2010-08-05 Julian Brown Backport from mainline (candidate patch): gcc/ * expr.c (expand_assignment): Add assertion to prevent emitting null rtx for movmisalign pattern. (expand_expr_real_1): Likewise. * config/arm/arm.c (arm_builtin_support_vector_misalignment): New. (TARGET_VECTORIZE_SUPPORT_VECTOR_MISALIGNMENT): New. Use above. (arm_vector_alignment_reachable): New. (TARGET_VECTORIZE_VECTOR_ALIGNMENT_REACHABLE): New. Use above. (neon_vector_mem_operand): Disallow PRE_DEC for misaligned loads. (arm_print_operand): Include alignment qualifier in %A. * config/arm/neon.md (UNSPEC_MISALIGNED_ACCESS): New constant. (movmisalign): New expander. (movmisalign_neon_store, movmisalign_neon_load): New insn patterns. gcc/testsuite/ * gcc.dg/vect/vect-42.c: Use vect_element_align instead of vect_hw_misalign. * gcc.dg/vect/vect-60.c: Likewise. * gcc.dg/vect/vect-56.c: Likewise. * gcc.dg/vect/vect-93.c: Likewise. * gcc.dg/vect/no-scevccp-outer-8.c: Likewise. * gcc.dg/vect/vect-95.c: Likewise. * gcc.dg/vect/vect-96.c: Likewise. * gcc.dg/vect/vect-outer-5.c: Use quad-word vectors when available. * gcc.dg/vect/slp-25.c: Likewise. * gcc.dg/vect/slp-3.c: Likewise. * gcc.dg/vect/vect-multitypes-1.c: Likewise. * gcc.dg/vect/no-vfa-pr29145.c: Likewise. * gcc.dg/vect/vect-multitypes-4.c: Likewise. Use vect_element_align. * gcc.dg/vect/vect-109.c: Likewise. * gcc.dg/vect/vect-peel-1.c: Likewise. * gcc.dg/vect/vect-peel-2.c: Likewise. * lib/target-supports.exp (check_effective_target_arm_vect_no_misalign): New. (check_effective_target_vect_no_align): Use above. (check_effective_target_vect_element_align): New. (add_options_for_quad_vectors): New. 2010-08-05 Jie Zhang Issue #7257 === modified file 'gcc/config/arm/arm.c' --- old/gcc/config/arm/arm.c 2010-08-16 09:41:58 +0000 +++ new/gcc/config/arm/arm.c 2010-08-20 16:21:01 +0000 @@ -228,6 +228,11 @@ static void arm_trampoline_init (rtx, tree, rtx); static rtx arm_trampoline_adjust_address (rtx); static rtx arm_pic_static_addr (rtx orig, rtx reg); +static bool arm_vector_alignment_reachable (const_tree type, bool is_packed); +static bool arm_builtin_support_vector_misalignment (enum machine_mode mode, + const_tree type, + int misalignment, + bool is_packed); /* Table of machine attributes. */ @@ -514,6 +519,14 @@ #undef TARGET_CAN_ELIMINATE #define TARGET_CAN_ELIMINATE arm_can_eliminate +#undef TARGET_VECTOR_ALIGNMENT_REACHABLE +#define TARGET_VECTOR_ALIGNMENT_REACHABLE \ + arm_vector_alignment_reachable + +#undef TARGET_SUPPORT_VECTOR_MISALIGNMENT +#define TARGET_SUPPORT_VECTOR_MISALIGNMENT \ + arm_builtin_support_vector_misalignment + struct gcc_target targetm = TARGET_INITIALIZER; /* Obstack for minipool constant handling. */ @@ -9084,7 +9097,8 @@ return arm_address_register_rtx_p (ind, 0); /* Allow post-increment with Neon registers. */ - if (type != 1 && (GET_CODE (ind) == POST_INC || GET_CODE (ind) == PRE_DEC)) + if ((type != 1 && GET_CODE (ind) == POST_INC) + || (type == 0 && GET_CODE (ind) == PRE_DEC)) return arm_address_register_rtx_p (XEXP (ind, 0), 0); /* FIXME: vld1 allows register post-modify. */ @@ -16365,6 +16379,8 @@ { rtx addr; bool postinc = FALSE; + unsigned align, modesize, align_bits; + gcc_assert (GET_CODE (x) == MEM); addr = XEXP (x, 0); if (GET_CODE (addr) == POST_INC) @@ -16372,7 +16388,29 @@ postinc = 1; addr = XEXP (addr, 0); } - asm_fprintf (stream, "[%r]", REGNO (addr)); + asm_fprintf (stream, "[%r", REGNO (addr)); + + /* We know the alignment of this access, so we can emit a hint in the + instruction (for some alignments) as an aid to the memory subsystem + of the target. */ + align = MEM_ALIGN (x) >> 3; + modesize = GET_MODE_SIZE (GET_MODE (x)); + + /* Only certain alignment specifiers are supported by the hardware. */ + if (modesize == 16 && (align % 32) == 0) + align_bits = 256; + else if ((modesize == 8 || modesize == 16) && (align % 16) == 0) + align_bits = 128; + else if ((align % 8) == 0) + align_bits = 64; + else + align_bits = 0; + + if (align_bits != 0) + asm_fprintf (stream, ", :%d", align_bits); + + asm_fprintf (stream, "]"); + if (postinc) fputs("!", stream); } @@ -22450,4 +22488,43 @@ return !TARGET_THUMB1; } +static bool +arm_vector_alignment_reachable (const_tree type, bool is_packed) +{ + /* Vectors which aren't in packed structures will not be less aligned than + the natural alignment of their element type, so this is safe. */ + if (TARGET_NEON && !BYTES_BIG_ENDIAN) + return !is_packed; + + return default_builtin_vector_alignment_reachable (type, is_packed); +} + +static bool +arm_builtin_support_vector_misalignment (enum machine_mode mode, + const_tree type, int misalignment, + bool is_packed) +{ + if (TARGET_NEON && !BYTES_BIG_ENDIAN) + { + HOST_WIDE_INT align = TYPE_ALIGN_UNIT (type); + + if (is_packed) + return align == 1; + + /* If the misalignment is unknown, we should be able to handle the access + so long as it is not to a member of a packed data structure. */ + if (misalignment == -1) + return true; + + /* Return true if the misalignment is a multiple of the natural alignment + of the vector's element type. This is probably always going to be + true in practice, since we've already established that this isn't a + packed access. */ + return ((misalignment % align) == 0); + } + + return default_builtin_support_vector_misalignment (mode, type, misalignment, + is_packed); +} + #include "gt-arm.h" === modified file 'gcc/config/arm/neon.md' --- old/gcc/config/arm/neon.md 2010-08-13 11:40:17 +0000 +++ new/gcc/config/arm/neon.md 2010-08-20 16:21:01 +0000 @@ -140,7 +140,8 @@ (UNSPEC_VUZP1 201) (UNSPEC_VUZP2 202) (UNSPEC_VZIP1 203) - (UNSPEC_VZIP2 204)]) + (UNSPEC_VZIP2 204) + (UNSPEC_MISALIGNED_ACCESS 205)]) ;; Double-width vector modes. (define_mode_iterator VD [V8QI V4HI V2SI V2SF]) @@ -660,6 +661,52 @@ neon_disambiguate_copy (operands, dest, src, 4); }) +(define_expand "movmisalign" + [(set (match_operand:VDQX 0 "nonimmediate_operand" "") + (unspec:VDQX [(match_operand:VDQX 1 "general_operand" "")] + UNSPEC_MISALIGNED_ACCESS))] + "TARGET_NEON && !BYTES_BIG_ENDIAN" +{ + /* This pattern is not permitted to fail during expansion: if both arguments + are non-registers (e.g. memory := constant, which can be created by the + auto-vectorizer), force operand 1 into a register. */ + if (!s_register_operand (operands[0], mode) + && !s_register_operand (operands[1], mode)) + operands[1] = force_reg (mode, operands[1]); +}) + +(define_insn "*movmisalign_neon_store" + [(set (match_operand:VDX 0 "memory_operand" "=Um") + (unspec:VDX [(match_operand:VDX 1 "s_register_operand" " w")] + UNSPEC_MISALIGNED_ACCESS))] + "TARGET_NEON && !BYTES_BIG_ENDIAN" + "vst1.\t{%P1}, %A0" + [(set_attr "neon_type" "neon_vst1_1_2_regs_vst2_2_regs")]) + +(define_insn "*movmisalign_neon_load" + [(set (match_operand:VDX 0 "s_register_operand" "=w") + (unspec:VDX [(match_operand:VDX 1 "memory_operand" " Um")] + UNSPEC_MISALIGNED_ACCESS))] + "TARGET_NEON && !BYTES_BIG_ENDIAN" + "vld1.\t{%P0}, %A1" + [(set_attr "neon_type" "neon_vld1_1_2_regs")]) + +(define_insn "*movmisalign_neon_store" + [(set (match_operand:VQX 0 "memory_operand" "=Um") + (unspec:VQX [(match_operand:VQX 1 "s_register_operand" " w")] + UNSPEC_MISALIGNED_ACCESS))] + "TARGET_NEON && !BYTES_BIG_ENDIAN" + "vst1.\t{%q1}, %A0" + [(set_attr "neon_type" "neon_vst1_1_2_regs_vst2_2_regs")]) + +(define_insn "*movmisalign_neon_load" + [(set (match_operand:VQX 0 "s_register_operand" "=w") + (unspec:VQX [(match_operand:VQX 1 "memory_operand" " Um")] + UNSPEC_MISALIGNED_ACCESS))] + "TARGET_NEON && !BYTES_BIG_ENDIAN" + "vld1.