From: Richard Sandiford Date: Fri, 25 May 2018 06:48:47 +0000 (+0000) Subject: Add an "else" argument to IFN_COND_* functions X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=9d4ac06e0235697c7fa3144b6790b779e6385ea5;p=gcc.git Add an "else" argument to IFN_COND_* functions As suggested by Richard B, this patch changes the IFN_COND_* functions so that they take the else value of the ?: operation as a final argument, rather than always using argument 1. All current callers will still use the equivalent of argument 1, so this patch makes the SVE code assert that for now. Later patches add the general case. 2018-05-25 Richard Sandiford gcc/ * doc/md.texi: Update the documentation of the cond_* optabs to mention the new final operand. Fix GET_MODE_NUNITS call. Describe the scalar case too. * internal-fn.def (IFN_EXTRACT_LAST): Change type to fold_left. * internal-fn.c (expand_cond_unary_optab_fn): Expect 3 operands instead of 2. (expand_cond_binary_optab_fn): Expect 4 operands instead of 3. (get_conditional_internal_fn): Update comment. * tree-vect-loop.c (vectorizable_reduction): Pass the original accumulator value as a final argument to conditional functions. * config/aarch64/aarch64-sve.md (cond_): Turn into a define_expand and add an "else" operand. Assert for now that the else operand is equal to operand 2. Use SVE_INT_BINARY and SVE_COND_FP_BINARY instead of SVE_COND_INT_OP and SVE_COND_FP_OP. (*cond_): New patterns. * config/aarch64/iterators.md (UNSPEC_COND_SMAX, UNSPEC_COND_UMAX) (UNSPEC_COND_SMIN, UNSPEC_COND_UMIN, UNSPEC_COND_AND, UNSPEC_COND_ORR) (UNSPEC_COND_EOR): Delete. (optab): Remove associated mappings. (SVE_INT_BINARY): New code iterator. (sve_int_op): Remove int attribute and add "minus" to the code attribute. (SVE_COND_INT_OP): Delete. (SVE_COND_FP_OP): Rename to... (SVE_COND_FP_BINARY): ...this. From-SVN: r260707 --- diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 11784405847..c258af3d255 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,31 @@ +2018-05-25 Richard Sandiford + + * doc/md.texi: Update the documentation of the cond_* optabs + to mention the new final operand. Fix GET_MODE_NUNITS call. + Describe the scalar case too. + * internal-fn.def (IFN_EXTRACT_LAST): Change type to fold_left. + * internal-fn.c (expand_cond_unary_optab_fn): Expect 3 operands + instead of 2. + (expand_cond_binary_optab_fn): Expect 4 operands instead of 3. + (get_conditional_internal_fn): Update comment. + * tree-vect-loop.c (vectorizable_reduction): Pass the original + accumulator value as a final argument to conditional functions. + * config/aarch64/aarch64-sve.md (cond_): Turn into + a define_expand and add an "else" operand. Assert for now that + the else operand is equal to operand 2. Use SVE_INT_BINARY and + SVE_COND_FP_BINARY instead of SVE_COND_INT_OP and SVE_COND_FP_OP. + (*cond_): New patterns. + * config/aarch64/iterators.md (UNSPEC_COND_SMAX, UNSPEC_COND_UMAX) + (UNSPEC_COND_SMIN, UNSPEC_COND_UMIN, UNSPEC_COND_AND, UNSPEC_COND_ORR) + (UNSPEC_COND_EOR): Delete. + (optab): Remove associated mappings. + (SVE_INT_BINARY): New code iterator. + (sve_int_op): Remove int