From 41f620bde553d38b1c0a05ac0b1b8dc17adc398a Mon Sep 17 00:00:00 2001 From: pfg Date: Sat, 22 Jun 2013 02:22:12 +0000 Subject: [PATCH] MFC r251212, r251480: GCC: bring back experimental support for amdfam10/barcelona CPUs. This is a revised subset of the support initially brought in in r236962 and later reverted. The collateral efects seem to have disappeared but it is still recommended to set the CPUTYPE with caution. While here also install AMD intrinsics header ammintrin.h Reviewed by: jkim (ages ago) git-svn-id: svn://svn.freebsd.org/base/stable/9@252080 ccf9f872-aa2e-dd11-9fc8-001c23d0bc1f --- contrib/gcc/ChangeLog.gcc43 | 191 +++++++++++- contrib/gcc/config.gcc | 16 +- contrib/gcc/config/i386/ammintrin.h | 73 +++++ contrib/gcc/config/i386/athlon.md | 378 +++++++++++++++++++--- contrib/gcc/config/i386/driver-i386.c | 11 +- contrib/gcc/config/i386/emmintrin.h | 6 +- contrib/gcc/config/i386/i386.c | 434 +++++++++++++++++++++++--- contrib/gcc/config/i386/i386.h | 23 +- contrib/gcc/config/i386/i386.md | 352 ++++++++++++++++++--- contrib/gcc/config/i386/i386.opt | 18 +- contrib/gcc/config/i386/pmmintrin.h | 8 +- contrib/gcc/config/i386/sse.md | 131 +++++++- contrib/gcc/config/i386/tmmintrin.h | 8 +- contrib/gcc/doc/extend.texi | 17 + contrib/gcc/doc/invoke.texi | 14 +- gnu/usr.bin/cc/include/Makefile | 4 +- 16 files changed, 1517 insertions(+), 167 deletions(-) create mode 100644 contrib/gcc/config/i386/ammintrin.h diff --git a/contrib/gcc/ChangeLog.gcc43 b/contrib/gcc/ChangeLog.gcc43 index b3047c4a2..3f893ac6b 100644 --- a/contrib/gcc/ChangeLog.gcc43 +++ b/contrib/gcc/ChangeLog.gcc43 @@ -1,3 +1,8 @@ +2007-05-01 Dwarakanath Rajagopal (r124341) + + * doc/invoke.texi: Fix typo, 'AMD Family 10h core' instead of + 'AMD Family 10 core'. + 2007-05-01 Dwarakanath Rajagopal (r124339) * config/i386/i386.c (override_options): Accept k8-sse3, opteron-sse3 @@ -5,6 +10,12 @@ with SSE3 instruction set support. * doc/invoke.texi: Likewise. +2007-05-01 Dwarakanath Rajagopal (r124330) + + * config/i386/i386.c (override_options): Tuning 32-byte loop + alignment for amdfam10 architecture. Increasing the max loop + alignment to 24 bytes. + 2007-04-12 Richard Guenther (r123736) PR tree-optimization/24689 @@ -21,6 +32,17 @@ * config/i386/i386.c (ix86_handle_option): Handle SSSE3. +2007-03-28 Dwarakanath Rajagopal (r123313) + + * config.gcc: Accept barcelona as a variant of amdfam10. + * config/i386/i386.c (override_options): Likewise. + * doc/invoke.texi: Likewise. + +2007-02-09 Dwarakanath Rajagopal (r121763) + + * config/i386/driver-i386.c: Turn on -mtune=native for AMDFAM10. + (bit_SSE4a): New. + 2007-02-08 Harsha Jagasia (r121726) * config/i386/xmmintrin.h: Make inclusion of emmintrin.h @@ -38,6 +60,168 @@ * config/i386/i386.c (override_options): Set PTA_SSSE3 for core2. +2007-02-05 Harsha Jagasia (r121625) + + * config/i386/athlon.md (athlon_fldxf_k8, athlon_fld_k8, + athlon_fstxf_k8, athlon_fst_k8, athlon_fist, athlon_fmov, + athlon_fadd_load, athlon_fadd_load_k8, athlon_fadd, athlon_fmul, + athlon_fmul_load, athlon_fmul_load_k8, athlon_fsgn, + athlon_fdiv_load, athlon_fdiv_load_k8, athlon_fdiv_k8, + athlon_fpspc_load, athlon_fpspc, athlon_fcmov_load, + athlon_fcmov_load_k8, athlon_fcmov_k8, athlon_fcomi_load_k8, + athlon_fcomi, athlon_fcom_load_k8, athlon_fcom): Added amdfam10. + +2007-02-05 Harsha Jagasia (r121625) + + * config/i386/i386.md (x86_sahf_1, cmpfp_i_mixed, cmpfp_i_sse, + cmpfp_i_i387, cmpfp_iu_mixed, cmpfp_iu_sse, cmpfp_iu_387, + swapsi, swaphi_1, swapqi_1, swapdi_rex64, fix_truncsfdi_sse, + fix_truncdfdi_sse, fix_truncsfsi_sse, fix_truncdfsi_sse, + x86_fldcw_1, floatsisf2_mixed, floatsisf2_sse, floatdisf2_mixed, + floatdisf2_sse, floatsidf2_mixed, floatsidf2_sse, + floatdidf2_mixed, floatdidf2_sse, muldi3_1_rex64, mulsi3_1, + mulsi3_1_zext, mulhi3_1, mulqi3_1, umulqihi3_1, mulqihi3_insn, + umulditi3_insn, umulsidi3_insn, mulditi3_insn, mulsidi3_insn, + umuldi3_highpart_rex64, umulsi3_highpart_insn, + umulsi3_highpart_zext, smuldi3_highpart_rex64, + smulsi3_highpart_insn, smulsi3_highpart_zext, x86_64_shld, + x86_shld_1, x86_64_shrd, sqrtsf2_mixed, sqrtsf2_sse, + sqrtsf2_i387, sqrtdf2_mixed, sqrtdf2_sse, sqrtdf2_i387, + sqrtextendsfdf2_i387, sqrtxf2, sqrtextendsfxf2_i387, + sqrtextenddfxf2_i387): Added