\t{%q0}, %A1" + [(set_attr "neon_type" "neon_vld1_1_2_regs")]) + (define_insn "vec_set_internal" [(set (match_operand:VD 0 "s_register_operand" "=w") (vec_merge:VD === modified file 'gcc/expr.c' --- old/gcc/expr.c 2010-08-12 13:51:16 +0000 +++ new/gcc/expr.c 2010-08-20 16:21:01 +0000 @@ -4362,7 +4362,10 @@ && op_mode1 != VOIDmode) reg = copy_to_mode_reg (op_mode1, reg); - insn = GEN_FCN (icode) (mem, reg); + insn = GEN_FCN (icode) (mem, reg); + /* The movmisalign pattern cannot fail, else the assignment would + silently be omitted. */ + gcc_assert (insn != NULL_RTX); emit_insn (insn); return; } @@ -8742,6 +8745,7 @@ /* Nor can the insn generator. */ insn = GEN_FCN (icode) (reg, temp); + gcc_assert (insn != NULL_RTX); emit_insn (insn); return reg; === modified file 'gcc/testsuite/gcc.dg/vect/no-scevccp-outer-8.c' --- old/gcc/testsuite/gcc.dg/vect/no-scevccp-outer-8.c 2009-06-05 14:28:50 +0000 +++ new/gcc/testsuite/gcc.dg/vect/no-scevccp-outer-8.c 2010-08-20 16:21:01 +0000 @@ -46,5 +46,5 @@ return 0; } -/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED." 1 "vect" { xfail { ! { vect_hw_misalign } } } } } */ +/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED." 1 "vect" { xfail { ! { vect_element_align } } } } } */ /* { dg-final { cleanup-tree-dump "vect" } } */ === modified file 'gcc/testsuite/gcc.dg/vect/no-vfa-pr29145.c' --- old/gcc/testsuite/gcc.dg/vect/no-vfa-pr29145.c 2008-08-18 19:36:03 +0000 +++ new/gcc/testsuite/gcc.dg/vect/no-vfa-pr29145.c 2010-08-20 16:21:01 +0000 @@ -1,4 +1,5 @@ /* { dg-require-effective-target vect_int } */ +/* { dg-add-options quad_vectors } */ #include #include "tree-vect.h" === modified file 'gcc/testsuite/gcc.dg/vect/slp-25.c' --- old/gcc/testsuite/gcc.dg/vect/slp-25.c 2009-10-27 11:46:07 +0000 +++ new/gcc/testsuite/gcc.dg/vect/slp-25.c 2010-08-20 16:21:01 +0000 @@ -1,4 +1,5 @@ /* { dg-require-effective-target vect_int } */ +/* { dg-add-options quad_vectors } */ #include #include "tree-vect.h" === modified file 'gcc/testsuite/gcc.dg/vect/slp-3.c' --- old/gcc/testsuite/gcc.dg/vect/slp-3.c 2009-05-12 13:05:28 +0000 +++ new/gcc/testsuite/gcc.dg/vect/slp-3.c 2010-08-20 16:21:01 +0000 @@ -1,4 +1,5 @@ /* { dg-require-effective-target vect_int } */ +/* { dg-add-options quad_vectors } */ #include #include === modified file 'gcc/testsuite/gcc.dg/vect/vect-109.c' --- old/gcc/testsuite/gcc.dg/vect/vect-109.c 2010-07-10 20:38:32 +0000 +++ new/gcc/testsuite/gcc.dg/vect/vect-109.c 2010-08-20 16:21:01 +0000 @@ -1,4 +1,5 @@ /* { dg-require-effective-target vect_int } */ +/* { dg-add-options quad_vectors } */ #include #include "tree-vect.h" @@ -72,8 +73,8 @@ return 0; } -/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { target vect_hw_misalign } } } */ -/* { dg-final { scan-tree-dump-times "not vectorized: unsupported unaligned store" 2 "vect" { xfail vect_hw_misalign } } } */ -/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 10 "vect" { target vect_hw_misalign } } } */ +/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { target vect_element_align } } } */ +/* { dg-final { scan-tree-dump-times "not vectorized: unsupported unaligned store" 2 "vect" { xfail vect_element_align } } } */ +/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 10 "vect" { target vect_element_align } } } */ /* { dg-final { cleanup-tree-dump "vect" } } */ === modified file 'gcc/testsuite/gcc.dg/vect/vect-42.c' --- old/gcc/testsuite/gcc.dg/vect/vect-42.c 2009-11-04 10:22:22 +0000 +++ new/gcc/testsuite/gcc.dg/vect/vect-42.c 2010-08-20 16:21:01 +0000 @@ -64,7 +64,7 @@ /* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" } } */ /* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 3 "vect" { target vect_no_align } } } */ -/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 1 "vect" { target { { ! vector_alignment_reachable } && { ! vect_hw_misalign } } } } } */ +/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 1 "vect" { target { { ! vector_alignment_reachable } && { ! vect_element_align } } } } } */ /* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { xfail { vect_no_align || { ! vector_alignment_reachable } } } } } */ /* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_no_align || { ! vector_alignment_reachable } } } } } */ /* { dg-final { cleanup-tree-dump "vect" } } */ === modified file 'gcc/testsuite/gcc.dg/vect/vect-95.c' --- old/gcc/testsuite/gcc.dg/vect/vect-95.c 2009-10-27 11:46:07 +0000 +++ new/gcc/testsuite/gcc.dg/vect/vect-95.c 2010-08-20 16:21:01 +0000 @@ -56,14 +56,14 @@ } /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */ -/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" { xfail {vect_hw_misalign} } } } */ +/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" { xfail {vect_element_align} } } } */ /* For targets that support unaligned loads we version for the two unaligned stores and generate misaligned accesses for the loads. For targets that don't support unaligned loads we version for all four accesses. */ -/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align || vect_hw_misalign} } } } */ -/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { xfail { vect_no_align || vect_hw_misalign } } } } */ +/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align || vect_element_align} } } } */ +/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { xfail { vect_no_align || vect_element_align } } } } */ /* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" { target vect_no_align } } } */ /* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 4 "vect" { target vect_no_align } } } */ /* { dg-final { cleanup-tree-dump "vect" } } */ === modified file 'gcc/testsuite/gcc.dg/vect/vect-96.c' --- old/gcc/testsuite/gcc.dg/vect/vect-96.c 2009-10-27 11:46:07 +0000 +++ new/gcc/testsuite/gcc.dg/vect/vect-96.c 2010-08-20 16:21:01 +0000 @@ -45,5 +45,5 @@ /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */ /* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target { {! vect_no_align} && vector_alignment_reachable } } } } */ /* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { { vect_no_align } || {! vector_alignment_reachable} } } } } */ -/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { vect_no_align || { {! vector_alignment_reachable} && {! vect_hw_misalign} } } } } } */ +/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { vect_no_align || { {! vector_alignment_reachable} && {! vect_element_align} } } } } } */ /* { dg-final { cleanup-tree-dump "vect" } } */ === modified file 'gcc/testsuite/gcc.dg/vect/vect-multitypes-1.c' --- old/gcc/testsuite/gcc.dg/vect/vect-multitypes-1.c 2009-10-27 11:46:07 +0000 +++ new/gcc/testsuite/gcc.dg/vect/vect-multitypes-1.c 2010-08-20 16:21:01 +0000 @@ -1,4 +1,5 @@ /* { dg-require-effective-target vect_int } */ +/* { dg-add-options quad_vectors } */ #include #include "tree-vect.h" @@ -78,11 +79,11 @@ return 0; } -/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { xfail {! vect_hw_misalign} } } } */ -/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align || vect_hw_misalign } } } } */ -/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail {! vect_hw_misalign} } } } */ -/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_no_align || vect_hw_misalign } } } } */ +/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { xfail {! vect_element_align} } } } */ +/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align || vect_element_align } } } } */ +/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail {! vect_element_align} } } } */ +/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_no_align || vect_element_align } } } } */ /* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { xfail *-*-* } } } */ -/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align || vect_hw_misalign } } } } */ +/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { vect_no_align || vect_element_align } } } } */ /* { dg-final { cleanup-tree-dump "vect" } } */ === modified file 