From c8d61ab863c188267b8bab3c4d0db2b9e91047c0 Mon Sep 17 00:00:00 2001 From: Thomas Preud'homme Date: Fri, 14 Jul 2017 15:26:09 +0000 Subject: [PATCH] [ARM] Rewire -mfpu=fp-armv8 as VFPv5 + D32 + DP fp-armv8 is currently defined as a double precision FPv5 with 32 D registers *and* a special FP_ARMv8 bit. However FP for ARMv8 should only bring 32 D registers on top of FPv5-D16 so this FP_ARMv8 bit is spurious. As a consequence, many instruction patterns which are guarded by TARGET_FPU_ARMV8 are unavailable to FPv5-D16 and FPv5-SP-D16. This commit gets rid of TARGET_FPU_ARMV8 and rewire all uses to expressions based on TARGET_VFP5, TARGET_VFPD32 and TARGET_VFP_DOUBLE. It also redefine ISA_FP_ARMv8 to include the D32 capability to distinguish it from FPv5-D16. At last, it sets the +fp.sp for ARMv8-R to enable FPv5-SP-D16 (ie FP for ARMv8 with single precision only and 16 D registers). 2017-07-14 Thomas Preud'homme gcc/ * config/arm/arm-isa.h (isa_bit_FP_ARMv8): Delete enumerator. (ISA_FP_ARMv8): Define as ISA_FPv5 and ISA_FP_D32. * config/arm/arm-cpus.in (armv8-r): Define fp.sp as enabling FPv5. (fp-armv8): Define it as FP_ARMv8 only. config/arm/arm.h (TARGET_FPU_ARMV8): Delete. (TARGET_VFP_FP16INST): Define using TARGET_VFP5 rather than TARGET_FPU_ARMV8. config/arm/arm.c (arm_rtx_costs_internal): Replace checks against TARGET_FPU_ARMV8 by checks against TARGET_VFP5. * config/arm/arm-builtins.c (arm_builtin_vectorized_function): Define first ARM_CHECK_BUILTIN_MODE definition using TARGET_VFP5 rather than TARGET_FPU_ARMV8. * config/arm/arm-c.c (arm_cpu_builtins): Likewise for __ARM_FEATURE_NUMERIC_MAXMIN macro definition. * config/arm/arm.md (cmov): Condition on TARGET_VFP5 rather than TARGET_FPU_ARMV8. * config/arm/neon.md (neon_vrint): Likewise. (neon_vcvt): Likewise. (neon_): Likewise. (3): Likewise. * config/arm/vfp.md (lsi2): Likewise. * config/arm/predicates.md (arm_cond_move_operator): Check against TARGET_VFP5 rather than TARGET_FPU_ARMV8 and fix spacing. From-SVN: r250204 --- gcc/ChangeLog | 26 ++++++++++++++++++++++++++ gcc/config/arm/arm-builtins.c | 2 +- gcc/config/arm/arm-c.c | 2 +- gcc/config/arm/arm-cpus.in | 4 ++-- gcc/config/arm/arm-isa.h | 5 ++--- gcc/config/arm/arm.c | 4 ++-- gcc/config/arm/arm.h | 6 +----- gcc/config/arm/arm.md | 2 +- gcc/config/arm/neon.md | 8 ++++---- gcc/config/arm/predicates.md | 6 +++--- gcc/config/arm/vfp.md | 2 +- 11 files changed, 44 insertions(+), 23 deletions(-) diff --git a/gcc/ChangeLog b/gcc/ChangeLog index c2f3eebe8fa..51bd2c2d322 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,29 @@ +2017-07-14 Thomas Preud'homme + + * config/arm/arm-isa.h (isa_bit_FP_ARMv8): Delete enumerator. + (ISA_FP_ARMv8): Define as ISA_FPv5 and ISA_FP_D32. + * config/arm/arm-cpus.in (armv8-r): Define fp.sp as enabling FPv5. + (fp-armv8): Define it as