attribute and add "minus" to the code + attribute. + (SVE_COND_INT_OP): Delete. + (SVE_COND_FP_OP): Rename to... + (SVE_COND_FP_BINARY): ...this. + 2018-05-25 Richard Sandiford * optabs.c (can_reuse_operands_p): New function. diff --git a/gcc/config/aarch64/aarch64-sve.md b/gcc/config/aarch64/aarch64-sve.md index 5c1427d22b1..4f918492ae4 100644 --- a/gcc/config/aarch64/aarch64-sve.md +++ b/gcc/config/aarch64/aarch64-sve.md @@ -1757,14 +1757,31 @@ "\t%0., %1/m, %0., %3." ) +;; Predicated integer operations with select. +(define_expand "cond_" + [(set (match_operand:SVE_I 0 "register_operand") + (unspec:SVE_I + [(match_operand: 1 "register_operand") + (SVE_INT_BINARY:SVE_I + (match_operand:SVE_I 2 "register_operand") + (match_operand:SVE_I 3 "register_operand")) + (match_operand:SVE_I 4 "register_operand")] + UNSPEC_SEL))] + "TARGET_SVE" +{ + gcc_assert (rtx_equal_p (operands[2], operands[4])); +}) + ;; Predicated integer operations. -(define_insn "cond_" +(define_insn "*cond_" [(set (match_operand:SVE_I 0 "register_operand" "=w") (unspec:SVE_I [(match_operand: 1 "register_operand" "Upl") - (match_operand:SVE_I 2 "register_operand" "0") - (match_operand:SVE_I 3 "register_operand" "w")] - SVE_COND_INT_OP))] + (SVE_INT_BINARY:SVE_I + (match_operand:SVE_I 2 "register_operand" "0") + (match_operand:SVE_I 3 "register_operand" "w")) + (match_dup 2)] + UNSPEC_SEL))] "TARGET_SVE" "\t%0., %1/m, %0., %3." ) @@ -2536,14 +2553,35 @@ } ) +;; Predicated floating-point operations with select. +(define_expand "cond_" + [(set (match_operand:SVE_F 0 "register_operand") + (unspec:SVE_F + [(match_operand: 1 "register_operand") + (unspec:SVE_F + [(match_dup 1) + (match_operand:SVE_F 2 "register_operand") + (match_operand:SVE_F 3 "register_operand")] + SVE_COND_FP_BINARY) + (match_operand:SVE_F 4 "register_operand")] + UNSPEC_SEL))] + "TARGET_SVE" +{ + gcc_assert (rtx_equal_p (operands[2], operands[4])); +}) + ;; Predicated floating-point operations. -(define_insn "cond_" +(define_insn "*cond_" [(set (match_operand:SVE_F 0 "register_operand" "=w") (unspec:SVE_F [(match_operand: 1 "register_operand" "Upl") - (match_operand:SVE_F 2 "register_operand" "0") - (match_operand:SVE_F 3 "register_operand" "w")] - SVE_COND_FP_OP))] + (unspec:SVE_F + [(match_dup 1) + (match_operand:SVE_F 2 "register_operand" "0") + (match_operand:SVE_F 3 "register_operand" "w")] + SVE_COND_FP_BINARY) + (match_dup 2)] + UNSPEC_SEL))] "TARGET_SVE" "\t%0., %1/m, %0., %3." ) diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md index 03a0c96e572..b57c7e221f8 100644 --- a/gcc/config/aarch64/iterators.md +++ b/gcc/config/aarch64/iterators.md @@ -464,13 +464,6 @@ UNSPEC_UMUL_HIGHPART ; Used in aarch64-sve.md. UNSPEC_COND_ADD ; Used in aarch64-sve.md. UNSPEC_COND_SUB ; Used in aarch64-sve.md. - UNSPEC_COND_SMAX ; Used in aarch64-sve.md. - UNSPEC_COND_UMAX ; Used in aarch64-sve.md. - UNSPEC_COND_SMIN ; Used in aarch64-sve.md. - UNSPEC_COND_UMIN ; Used in aarch64-sve.md. - UNSPEC_COND_AND ; Used in aarch64-sve.md. - UNSPEC_COND_ORR ; Used in aarch64-sve.md. - UNSPEC_COND_EOR ; Used in aarch64-sve.md. UNSPEC_COND_LT ; Used in aarch64-sve.md. UNSPEC_COND_LE ; Used in aarch64-sve.md. UNSPEC_COND_EQ ; Used in aarch64-sve.md. @@ -1207,6 +1200,9 @@ ;; SVE floating-point unary operations. (define_code_iterator SVE_FP_UNARY [neg abs sqrt]) +(define_code_iterator SVE_INT_BINARY [plus minus smax umax smin umin + and ior xor]) + ;; SVE integer comparisons. (define_code_iterator SVE_INT_CMP [lt le eq ne ge gt ltu leu geu gtu]) @@ -1377,6 +1373,7 @@ ;; The integer SVE instruction that implements an rtx code. (define_code_attr sve_int_op [(plus "add") + (minus "sub") (neg "neg") (smin "smin") (smax "smax") @@ -1532,14 +1529,7 @@ (define_int_iterator MUL_HIGHPART [UNSPEC_SMUL_HIGHPART UNSPEC_UMUL_HIGHPART]) -(define_int_iterator SVE_COND_INT_OP [UNSPEC_COND_ADD UNSPEC_COND_SUB - UNSPEC_COND_SMAX UNSPEC_COND_UMAX - UNSPEC_COND_SMIN UNSPEC_COND_UMIN - UNSPEC_COND_AND - UNSPEC_COND_ORR - UNSPEC_COND_EOR]) - -(define_int_iterator SVE_COND_FP_OP [UNSPEC_COND_ADD UNSPEC_COND_SUB]) +(define_int_iterator SVE_COND_FP_BINARY [UNSPEC_COND_ADD UNSPEC_COND_SUB]) (define_int_iterator SVE_COND_FP_CMP [UNSPEC_COND_LT UNSPEC_COND_LE UNSPEC_COND_EQ UNSPEC_COND_NE @@ -1569,14 +1559,7 @@ (UNSPEC_IORV "ior") (UNSPEC_XORV "xor") (UNSPEC_COND_ADD "add") - (UNSPEC_COND_SUB "sub") - (UNSPEC_COND_SMAX "smax") - (UNSPEC_COND_UMAX "umax") - (UNSPEC_COND_SMIN "smin") - (UNSPEC_COND_UMIN "umin") - (UNSPEC_COND_AND "and") - (UNSPEC_COND_ORR "ior") - (UNSPEC_COND_EOR "xor")]) + (UNSPEC_COND_SUB "sub")]) (define_int_attr maxmin_uns [(UNSPEC_UMAXV "umax") (UNSPEC_UMINV "umin") @@ -1787,15 +1770,5 @@ (UNSPEC_COND_GE "ge") (UNSPEC_COND_GT "gt")]) -(define_int_attr sve_int_op [(UNSPEC_COND_ADD "add") - (UNSPEC_COND_SUB "sub") - (UNSPEC_COND_SMAX "smax") - (UNSPEC_COND_UMAX "umax") - (UNSPEC_COND_SMIN "smin") - (UNSPEC_COND_UMIN "umin") - (UNSPEC_COND_AND "and") - (UNSPEC_COND_ORR "orr") - (UNSPEC_COND_EOR "eor")]) - (define_int_attr sve_fp_op [(UNSPEC_COND_ADD "fadd") (UNSPEC_COND_SUB "fsub")]) diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi index 30f1e09a310..ce46320b418 100644 --- a/gcc/doc/md.texi +++ b/gcc/doc/md.texi @@ -6349,13 +6349,21 @@ operand 0, otherwise (operand 2 + operand 3) is moved. @itemx @samp{cond_smax@var{mode}} @itemx @samp{cond_umin@var{mode}} @itemx @samp{cond_umax@var{mode}} -Perform an elementwise operation on vector operands 2 and 3, -under the control of the vector mask in operand 1, and store the result -in operand 0. This is equivalent to: +When operand 1 is true, perform an operation on operands 2 and 3 and +store the result in operand 0, otherwise store operand 4 in operand 0. +The operation works elementwise if the operands are vectors. + +The scalar case is equivalent to: + +@smallexample +op0 = op1 ? op2 @var{op} op3 : op4; +@end smallexample + +while the vector case is equivalent to: @smallexample -for (i = 0; i < GET_MODE_NUNITS (@var{n}); i++) - op0[i] = op1[i] ? op2[i] @var{op} op3[i] : op2[i]; +for (i = 0; i < GET_MODE_NUNITS (@var{m}); i++) + op0[i] = op1[i] ? op2[i] @var{op} op3[i] : op4[i]; @end smallexample where, for example, @var{op} is @code{+} for @samp{cond_add@var{mode}}. @@ -6364,8 +6372,9 @@ When defined for floating-point