amdfam10_decode. + + * config/i386/athlon.md (athlon_idirect_amdfam10, + athlon_ivector_amdfam10, athlon_idirect_load_amdfam10, + athlon_ivector_load_amdfam10, athlon_idirect_both_amdfam10, + athlon_ivector_both_amdfam10, athlon_idirect_store_amdfam10, + athlon_ivector_store_amdfam10): New define_insn_reservation. + (athlon_idirect_loadmov, athlon_idirect_movstore): Added + amdfam10. + +2007-02-05 Harsha Jagasia (r121625) + + * config/i386/athlon.md (athlon_call_amdfam10, + athlon_pop_amdfam10, athlon_lea_amdfam10): New + define_insn_reservation. + (athlon_branch, athlon_push, athlon_leave_k8, athlon_imul_k8, + athlon_imul_k8_DI, athlon_imul_mem_k8, athlon_imul_mem_k8_DI, + athlon_idiv, athlon_idiv_mem, athlon_str): Added amdfam10. + +2007-02-05 Harsha Jagasia (r121625) + + * config/i386/athlon.md (athlon_sseld_amdfam10, + athlon_mmxld_amdfam10, athlon_ssest_amdfam10, + athlon_mmxssest_short_amdfam10): New define_insn_reservation. + +2007-02-05 Harsha Jagasia (r121625) + + * config/i386/athlon.md (athlon_sseins_amdfam10): New + define_insn_reservation. + * config/i386/i386.md (sseins): Added sseins to define_attr type + and define_attr unit. + * config/i386/sse.md: Set type attribute to sseins for insertq + and insertqi. + +2007-02-05 Harsha Jagasia (r121625) + + * config/i386/athlon.md (sselog_load_amdfam10, sselog_amdfam10, + ssecmpvector_load_amdfam10, ssecmpvector_amdfam10, + ssecomi_load_amdfam10, ssecomi_amdfam10, + sseaddvector_load_amdfam10, sseaddvector_amdfam10): New + define_insn_reservation. + (ssecmp_load_k8, ssecmp, sseadd_load_k8, seadd): Added amdfam10. + +2007-02-05 Harsha Jagasia (r121625) + + * config/i386/athlon.md (cvtss2sd_load_amdfam10, + cvtss2sd_amdfam10, cvtps2pd_load_amdfam10, cvtps2pd_amdfam10, + cvtsi2sd_load_amdfam10, cvtsi2ss_load_amdfam10, + cvtsi2sd_amdfam10, cvtsi2ss_amdfam10, cvtsd2ss_load_amdfam10, + cvtsd2ss_amdfam10, cvtpd2ps_load_amdfam10, cvtpd2ps_amdfam10, + cvtsX2si_load_amdfam10, cvtsX2si_amdfam10): New + define_insn_reservation. + + * config/i386/sse.md (cvtsi2ss, cvtsi2ssq, cvtss2si, + cvtss2siq, cvttss2si, cvttss2siq, cvtsi2sd, cvtsi2sdq, + cvtsd2si, cvtsd2siq, cvttsd2si, cvttsd2siq, + cvtpd2dq, cvttpd2dq, cvtsd2ss, cvtss2sd, + cvtpd2ps, cvtps2pd): Added amdfam10_decode attribute. + +2007-02-05 Harsha Jagasia (r121625) + + * config/i386/athlon.md (athlon_ssedivvector_amdfam10, + athlon_ssedivvector_load_amdfam10, athlon_ssemulvector_amdfam10, + athlon_ssemulvector_load_amdfam10): New define_insn_reservation. + (athlon_ssediv, athlon_ssediv_load_k8, athlon_ssemul, + athlon_ssemul_load_k8): Added amdfam10. + +2007-02-05 Harsha Jagasia (r121625) + + * config/i386/i386.h (TARGET_SSE_UNALIGNED_MOVE_OPTIMAL): New macro. + (x86_sse_unaligned_move_optimal): New variable. + + * config/i386/i386.c (x86_sse_unaligned_move_optimal): Enable for + m_AMDFAM10. + (ix86_expand_vector_move_misalign): Add code to generate movupd/movups + for unaligned vector SSE double/single precision loads for AMDFAM10. + +2007-02-05 Harsha Jagasia (r121625) + + * config/i386/i386.h (TARGET_AMDFAM10): New macro. + (TARGET_CPU_CPP_BUILTINS): Add code for amdfam10. + Define TARGET_CPU_DEFAULT_amdfam10. + (TARGET_CPU_DEFAULT_NAMES): Add amdfam10. + (processor_type): Add PROCESSOR_AMDFAM10. + + * config/i386/i386.md: Add amdfam10 as a new cpu attribute to match + processor_type in config/i386/i386.h. + Enable imul peepholes for TARGET_AMDFAM10. + + * config.gcc: Add support for --with-cpu option for amdfam10. + + * config/i386/i386.c (amdfam10_cost): New variable. + (m_AMDFAM10): New macro. + (m_ATHLON_K8_AMDFAM10): New macro. + (x86_use_leave, x86_push_memory, x86_movx, x86_unroll_strlen, + x86_cmove, x86_3dnow_a, x86_deep_branch, x86_use_simode_fiop, + x86_promote_QImode, x86_integer_DFmode_moves, + x86_partial_reg_dependency, x86_memory_mismatch_stall, + x86_accumulate_outgoing_args, x86_arch_always_fancy_math_387, + x86_sse_partial_reg_dependency, x86_sse_typeless_stores, + x86_use_ffreep, x86_use_incdec, x86_four_jump_limit, + x86_schedule, x86_use_bt, x86_cmpxchg16b, x86_pad_returns): + Enable/disable