-10-22 08:46:57.359355939 +0100 > +++ gcc/expr.c 2019-10-25 13:27:36.193616936 +0100 > @@ -250,6 +250,31 @@ convert_move (rtx to, rtx from, int unsi > >if (VECTOR_MODE_P (to_mode) || VECTOR_MODE_P (from_mode)) > { > + if (GET_MODE_UNIT_PRECISION (to_mode) > + > GET_MODE_UNIT_PRECISION (from_mode)) > + { > + optab op = unsignedp ? zext_optab : sext_optab; > + insn_code icode = convert_optab_handler (op, to_mode, from_mode); > + if (icode != CODE_FOR_nothing) > + { > + emit_unop_insn (icode, to, from, > + unsignedp ? ZERO_EXTEND : SIGN_EXTEND); > + return; > + } > + } > + > + if (GET_MODE_UNIT_PRECISION (to_mode) > + < GET_MODE_UNIT_PRECISION (from_mode)) > + { > + insn_code icode = convert_optab_handler (trunc_optab, > + to_mode, from_mode); > + if (icode != CODE_FOR_nothing) > + { > + emit_unop_insn (icode, to, from, TRUNCATE); > + return; > + } > + } > + >gcc_assert (known_eq (GET_MODE_BITSIZE (from_mode), > GET_MODE_BITSIZE (to_mode))); > > Index: gcc/optabs-tree.c > === > --- gcc/optabs-tree.c 2019-10-08 09:23:31.894529571 +0100 > +++ gcc/optabs-tree.c 2019-10-25 13:27:36.193616936 +0100 > @@ -303,6 +303,20 @@ supportable_convert_operation (enum tree >return true; > } > > + if (GET_MODE_UNIT_PRECISION (m1) > GET_MODE_UNIT_PRECISION (m2) > + && can_extend_p (m1, m2, TYPE_UNSIGNED (vectype_in))) > +{ > + *code1 = code; > + return true; > +} > + > + if (GET_MODE_UNIT_PRECISION (m1) < GET_MODE_UNIT_PRECISION (m2) > + && convert_optab_handler (trunc_optab, m1, m2) != CODE_FOR_nothing) > +{ > + *code1 = code; > + return true; > +} > + >/* Now check for builtin. */ >if (targetm.vectorize.builtin_conversion >&& targetm.vectorize.builtin_conversion (code, vectype_out, > vectype_in)) > Index: gcc/config/aarch64/iterators.md > === > --- gcc/config/aarch64/iterators.md 2019-10-17 14:23:07.71142 +0100 > +++
[14/n] Vectorise conversions between differently-sized integer vectors
This patch adds AArch64 patterns for converting between 64-bit and 128-bit integer vectors, and makes the vectoriser and expand pass use them. 2019-10-24 Richard Sandiford gcc/ * tree-vect-stmts.c (vectorizable_conversion): Extend the non-widening and non-narrowing path to handle standard conversion codes, if the target supports them. * expr.c (convert_move): Try using the extend and truncate optabs for vectors. * optabs-tree.c (supportable_convert_operation): Likewise. * config/aarch64/iterators.md (Vnarroqw): New iterator. * config/aarch64/aarch64-simd.md (2) (trunc2): New patterns. gcc/testsuite/ * gcc.dg/vect/no-scevccp-outer-12.c: Expect the test to pass on aarch64 targets. * gcc.dg/vect/vect-double-reduc-5.c: Likewise. * gcc.dg/vect/vect-outer-4e.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_5.c: New test. * gcc.target/aarch64/vect_mixed_sizes_6.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_7.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_8.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_9.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_10.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_11.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_12.c: Likewise. * gcc.target/aarch64/vect_mixed_sizes_13.c: Likewise. Index: gcc/tree-vect-stmts.c === --- gcc/tree-vect-stmts.c 2019-10-25 13:27:32.877640367 +0100 +++ gcc/tree-vect-stmts.c 2019-10-25 13:27:36.197616908 +0100 @@ -4861,7 +4861,9 @@ vectorizable_conversion (stmt_vec_info s switch (modifier) { case NONE: - if (code != FIX_TRUNC_EXPR && code != FLOAT_EXPR) + if (code != FIX_TRUNC_EXPR + && code != FLOAT_EXPR + && !CONVERT_EXPR_CODE_P (code)) return false; if (supportable_convert_operation (code, vectype_out, vectype_in, , )) Index: gcc/expr.c === --- gcc/expr.c 2019-10-22 08:46:57.359355939 +0100 +++ gcc/expr.c 2019-10-25 13:27:36.193616936 +0100 @@ -250,6 +250,31 @@ convert_move (rtx to, rtx from, int unsi if (VECTOR_MODE_P (to_mode) || VECTOR_MODE_P (from_mode)) { + if (GET_MODE_UNIT_PRECISION (to_mode) + > GET_MODE_UNIT_PRECISION (from_mode)) + { + optab op = unsignedp ? zext_optab : sext_optab; + insn_code icode = convert_optab_handler (op, to_mode, from_mode); + if (icode != CODE_FOR_nothing) + { + emit_unop_insn (icode, to, from, + unsignedp ? ZERO_EXTEND : SIGN_EXTEND); + return; + } + } + + if (GET_MODE_UNIT_PRECISION (to_mode) + < GET_MODE_UNIT_PRECISION (from_mode)) + { + insn_code icode = convert_optab_handler (trunc_optab, + to_mode, from_mode); + if (icode != CODE_FOR_nothing) + { + emit_unop_insn (icode, to, from, TRUNCATE); + return; + } + } + gcc_assert (known_eq (GET_MODE_BITSIZE (from_mode), GET_MODE_BITSIZE (to_mode))); Index: gcc/optabs-tree.c === --- gcc/optabs-tree.c 2019-10-08 09:23:31.894529571 +0100 +++ gcc/optabs-tree.c 2019-10-25 13:27:36.193616936 +0100 @@ -303,6 +303,20 @@ supportable_convert_operation (enum tree return true; } + if (GET_MODE_UNIT_PRECISION (m1) > GET_MODE_UNIT_PRECISION (m2) + && can_extend_p (m1, m2, TYPE_UNSIGNED (vectype_in))) +{ + *code1 = code; + return true; +} + + if (GET_MODE_UNIT_PRECISION (m1) < GET_MODE_UNIT_PRECISION (m2) + && convert_optab_handler (trunc_optab, m1, m2) != CODE_FOR_nothing) +{ + *code1 = code; + return true; +} + /* Now check for builtin. */ if (targetm.vectorize.builtin_conversion && targetm.vectorize.builtin_conversion (code, vectype_out, vectype_in)) Index: gcc/config/aarch64/iterators.md === --- gcc/config/aarch64/iterators.md 2019-10-17 14:23:07.71142 +0100 +++ gcc/config/aarch64/iterators.md 2019-10-25 13:27:36.189616964 +0100 @@ -860,6 +860,8 @@ (define_mode_attr VNARROWQ [(V8HI "V8QI" (V2DI "V2SI") (DI "SI") (SI "HI") (HI "QI")]) +(define_mode_attr Vnarrowq [(V8HI "v8qi") (V4SI "v4hi") + (V2DI "v2si")]) ;; Narrowed quad-modes for VQN (Used for XTN2). (define_mode_attr VNARROWQ2 [(V8HI "V16QI") (V4SI "V8HI") Index: gcc/config/aarch64/aarch64-simd.md