modes, the contents of @samp{op3[i]} are not interpreted if @var{op1[i]} is false, just like they would not be in a normal C @samp{?:} condition. -Operands 0, 2 and 3 all have mode @var{m}, while operand 1 has the mode -returned by @code{TARGET_VECTORIZE_GET_MASK_MODE}. +Operands 0, 2, 3 and 4 all have mode @var{m}. Operand 1 is a scalar +integer if @var{m} is scalar, otherwise it has the mode returned by +@code{TARGET_VECTORIZE_GET_MASK_MODE}. @cindex @code{neg@var{mode}cc} instruction pattern @item @samp{neg@var{mode}cc} diff --git a/gcc/internal-fn.c b/gcc/internal-fn.c index bb4404ed290..6765a770819 100644 --- a/gcc/internal-fn.c +++ b/gcc/internal-fn.c @@ -2988,10 +2988,10 @@ expand_while_optab_fn (internal_fn, gcall *stmt, convert_optab optab) expand_direct_optab_fn (FN, STMT, OPTAB, 3) #define expand_cond_unary_optab_fn(FN, STMT, OPTAB) \ - expand_direct_optab_fn (FN, STMT, OPTAB, 2) + expand_direct_optab_fn (FN, STMT, OPTAB, 3) #define expand_cond_binary_optab_fn(FN, STMT, OPTAB) \ - expand_direct_optab_fn (FN, STMT, OPTAB, 3) + expand_direct_optab_fn (FN, STMT, OPTAB, 4) #define expand_fold_extract_optab_fn(FN, STMT, OPTAB) \ expand_direct_optab_fn (FN, STMT, OPTAB, 3) @@ -3219,12 +3219,19 @@ static void (*const internal_fn_expanders[]) (internal_fn, gcall *) = { 0 }; -/* Return a function that performs the conditional form of CODE, i.e.: +/* Return a function that only performs CODE when a certain condition is met + and that uses a given fallback value otherwise. For example, if CODE is + a binary operation associated with conditional function FN: + + LHS = FN (COND, A, B, ELSE) + + is equivalent to the C expression: + + LHS = COND ? A CODE B : ELSE; - LHS = RHS1 ? RHS2 CODE RHS3 : RHS2 + operating elementwise if the operands are vectors. - (operating elementwise if the operands are vectors). Return IFN_LAST - if no such function exists. */ + Return IFN_LAST if no such function exists. */ internal_fn get_conditional_internal_fn (tree_code code) diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def index a5f85048490..c56b731addb 100644 --- a/gcc/internal-fn.def +++ b/gcc/internal-fn.def @@ -173,7 +173,7 @@ DEF_INTERNAL_OPTAB_FN (REDUC_XOR, ECF_CONST | ECF_NOTHROW, /* Extract the last active element from a vector. */ DEF_INTERNAL_OPTAB_FN (EXTRACT_LAST, ECF_CONST | ECF_NOTHROW, - extract_last, cond_unary) + extract_last, fold_left) /* Same, but return the first argument if no elements are active. */ DEF_INTERNAL_OPTAB_FN (FOLD_EXTRACT_LAST, ECF_CONST | ECF_NOTHROW, diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c index 0caa6e4c7dd..2507bbcb1f1 100644 --- a/gcc/tree-vect-loop.c +++ b/gcc/tree-vect-loop.c @@ -7222,8 +7222,9 @@ vectorizable_reduction (gimple *stmt, gimple_stmt_iterator *gsi, } tree mask = vect_get_loop_mask (gsi, masks, vec_num * ncopies, vectype_in, i * ncopies + j); - gcall *call = gimple_build_call_internal (cond_fn, 3, mask, - vop[0], vop[1]); + gcall *call = gimple_build_call_internal (cond_fn, 4, mask, + vop[0], vop[1], + vop[0]); new_temp = make_ssa_name (vec_dest, call); gimple_call_set_lhs (call, new_temp); gimple_call_set_nothrow (call, true);