for amdfam10. + (override_options): Add amdfam10_cost to processor_target_table. + Set up PROCESSOR_AMDFAM10 for amdfam10 entry in + processor_alias_table. + (ix86_issue_rate): Add PROCESSOR_AMDFAM10. + (ix86_adjust_cost): Add code for amdfam10. + +2007-02-05 Harsha Jagasia (r121625) + + * config/i386/i386.opt: Add new Advanced Bit Manipulation (-mabm) + instruction set feature flag. Add new (-mpopcnt) flag for popcnt + instruction. Add new SSE4A (-msse4a) instruction set feature flag. + * config/i386/i386.h: Add builtin definition for SSE4A. + * config/i386/i386.md: Add support for ABM instructions + (popcnt and lzcnt). + * config/i386/sse.md: Add support for SSE4A instructions + (movntss, movntsd, extrq, insertq). + * config/i386/i386.c: Add support for ABM and SSE4A builtins. + Add -march=amdfam10 flag. + * config/i386/ammintrin.h: Add support for SSE4A intrinsics. + * doc/invoke.texi: Add documentation on flags for sse4a, abm, popcnt + and amdfam10. + * doc/extend.texi: Add documentation for SSE4A builtins. + +2007-01-24 Jakub Jelinek (r121140) + + * config/i386/i386.h (x86_cmpxchg16b): Remove const. + (TARGET_CMPXCHG16B): Define to x86_cmpxchg16b. + * config/i386/i386.c (x86_cmpxchg16b): Remove const. + (override_options): Add PTA_CX16 flag. Set x86_cmpxchg16b + for CPUs that have PTA_CX16 set. + 2007-01-17 Eric Christopher (r120846) * config.gcc: Support core2 processor. @@ -47,6 +231,11 @@ PR target/30040 * config/i386/driver-i386.c (bit_SSSE3): New. +2006-11-27 Uros Bizjak (r119260) + + * config/i386/i386.c (x86_ext_80387_constants): Add m_K8, m_CORE2 + and m_GENERIC64. + 2006-11-18 Vladimir Makarov (r118973) * doc/invoke.texi (core2): Add item. @@ -182,7 +371,7 @@ * doc/invoke.texi: Document -mssse3/-mno-ssse3 switches. -2006-10-22 H.J. Lu +2006-10-22 H.J. Lu (r117959) * config/i386/tmmintrin.h: Remove the duplicated content. diff --git a/contrib/gcc/config.gcc b/contrib/gcc/config.gcc index 44065937a..5806ce736 100644 --- a/contrib/gcc/config.gcc +++ b/contrib/gcc/config.gcc @@ -269,12 +269,12 @@ xscale-*-*) i[34567]86-*-*) cpu_type=i386 extra_headers="mmintrin.h mm3dnow.h xmmintrin.h emmintrin.h - pmmintrin.h tmmintrin.h" + pmmintrin.h tmmintrin.h ammintrin.h" ;; x86_64-*-*) cpu_type=i386 extra_headers="mmintrin.h mm3dnow.h xmmintrin.h emmintrin.h - pmmintrin.h tmmintrin.h" + pmmintrin.h tmmintrin.h ammintrin.h" need_64bit_hwint=yes ;; ia64-*-*) @@ -1209,14 +1209,14 @@ i[34567]86-*-solaris2*) # FIXME: -m64 for i[34567]86-*-* should be allowed just # like -m32 for x86_64-*-*. case X"${with_cpu}" in - Xgeneric|Xcore2|Xnocona|Xx86-64|Xk8|Xopteron|Xathlon64|Xathlon-fx) + Xgeneric|Xcore2|Xnocona|Xx86-64|Xamdfam10|Xbarcelona|Xk8|Xopteron|Xathlon64|Xathlon-fx) ;; X) with_cpu=generic ;; *) echo "Unsupported CPU used in --with-cpu=$with_cpu, supported values:" 1>&2 - echo "generic core2 nocona x86-64 k8 opteron athlon64 athlon-fx" 1>&2 + echo "generic core2 nocona x86-64 amdfam10 barcelona k8 opteron athlon64 athlon-fx" 1>&2 exit 1 ;; esac @@ -2515,6 +2515,9 @@ if test x$with_cpu = x ; then ;; i686-*-* | i786-*-*) case ${target_noncanonical} in + amdfam10-*|barcelona-*) + with_cpu=amdfam10 + ;; k8-*|opteron-*|athlon_64-*) with_cpu=k8 ;; @@ -2555,6 +2558,9 @@ if test x$with_cpu = x ; then ;; x86_64-*-*) case ${target_noncanonical} in + amdfam10-*|barcelona-*) + with_cpu=amdfam10 + ;; k8-*|opteron-*|athlon_64-*) with_cpu=k8 ;; @@ -2795,7 +2801,7 @@ case "${target}" in esac # OK ;; - "" | k8 | opteron | athlon64 | athlon-fx | nocona | core2 | generic) + "" | amdfam10 | barcelona | k8 | opteron | athlon64 | athlon-fx | nocona | core2 | generic) # OK ;; *) diff --git a/contrib/gcc/config/i386/ammintrin.h b/contrib/gcc/config/i386/ammintrin.h new file mode 100644 index 000000000..869c2880e --- /dev/null +++ b/contrib/gcc/config/i386/ammintrin.h @@ -0,0 +1,73 @@ +/* Copyright (C) 2007 Free Software Foundation, Inc. + + This file is part of GCC. + + GCC