FP_ARMv8 only. + config/arm/arm.h (TARGET_FPU_ARMV8): Delete. + (TARGET_VFP_FP16INST): Define using TARGET_VFP5 rather than + TARGET_FPU_ARMV8. + config/arm/arm.c (arm_rtx_costs_internal): Replace checks against + TARGET_FPU_ARMV8 by checks against TARGET_VFP5. + * config/arm/arm-builtins.c (arm_builtin_vectorized_function): Define + first ARM_CHECK_BUILTIN_MODE definition using TARGET_VFP5 rather + than TARGET_FPU_ARMV8. + * config/arm/arm-c.c (arm_cpu_builtins): Likewise for + __ARM_FEATURE_NUMERIC_MAXMIN macro definition. + * config/arm/arm.md (cmov): Condition on TARGET_VFP5 rather than + TARGET_FPU_ARMV8. + * config/arm/neon.md (neon_vrint): Likewise. + (neon_vcvt): Likewise. + (neon_): Likewise. + (3): Likewise. + * config/arm/vfp.md (lsi2): Likewise. + * config/arm/predicates.md (arm_cond_move_operator): Check against + TARGET_VFP5 rather than TARGET_FPU_ARMV8 and fix spacing. + 2017-07-14 Jackson Woodruff * config/aarch64/aarch64.c (aarch64_print_operand): Move comments diff --git a/gcc/config/arm/arm-builtins.c b/gcc/config/arm/arm-builtins.c index 63ee880822c..7504ed581c6 100644 --- a/gcc/config/arm/arm-builtins.c +++ b/gcc/config/arm/arm-builtins.c @@ -3098,7 +3098,7 @@ arm_builtin_vectorized_function (unsigned int fn, tree type_out, tree type_in) NULL_TREE is returned if no such builtin is available. */ #undef ARM_CHECK_BUILTIN_MODE #define ARM_CHECK_BUILTIN_MODE(C) \ - (TARGET_FPU_ARMV8 \ + (TARGET_VFP5 \ && flag_unsafe_math_optimizations \ && ARM_CHECK_BUILTIN_MODE_1 (C)) diff --git a/gcc/config/arm/arm-c.c b/gcc/config/arm/arm-c.c index a3daa3220a2..9178937b6d9 100644 --- a/gcc/config/arm/arm-c.c +++ b/gcc/config/arm/arm-c.c @@ -96,7 +96,7 @@ arm_cpu_builtins (struct cpp_reader* pfile) || TARGET_ARM_ARCH_ISA_THUMB >=2)); def_or_undef_macro (pfile, "__ARM_FEATURE_NUMERIC_MAXMIN", - TARGET_ARM_ARCH >= 8 && TARGET_NEON && TARGET_FPU_ARMV8); + TARGET_ARM_ARCH >= 8 && TARGET_NEON && TARGET_VFP5); def_or_undef_macro (pfile, "__ARM_FEATURE_SIMD32", TARGET_INT_SIMD); diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in index f35128acb7d..e2ff297aed7 100644 --- a/gcc/config/arm/arm-cpus.in +++ b/gcc/config/arm/arm-cpus.in @@ -389,7 +389,7 @@ begin arch armv8-r option crc add bit_crc32 # fp.sp => fp-armv8 (d16); simd => simd + fp-armv8 + d32 + double precision # note: no fp option for fp-armv8 (d16) + double precision at the moment - option fp.sp add FP_ARMv8 + option fp.sp add FPv5 option simd add FP_ARMv8 NEON option crypto add FP_ARMv8 CRYPTO option nocrypto remove ALL_CRYPTO @@ -1390,7 +1390,7 @@ begin fpu fpv5-d16 end fpu fpv5-d16 begin fpu fp-armv8 - isa FP_ARMv8 FP_D32 + isa FP_ARMv8 end fpu fp-armv8 begin fpu neon-fp-armv8 diff --git a/gcc/config/arm/arm-isa.h b/gcc/config/arm/arm-isa.h index 0d66a0400c5..dbd29eaa52f 100644 --- a/gcc/config/arm/arm-isa.h +++ b/gcc/config/arm/arm-isa.h @@ -60,7 +60,6 @@ enum isa_feature isa_bit_VFPv4, /* Vector floating point v4. */ isa_bit_FPv5, /* Floating point v5. */ isa_bit_lpae, /* ARMv7-A LPAE. */ - isa_bit_FP_ARMv8, /* ARMv8 floating-point extension. */ isa_bit_neon, /* Advanced SIMD instructions. */ isa_bit_fp16conv, /* Conversions to/from fp16 (VFPv3 extension). */ isa_bit_fp_dbl, /* Double precision operations supported. */ @@ -143,7 +142,7 @@ enum isa_feature default. isa_bit_fp16 is deliberately missing from this list. */ #define ISA_ALL_FPU_INTERNAL \ isa_bit_VFPv2, isa_bit_VFPv3, isa_bit_VFPv4, isa_bit_FPv5, \ - isa_bit_FP_ARMv8, isa_bit_fp16conv, isa_bit_fp_dbl, ISA_ALL_SIMD + isa_bit_fp16conv, isa_bit_fp_dbl, ISA_ALL_SIMD /* Similarly, but including fp16 and other extensions that aren't part of -mfpu support. */ @@ -154,10 +153,10 @@ enum isa_feature #define ISA_VFPv3 ISA_VFPv2, isa_bit_VFPv3 #define ISA_VFPv4 ISA_VFPv3, isa_bit_VFPv4, isa_bit_fp16conv #define ISA_FPv5 ISA_VFPv4, isa_bit_FPv5 -#define ISA_FP_ARMv8 ISA_FPv5, isa_bit_FP_ARMv8 #define ISA_FP_DBL isa_bit_fp_dbl #define ISA_FP_D32 ISA_FP_DBL, isa_bit_fp_d32 +#define ISA_FP_ARMv8 ISA_FPv5, ISA_FP_D32 #define ISA_NEON ISA_FP_D32, isa_bit_neon #define ISA_CRYPTO ISA_NEON, isa_bit_crypto diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c index c6101efd555..f59132c3f07 100644 --- a/gcc/config/arm/arm.c +++ b/gcc/config/arm/arm.c @@ -10755,7 +10755,7 @@ arm_rtx_costs_internal (rtx x, enum rtx_code code, enum rtx_code outer_code, { if (speed_p) *cost += extra_cost->fp[mode == DFmode].widen; - if (!TARGET_FPU_ARMV8 + if (!TARGET_VFP5 && GET_MODE (XEXP (x, 0)) == HFmode) { /* Pre v8, widening HF->DF is a two-step process, first @@ -10849,7 +10849,7 @@ arm_rtx_costs_internal (rtx x, enum rtx_code code, enum rtx_code outer_code, return true; } else if (GET_MODE_CLASS (mode) == MODE_FLOAT - && TARGET_FPU_ARMV8) + && TARGET_VFP5) { if (speed_p) *cost += extra_cost->fp[mode == DFmode].roundint; diff --git a/gcc/config/arm/arm.h b/gcc/config/arm/arm.h index 315622212a5..4f53583cf02 100644 --- a/gcc/config/arm/arm.h +++ b/gcc/config/arm/arm.h @@ -196,10 +196,6 @@ extern tree arm_fp16_type_node; /* FPU supports fused-multiply-add operations. */ #define TARGET_FMA (bitmap_bit_p (arm_active_target.isa, isa_bit_VFPv4)) -/* FPU is ARMv8 compatible. */ -#define TARGET_FPU_ARMV8 \ - (bitmap_bit_p (arm_active_target.isa, isa_bit_FP_ARMv8)) - /* FPU supports Crypto extensions. */ #define TARGET_CRYPTO (bitmap_bit_p (arm_active_target.isa, isa_bit_crypto)) @@ -216,7 +212,7 @@ extern tree arm_fp16_type_node; /* FPU supports the floating point FP16 instructions for ARMv8.2 and later. */ #define TARGET_VFP_FP16INST \ - (TARGET_32BIT && TARGET_HARD_FLOAT && TARGET_FPU_ARMV8 && arm_fp16_inst) + (TARGET_32BIT && TARGET_HARD_FLOAT && TARGET_VFP5 && arm_fp16_inst) /* FPU supports the AdvSIMD FP16 instructions for ARMv8.2 and later. */ #define TARGET_NEON_FP16INST (TARGET_VFP_FP16INST && TARGET_NEON_RDMA) diff --git a/gcc/config/arm/arm.md b/gcc/config/arm/arm.md index e6e1ac54a85..049a78edefe 100644 --- a/gcc/config/arm/arm.md +++ b/gcc/config/arm/arm.md @@ -7879,7 +7879,7 @@ "") (match_operand:SDF 4 "s_register_operand" "")))] - "TARGET_HARD_FLOAT && TARGET_FPU_ARMV8 " + "TARGET_HARD_FLOAT && TARGET_VFP5 " "* { enum arm_cond_code code = maybe_get_arm_condition_code (operands[1]); diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md index 33b25ff3c73..235c46da1a1 100644 --- a/gcc/config/arm/neon.md +++ b/gcc/config/arm/neon.md @@ -751,7 +751,7 @@ (unspec:VCVTF [(match_operand:VCVTF 1 "s_register_operand" "w")] NEON_VRINT))] - "TARGET_NEON && TARGET_FPU_ARMV8" + "TARGET_NEON && TARGET_VFP5" "vrint.f32\\t%0, %1" [(set_attr "type" "neon_fp_round_")] ) @@ -761,7 +761,7 @@ (FIXUORS: (unspec:VCVTF [(match_operand:VCVTF 1 "register_operand" "w")] NEON_VCVT)))] - "TARGET_NEON && TARGET_FPU_ARMV8" + "TARGET_NEON && TARGET_VFP5" "vcvt.32.f32\\t%0, %1" [(set_attr "type" "neon_fp_to_int_") (set_attr "predicable" "no")] @@ -2901,7 +2901,7 @@ (unspec:VCVTF [(match_operand:VCVTF 1 "s_register_operand" "w") (match_operand:VCVTF 2 "s_register_operand" "w")] VMAXMINFNM))] - "TARGET_NEON && TARGET_FPU_ARMV8" + "TARGET_NEON && TARGET_VFP5" ".\t%0, %1, %2" [(set_attr "type" "neon_fp_minmax_s")] ) @@ -2912,7 +2912,7 @@ (unspec:VCVTF [(match_operand:VCVTF 1 "s_register_operand" "w") (match_operand:VCVTF 2 "s_register_operand" "w")] VMAXMINFNM))] - "TARGET_NEON && TARGET_FPU_ARMV8" + "TARGET_NEON && TARGET_VFP5" ".\t%0, %1, %2" [(set_attr "type" "neon_fp_minmax_s")] ) diff --git a/gcc/config/arm/predicates.md b/gcc/config/arm/predicates.md index afb5d6339a8..3e25cd16b29 100644 --- a/gcc/config/arm/predicates.md +++ b/gcc/config/arm/predicates.md @@ -350,9 +350,9 @@ (define_special_predicate "arm_cond_move_operator" (if_then_else (match_test "arm_restrict_it") - (and (match_test "TARGET_FPU_ARMV8") - (match_operand 0 "arm_vsel_comparison_operator")) - (match_operand 0 "expandable_comparison_operator"))) + (and (match_test "TARGET_VFP5") + (match_operand 0 "arm_vsel_comparison_operator")) + (match_operand 0 "expandable_comparison_operator"))) (define_special_predicate "noov_comparison_operator" (match_code "lt,ge,eq,ne")) diff --git a/gcc/config/arm/vfp.md b/gcc/config/arm/vfp.md index d8f77e2ffe4..23c1d67c9e3 100644 --- a/gcc/config/arm/vfp.md +++ b/gcc/config/arm/vfp.md @@ -1997,7 +1997,7 @@ (FIXUORS:SI (unspec:SDF [(match_operand:SDF 1 "register_operand" "")] VCVT)))] - "TARGET_HARD_FLOAT && TARGET_FPU_ARMV8 " + "TARGET_HARD_FLOAT && TARGET_VFP5 " "vcvt.32.\\t%0, %1" [(set_attr "predicable" "no") (set_attr "conds" "unconditional") -- 2.30.2