'gcc/testsuite/gcc.dg/vect/vect-multitypes-4.c' --- old/gcc/testsuite/gcc.dg/vect/vect-multitypes-4.c 2009-10-27 11:46:07 +0000 +++ new/gcc/testsuite/gcc.dg/vect/vect-multitypes-4.c 2010-08-20 16:21:01 +0000 @@ -1,4 +1,5 @@ /* { dg-require-effective-target vect_int } */ +/* { dg-add-options quad_vectors } */ #include #include "tree-vect.h" @@ -85,11 +86,11 @@ return 0; } -/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { xfail {! vect_hw_misalign} } } } */ -/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align || vect_hw_misalign } } } } */ -/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail {! vect_hw_misalign} } } } */ -/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_no_align || vect_hw_misalign } } } } */ +/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { xfail {! vect_element_align} } } } */ +/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align || vect_element_align } } } } */ +/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail {! vect_element_align} } } } */ +/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_no_align || vect_element_align } } } } */ /* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 8 "vect" { xfail *-*-* } } } */ -/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { xfail { vect_no_align || vect_hw_misalign } } } } */ +/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { xfail { vect_no_align || vect_element_align } } } } */ /* { dg-final { cleanup-tree-dump "vect" } } */ === modified file 'gcc/testsuite/gcc.dg/vect/vect-outer-5.c' --- old/gcc/testsuite/gcc.dg/vect/vect-outer-5.c 2009-05-08 12:39:01 +0000 +++ new/gcc/testsuite/gcc.dg/vect/vect-outer-5.c 2010-08-20 16:21:01 +0000 @@ -1,4 +1,5 @@ /* { dg-require-effective-target vect_float } */ +/* { dg-add-options quad_vectors } */ #include #include === modified file 'gcc/testsuite/lib/target-supports.exp' --- old/gcc/testsuite/lib/target-supports.exp 2010-08-10 13:31:21 +0000 +++ new/gcc/testsuite/lib/target-supports.exp 2010-08-20 16:21:01 +0000 @@ -1642,6 +1642,18 @@ }] } +# Return 1 if this is an ARM target that only supports aligned vector accesses +proc check_effective_target_arm_vect_no_misalign { } { + return [check_no_compiler_messages arm_vect_no_misalign assembly { + #if !defined(__arm__) \ + || (defined(__ARMEL__) \ + && (!defined(__thumb__) || defined(__thumb2__))) + #error FOO + #endif + }] +} + + # Return 1 if this is an ARM target supporting -mfpu=vfp # -mfloat-abi=softfp. Some multilibs may be incompatible with these # options. @@ -2547,7 +2559,7 @@ if { [istarget mipsisa64*-*-*] || [istarget sparc*-*-*] || [istarget ia64-*-*] - || [check_effective_target_arm32] } { + || [check_effective_target_arm_vect_no_misalign] } { set et_vect_no_align_saved 1 } } @@ -2682,6 +2694,25 @@ return $et_vector_alignment_reachable_for_64bit_saved } +# Return 1 if the target only requires element alignment for vector accesses + +proc check_effective_target_vect_element_align { } { + global et_vect_element_align + + if [info exists et_vect_element_align] { + verbose "check_effective_target_vect_element_align: using cached result" 2 + } else { + set et_vect_element_align 0 + if { [istarget arm*-*-*] + || [check_effective_target_vect_hw_misalign] } { + set et_vect_element_align 1 + } + } + + verbose "check_effective_target_vect_element_align: returning $et_vect_element_align" 2 + return $et_vect_element_align +} + # Return 1 if the target supports vector conditional operations, 0 otherwise. proc check_effective_target_vect_condition { } { @@ -3239,6 +3270,16 @@ return $flags } +# Add to FLAGS the flags needed to enable 128-bit vectors. + +proc add_options_for_quad_vectors { flags } { + if [is-effective-target arm_neon_ok] { + return "$flags -mvectorize-with-neon-quad" + } + + return $flags +} + # Return 1 if the target provides a full C99 runtime. proc check_effective_target_c99_runtime { } {