is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + GCC is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with GCC; see the file COPYING. If not, write to + the Free Software Foundation, 51 Franklin Street, Fifth Floor, + Boston, MA 02110-1301, USA. */ + +/* As a special exception, if you include this header file into source + files compiled by GCC, this header file does not by itself cause + the resulting executable to be covered by the GNU General Public + License. This exception does not however invalidate any other + reasons why the executable file might be covered by the GNU General + Public License. */ + +/* Implemented from the specification included in the AMD Programmers + Manual Update, version 2.x */ + +#ifndef _AMMINTRIN_H_INCLUDED +#define _AMMINTRIN_H_INCLUDED + +#ifndef __SSE4A__ +# error "SSE4A instruction set not enabled" +#else + +/* We need definitions from the SSE3, SSE2 and SSE header files*/ +#include + +static __inline void __attribute__((__always_inline__)) +_mm_stream_sd (double * __P, __m128d __Y) +{ + __builtin_ia32_movntsd (__P, (__v2df) __Y); +} + +static __inline void __attribute__((__always_inline__)) +_mm_stream_ss (float * __P, __m128 __Y) +{ + __builtin_ia32_movntss (__P, (__v4sf) __Y); +} + +static __inline __m128i __attribute__((__always_inline__)) +_mm_extract_si64 (__m128i __X, __m128i __Y) +{ + return (__m128i) __builtin_ia32_extrq ((__v2di) __X, (__v16qi) __Y); +} + +#define _mm_extracti_si64(X, I, L) \ +((__m128i) __builtin_ia32_extrqi ((__v2di)(X), I, L)) + +static __inline __m128i __attribute__((__always_inline__)) +_mm_insert_si64 (__m128i __X,__m128i __Y) +{ + return (__m128i) __builtin_ia32_insertq ((__v2di)__X, (__v2di)__Y); +} + +#define _mm_inserti_si64(X, Y, I, L) \ +((__m128i) __builtin_ia32_insertqi ((__v2di)(X), (__v2di)(Y), I, L)) + + +#endif /* __SSE4A__ */ + +#endif /* _AMMINTRIN_H_INCLUDED */ diff --git a/contrib/gcc/config/i386/athlon.md b/contrib/gcc/config/i386/athlon.md index 6d92b948b..a52f9bc28 100644 --- a/contrib/gcc/config/i386/athlon.md +++ b/contrib/gcc/config/i386/athlon.md @@ -29,6 +29,8 @@ (const_string "vector")] (const_string "direct"))) +(define_attr "amdfam10_decode" "direct,vector,double" + (const_string "direct")) ;; ;; decode0 decode1 decode2 ;; \ | / @@ -131,18 +133,22 @@ ;; Jump instructions are executed in the branch unit completely transparent to us (define_insn_reservation "athlon_branch" 0 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (eq_attr "type" "ibr")) "athlon-direct,athlon-ieu") (define_insn_reservation "athlon_call" 0 (and (eq_attr "cpu" "athlon,k8,generic64") (eq_attr "type" "call,callv")) "athlon-vector,athlon-ieu") +(define_insn_reservation "athlon_call_amdfam10" 0 + (and (eq_attr "cpu" "amdfam10") + (eq_attr "type" "call,callv")) + "athlon-double,athlon-ieu") ;; Latency of push operation is 3 cycles, but ESP value is available ;; earlier (define_insn_reservation "athlon_push" 2 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (eq_attr "type" "push")) "athlon-direct,athlon-agu,athlon-store") (define_insn_reservation "athlon_pop" 4 @@ -153,12 +159,16 @@ (and (eq_attr "cpu" "k8,generic64") (eq_attr "type" "pop")) "athlon-double,(athlon-ieu+athlon-load)") +(define_insn_reservation "athlon_pop_amdfam10" 3 + (and (eq_attr "cpu" "amdfam10") + (eq_attr "type" "pop")) + "athlon-direct,(athlon-ieu+athlon-load)") (define_insn_reservation "athlon_leave" 3 (and (eq_attr "cpu" "athlon") (eq_attr "type" "leave")) "athlon-vector,(athlon-ieu+athlon-load)") (define_insn_reservation "athlon_leave_k8" 3 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (eq_attr "type" "leave")) "athlon-double,(athlon-ieu+athlon-load)") @@ -167,6 +177,11 @@ (and (eq_attr "cpu" "athlon,k8,generic64") (eq_attr "type" "lea")) "athlon-direct,athlon-agu,nothing") +;; Lea executes in AGU unit with 1 cycle latency on AMDFAM10 +(define_insn_reservation "athlon_lea_amdfam10" 1 + (and (eq_attr "cpu" "amdfam10") + (eq_attr "type" "lea")) + "athlon-direct,athlon-agu,nothing") ;; Mul executes in special multiplier unit attached to IEU0 (define_insn_reservation "athlon_imul" 