From: Richard Sandiford Date: Mon, 6 Nov 2017 20:02:49 +0000 (+0000) Subject: [AArch64] Pass number of units to aarch64_expand_vec_perm(_const) X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=8094001759f757a5dc7ce375e4d1e5fd0d9a2a8e;p=gcc.git [AArch64] Pass number of units to aarch64_expand_vec_perm(_const) This patch passes the number of units to aarch64_expand_vec_perm and aarch64_expand_vec_perm_const, which avoids a to_constant () once GET_MODE_NUNITS is variable. 2017-11-06 Richard Sandiford Alan Hayward David Sherwood gcc/ * config/aarch64/aarch64-protos.h (aarch64_expand_vec_perm) (aarch64_expand_vec_perm_const): Take the number of units too. * config/aarch64/aarch64.c (aarch64_expand_vec_perm) (aarch64_expand_vec_perm_const): Likewise. * config/aarch64/aarch64-simd.md (vec_perm_const) (vec_perm): Update accordingly. Reviewed-by: James Greenhalgh Co-Authored-By: Alan Hayward Co-Authored-By: David Sherwood From-SVN: r254469 --- diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 5d11224126d..46bffaee9c3 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,14 @@ +2017-11-06 Richard Sandiford + Alan Hayward + David Sherwood + + * config/aarch64/aarch64-protos.h (aarch64_expand_vec_perm) + (aarch64_expand_vec_perm_const): Take the number of units too. + * config/aarch64/aarch64.c (aarch64_expand_vec_perm) + (aarch64_expand_vec_perm_const): Likewise. + * config/aarch64/aarch64-simd.md (vec_perm_const) + (vec_perm): Update accordingly. + 2017-11-06 Richard Sandiford Alan Hayward David Sherwood diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h index 4fdded76dac..15c3b46ebef 100644 --- a/gcc/config/aarch64/aarch64-protos.h +++ b/gcc/config/aarch64/aarch64-protos.h @@ -471,11 +471,11 @@ tree aarch64_builtin_rsqrt (unsigned int); tree aarch64_builtin_vectorized_function (unsigned int, tree, tree); extern void aarch64_split_combinev16qi (rtx operands[3]); -extern void aarch64_expand_vec_perm (rtx target, rtx op0, rtx op1, rtx sel); +extern void aarch64_expand_vec_perm (rtx, rtx, rtx, rtx, unsigned int); extern bool aarch64_madd_needs_nop (rtx_insn *); extern void aarch64_final_prescan_insn (rtx_insn *); extern bool -aarch64_expand_vec_perm_const (rtx target, rtx op0, rtx op1, rtx sel); +aarch64_expand_vec_perm_const (rtx, rtx, rtx, rtx, unsigned int); void aarch64_atomic_assign_expand_fenv (tree *, tree *, tree *); int aarch64_ccmp_mode_to_code (machine_mode mode); diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md index 0699e56e6e8..9aeeffd27b0 100644 --- a/gcc/config/aarch64/aarch64-simd.md +++ b/gcc/config/aarch64/aarch64-simd.md @@ -5239,7 +5239,7 @@ "TARGET_SIMD" { if (aarch64_expand_vec_perm_const (operands[0], operands[1], - operands[2], operands[3])) + operands[2], operands[3], )) DONE; else FAIL; @@ -5253,7 +5253,7 @@ "TARGET_SIMD" { aarch64_expand_vec_perm (operands[0], operands[1], - operands[2], operands[3]); + operands[2], operands[3], ); DONE; }) diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c index d209f816663..62ce7d69bf1 100644 --- a/gcc/config/aarch64/aarch64.c +++ b/gcc/config/aarch64/aarch64.c @@ -13242,11 +13242,14 @@ aarch64_expand_vec_perm_1 (rtx target, rtx op0, rtx op1, rtx sel) } } +/* Expand a vec_perm with the operands given by TARGET, OP0, OP1 and SEL. + NELT is the number of elements in the vector. */ + void -aarch64_expand_vec_perm (rtx target, rtx op0, rtx op1, rtx sel) +aarch64_expand_vec_perm (rtx target, rtx op0, rtx op1, rtx sel, + unsigned int nelt) { machine_mode vmode = GET_MODE (target); - unsigned int nelt = GET_MODE_NUNITS (vmode); bool one_vector_p = rtx_equal_p (op0, op1); rtx mask; @@ -13602,13 +13605,15 @@ aarch64_expand_vec_perm_const_1 (struct expand_vec_perm_d *d) return false; } -/* Expand a vec_perm_const pattern. */ +/* Expand a vec_perm_const pattern with the operands given by TARGET, + OP0, OP1 and SEL. NELT is the number of elements in the vector. */ bool -aarch64_expand_vec_perm_const (rtx target, rtx op0, rtx op1, rtx sel) +aarch64_expand_vec_perm_const (rtx target, rtx op0, rtx op1, rtx sel, + unsigned int nelt) { struct expand_vec_perm_d d; - int i, nelt, which; + unsigned int i, which; d.target = target; d.op0 = op0; @@ -13618,12 +13623,11 @@ aarch64_expand_vec_perm_const (rtx target, rtx op0, rtx op1, rtx sel) gcc_assert (VECTOR_MODE_P (d.vmode)); d.testing_p = false; - nelt = GET_MODE_NUNITS (d.vmode); d.perm.reserve (nelt); for (i = which = 0; i < nelt; ++i) { rtx e = XVECEXP (sel, 0, i); - int ei = INTVAL (e) & (2 * nelt - 1); + unsigned int ei = INTVAL (e) & (2 * nelt - 1); which |= (ei < nelt ? 1 : 2); d.perm.quick_push (ei); }