5 @@ -176,29 +191,35 @@ "athlon-vector,athlon-ieu0,athlon-mult,nothing,nothing,athlon-ieu0") ;; ??? Widening multiply is vector or double. (define_insn_reservation "athlon_imul_k8_DI" 4 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "imul") (and (eq_attr "mode" "DI") (eq_attr "memory" "none,unknown")))) "athlon-direct0,athlon-ieu0,athlon-mult,nothing,athlon-ieu0") (define_insn_reservation "athlon_imul_k8" 3 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "imul") (eq_attr "memory" "none,unknown"))) "athlon-direct0,athlon-ieu0,athlon-mult,athlon-ieu0") +(define_insn_reservation "athlon_imul_amdfam10_HI" 4 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "imul") + (and (eq_attr "mode" "HI") + (eq_attr "memory" "none,unknown")))) + "athlon-vector,athlon-ieu0,athlon-mult,nothing,athlon-ieu0") (define_insn_reservation "athlon_imul_mem" 8 (and (eq_attr "cpu" "athlon") (and (eq_attr "type" "imul") (eq_attr "memory" "load,both"))) "athlon-vector,athlon-load,athlon-ieu,athlon-mult,nothing,nothing,athlon-ieu") (define_insn_reservation "athlon_imul_mem_k8_DI" 7 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "imul") (and (eq_attr "mode" "DI") (eq_attr "memory" "load,both")))) "athlon-vector,athlon-load,athlon-ieu,athlon-mult,nothing,athlon-ieu") (define_insn_reservation "athlon_imul_mem_k8" 6 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "imul") (eq_attr "memory" "load,both"))) "athlon-vector,athlon-load,athlon-ieu,athlon-mult,athlon-ieu") @@ -209,21 +230,23 @@ ;; other instructions. ;; ??? Experiments show that the idiv can overlap with roughly 6 cycles ;; of the other code +;; Using the same heuristics for amdfam10 as K8 with idiv (define_insn_reservation "athlon_idiv" 6 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (and (eq_attr "type" "idiv") (eq_attr "memory" "none,unknown"))) "athlon-vector,(athlon-ieu0*6+(athlon-fpsched,athlon-fvector))") (define_insn_reservation "athlon_idiv_mem" 9 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (and (eq_attr "type" "idiv") (eq_attr "memory" "load,both"))) "athlon-vector,((athlon-load,athlon-ieu0*6)+(athlon-fpsched,athlon-fvector))") ;; The parallelism of string instructions is not documented. Model it same way ;; as idiv to create smaller automata. This probably does not matter much. +;; Using the same heuristics for amdfam10 as K8 with idiv (define_insn_reservation "athlon_str" 6 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (and (eq_attr "type" "str") (eq_attr "memory" "load,both,store"))) "athlon-vector,athlon-load,athlon-ieu0*6") @@ -234,34 +257,62 @@ (and (eq_attr "unit" "integer,unknown") (eq_attr "memory" "none,unknown")))) "athlon-direct,athlon-ieu") +(define_insn_reservation "athlon_idirect_amdfam10" 1 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "amdfam10_decode" "direct") + (and (eq_attr "unit" "integer,unknown") + (eq_attr "memory" "none,unknown")))) + "athlon-direct,athlon-ieu") (define_insn_reservation "athlon_ivector" 2 (and (eq_attr "cpu" "athlon,k8,generic64") (and (eq_attr "athlon_decode" "vector") (and (eq_attr "unit" "integer,unknown") (eq_attr "memory" "none,unknown")))) "athlon-vector,athlon-ieu,athlon-ieu") +(define_insn_reservation "athlon_ivector_amdfam10" 2 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "amdfam10_decode" "vector") + (and (eq_attr "unit" "integer,unknown") + (eq_attr "memory" "none,unknown")))) + "athlon-vector,athlon-ieu,athlon-ieu") + (define_insn_reservation "athlon_idirect_loadmov" 3 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (and (eq_attr "type" "imov") (eq_attr "memory" "load"))) "athlon-direct,athlon-load") + (define_insn_reservation "athlon_idirect_load" 4 (and (eq_attr "cpu" "athlon,k8,generic64") (and (eq_attr "athlon_decode" "direct") (and (eq_attr "unit" "integer,unknown") (eq_attr "memory" "load")))) "athlon-direct,athlon-load,athlon-ieu") +(define_insn_reservation "athlon_idirect_load_amdfam10" 4 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "amdfam10_decode" "direct") + (and (eq_attr "unit" "integer,unknown") + (eq_attr "memory" "load")))) + "athlon-direct,athlon-load,athlon-ieu") (define_insn_reservation "athlon_ivector_load" 6 (and (eq_attr "cpu" "athlon,k8,generic64") (and (eq_attr "athlon_decode" "vector") (and (eq_attr "unit" "integer,unknown") (eq_attr "memory" "load")))) "athlon-vector,athlon-load,athlon-ieu,athlon-ieu") +(define_insn_reservation "athlon_ivector_load_amdfam10" 6 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "amdfam10_decode" "vector") + (and (eq_attr "unit" "integer,unknown") + (eq_attr "memory" "load")))) + "athlon-vector,athlon-load,athlon-ieu,athlon-ieu") + (define_insn_reservation "athlon_idirect_movstore" 1 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (and (eq_attr "type" "imov") (eq_attr "memory" "store"))) "athlon-direct,athlon-agu,athlon-store") + (define_insn_reservation "athlon_idirect_both" 4 (and (eq_attr "cpu" "athlon,k8,generic64") (and (eq_attr "athlon_decode" "direct") @@ -270,6 +321,15 @@ "athlon-direct,athlon-load, athlon-ieu,athlon-store, athlon-store") +(define_insn_reservation "athlon_idirect_both_amdfam10" 4 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "amdfam10_decode" "direct") + (and (eq_attr "unit" "integer,unknown") + (eq_attr "memory" "both")))) + "athlon-direct,athlon-load, + athlon-ieu,athlon-store, + athlon-store") + (define_insn_reservation "athlon_ivector_both" 6 (and (eq_attr "cpu" "athlon,k8,generic64") (and (eq_attr "athlon_decode" "vector") @@ -279,6 +339,16 @@ athlon-ieu, athlon-ieu, athlon-store") +(define_insn_reservation "athlon_ivector_both_amdfam10" 6 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "amdfam10_decode" "vector") + (and (eq_attr "unit" "integer,unknown") + (eq_attr "memory" "both")))) + "athlon-vector,athlon-load, + athlon-ieu, + athlon-ieu, + athlon-store") + (define_insn_reservation "athlon_idirect_store" 1 (and (eq_attr "cpu" "athlon,k8,generic64") (and (eq_attr "athlon_decode" "direct") @@ -286,6 +356,14 @@ (eq_attr "memory" "store")))) "athlon-direct,(athlon-ieu+athlon-agu), athlon-store") +(define_insn_reservation "athlon_idirect_store_amdfam10" 1 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "amdfam10_decode" "direct") + (and (eq_attr "unit" "integer,unknown") + (eq_attr "memory" "store")))) + "athlon-direct,(athlon-ieu+athlon-agu), + athlon-store") + (define_insn_reservation "athlon_ivector_store" 2 (and (eq_attr "cpu" "athlon,k8,generic64") (and (eq_attr "athlon_decode" "vector") @@ -293,6 +371,13 @@ (eq_attr "memory" "store")))) "athlon-vector,(athlon-ieu+athlon-agu),athlon-ieu, athlon-store") +(define_insn_reservation "athlon_ivector_store_amdfam10" 2 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "amdfam10_decode" "vector") + (and (eq_attr "unit" "integer,unknown") + (eq_attr "memory" "store")))) + "athlon-vector,(athlon-ieu+athlon-agu),athlon-ieu, + athlon-store") ;; Athlon floatin point unit (define_insn_reservation "athlon_fldxf" 12 @@ -302,7 +387,7 @@ (eq_attr "mode" "XF")))) "athlon-vector,athlon-fpload2,athlon-fvector*9") (define_insn_reservation "athlon_fldxf_k8" 13 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "fmov") (and (eq_attr "memory" "load") (eq_attr "mode" "XF")))) @@ -314,7 +399,7 @@ (eq_attr "memory" "load"))) "athlon-direct,athlon-fpload,athlon-fany") (define_insn_reservation "athlon_fld_k8" 2 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "fmov") (eq_attr "memory" "load"))) "athlon-direct,athlon-fploadk8,athlon-fstore") @@ -326,7 +411,7 @@ (eq_attr "mode" "XF")))) "athlon-vector,(athlon-fpsched+athlon-agu),(athlon-store2+(athlon-fvector*7))") (define_insn_reservation "athlon_fstxf_k8" 8 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "fmov") (and (eq_attr "memory" "store,both") (eq_attr "mode" "XF")))) @@ -337,16 +422,16 @@ (eq_attr "memory" "store,both"))) "athlon-direct,(athlon-fpsched+athlon-agu),(athlon-fstore+athlon-store)") (define_insn_reservation "athlon_fst_k8" 2 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "fmov") (eq_attr "memory" "store,both"))) "athlon-direct,(athlon-fpsched+athlon-agu),(athlon-fstore+athlon-store)") (define_insn_reservation "athlon_fist" 4 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (eq_attr "type" "fistp,fisttp")) "athlon-direct,(athlon-fpsched+athlon-agu),(athlon-fstore+athlon-store)") (define_insn_reservation "athlon_fmov" 2 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (eq_attr "type" "fmov")) "athlon-direct,athlon-fpsched,athlon-faddmul") (define_insn_reservation "athlon_fadd_load" 4 @@ -355,12 +440,12 @@ (eq_attr "memory" "load"))) "athlon-direct,athlon-fpload,athlon-fadd") (define_insn_reservation "athlon_fadd_load_k8" 6 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "fop") (eq_attr "memory" "load"))) "athlon-direct,athlon-fploadk8,athlon-fadd") (define_insn_reservation "athlon_fadd" 4 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (eq_attr "type" "fop")) "athlon-direct,athlon-fpsched,athlon-fadd") (define_insn_reservation "athlon_fmul_load" 4 @@ -369,16 +454,16 @@ (eq_attr "memory" "load"))) "athlon-direct,athlon-fpload,athlon-fmul") (define_insn_reservation "athlon_fmul_load_k8" 6 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "fmul") (eq_attr "memory" "load"))) "athlon-direct,athlon-fploadk8,athlon-fmul") (define_insn_reservation "athlon_fmul" 4 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (eq_attr "type" "fmul")) "athlon-direct,athlon-fpsched,athlon-fmul") (define_insn_reservation "athlon_fsgn" 2 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (eq_attr "type" "fsgn")) "athlon-direct,athlon-fpsched,athlon-fmul") (define_insn_reservation "athlon_fdiv_load" 24 @@ -387,7 +472,7 @@ (eq_attr "memory" "load"))) "athlon-direct,athlon-fpload,athlon-fmul") (define_insn_reservation "athlon_fdiv_load_k8" 13 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "fdiv") (eq_attr "memory" "load"))) "athlon-direct,athlon-fploadk8,athlon-fmul") @@ -396,16 +481,16 @@ (eq_attr "type" "fdiv")) "athlon-direct,athlon-fpsched,athlon-fmul") (define_insn_reservation "athlon_fdiv_k8" 11 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (eq_attr "type" "fdiv")) "athlon-direct,athlon-fpsched,athlon-fmul") (define_insn_reservation "athlon_fpspc_load" 103 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (and (eq_attr "type" "fpspc") (eq_attr "memory" "load"))) "athlon-vector,athlon-fpload,athlon-fvector") (define_insn_reservation "athlon_fpspc" 100 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (eq_attr "type" "fpspc")) "athlon-vector,athlon-fpsched,athlon-fvector") (define_insn_reservation "athlon_fcmov_load" 7 @@ -418,12 +503,12 @@ (eq_attr "type" "fcmov")) "athlon-vector,athlon-fpsched,athlon-fvector") (define_insn_reservation "athlon_fcmov_load_k8" 17 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "fcmov") (eq_attr "memory" "load"))) "athlon-vector,athlon-fploadk8,athlon-fvector") (define_insn_reservation "athlon_fcmov_k8" 15 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (eq_attr "type" "fcmov")) "athlon-vector,athlon-fpsched,athlon-fvector") ;; fcomi is vector decoded by uses only one pipe. @@ -434,13 +519,13 @@ (eq_attr "memory" "load")))) "athlon-vector,athlon-fpload,athlon-fadd") (define_insn_reservation "athlon_fcomi_load_k8" 5 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "fcmp") (and (eq_attr "athlon_decode" "vector") (eq_attr "memory" "load")))) "athlon-vector,athlon-fploadk8,athlon-fadd") (define_insn_reservation "athlon_fcomi" 3 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (and (eq_attr "athlon_decode" "vector") (eq_attr "type" "fcmp"))) "athlon-vector,athlon-fpsched,athlon-fadd") @@ -450,18 +535,18 @@ (eq_attr "memory" "load"))) "athlon-direct,athlon-fpload,athlon-fadd") (define_insn_reservation "athlon_fcom_load_k8" 4 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "fcmp") (eq_attr "memory" "load"))) "athlon-direct,athlon-fploadk8,athlon-fadd") (define_insn_reservation "athlon_fcom" 2 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (eq_attr "type" "fcmp")) "athlon-direct,athlon-fpsched,athlon-fadd") ;; Never seen by the scheduler because we still don't do post reg-stack ;; scheduling. ;(define_insn_reservation "athlon_fxch" 2 -; (and (eq_attr "cpu" "athlon,k8,generic64") +; (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") ; (eq_attr "type" "fxch")) ; "athlon-direct,athlon-fpsched,athlon-fany") @@ -516,6 +601,23 @@ (and (eq_attr "type" "mmxmov,ssemov") (eq_attr "memory" "load"))) "athlon-direct,athlon-fploadk8,athlon-fstore") +;; On AMDFAM10 all double, single and integer packed and scalar SSEx data +;; loads generated are direct path, latency of 2 and do not use any FP +;; executions units. No seperate entries for movlpx/movhpx loads, which +;; are direct path, latency of 4 and use the FADD/FMUL FP execution units, +;; as they will not be generated. +(define_insn_reservation "athlon_sseld_amdfam10" 2 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssemov") + (eq_attr "memory" "load"))) + "athlon-direct,athlon-fploadk8") +;; On AMDFAM10 MMX data loads generated are direct path, latency of 4 +;; and can use any FP executions units +(define_insn_reservation "athlon_mmxld_amdfam10" 4 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "mmxmov") + (eq_attr "memory" "load"))) + "athlon-direct,athlon-fploadk8, athlon-fany") (define_insn_reservation "athlon_mmxssest" 3 (and (eq_attr "cpu" "k8,generic64") (and (eq_attr "type" "mmxmov,ssemov") @@ -533,6 +635,25 @@ (and (eq_attr "type" "mmxmov,ssemov") (eq_attr "memory" "store,both"))) "athlon-direct,(athlon-fpsched+athlon-agu),(athlon-fstore+athlon-store)") +;; On AMDFAM10 all double, single and integer packed SSEx data stores +;; generated are all double path, latency of 2 and use the FSTORE FP +;; execution unit. No entries seperate for movupx/movdqu, which are +;; vector path, latency of 3 and use the FSTORE*2 FP execution unit, +;; as they will not be generated. +(define_insn_reservation "athlon_ssest_amdfam10" 2 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssemov") + (and (eq_attr "mode" "V4SF,V2DF,TI") + (eq_attr "memory" "store,both")))) + "athlon-double,(athlon-fpsched+athlon-agu),((athlon-fstore+athlon-store)*2)") +;; On AMDFAM10 all double, single and integer scalar SSEx and MMX +;; data stores generated are all direct path, latency of 2 and use +;; the FSTORE FP execution unit +(define_insn_reservation "athlon_mmxssest_short_amdfam10" 2 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "mmxmov,ssemov") + (eq_attr "memory" "store,both"))) + "athlon-direct,(athlon-fpsched+athlon-agu),(athlon-fstore+athlon-store)") (define_insn_reservation "athlon_movaps_k8" 2 (and (eq_attr "cpu" "k8,generic64") (and (eq_attr "type" "ssemov") @@ -578,6 +699,11 @@ (and (eq_attr "type" "sselog,sselog1") (eq_attr "memory" "load"))) "athlon-double,athlon-fpload2k8,(athlon-fmul*2)") +(define_insn_reservation "athlon_sselog_load_amdfam10" 4 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "sselog,sselog1") + (eq_attr "memory" "load"))) + "athlon-direct,athlon-fploadk8,(athlon-fadd|athlon-fmul)") (define_insn_reservation "athlon_sselog" 3 (and (eq_attr "cpu" "athlon") (eq_attr "type" "sselog,sselog1")) @@ -586,6 +712,11 @@ (and (eq_attr "cpu" "k8,generic64") (eq_attr "type" "sselog,sselog1")) "athlon-double,athlon-fpsched,athlon-fmul") +(define_insn_reservation "athlon_sselog_amdfam10" 2 + (and (eq_attr "cpu" "amdfam10") + (eq_attr "type" "sselog,sselog1")) + "athlon-direct,athlon-fpsched,(athlon-fadd|athlon-fmul)") + ;; ??? pcmp executes in addmul, probably not worthwhile to bother about that. (define_insn_reservation "athlon_ssecmp_load" 2 (and (eq_attr "cpu" "athlon") @@ -594,13 +725,13 @@ (eq_attr "memory" "load")))) "athlon-direct,athlon-fpload,athlon-fadd") (define_insn_reservation "athlon_ssecmp_load_k8" 4 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "ssecmp") (and (eq_attr "mode" "SF,DF,DI,TI") (eq_attr "memory" "load")))) "athlon-direct,athlon-fploadk8,athlon-fadd") (define_insn_reservation "athlon_ssecmp" 2 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (and (eq_attr "type" "ssecmp") (eq_attr "mode" "SF,DF,DI,TI"))) "athlon-direct,athlon-fpsched,athlon-fadd") @@ -614,6 +745,11 @@ (and (eq_attr "type" "ssecmp") (eq_attr "memory" "load"))) "athlon-double,athlon-fpload2k8,(athlon-fadd*2)") +(define_insn_reservation "athlon_ssecmpvector_load_amdfam10" 4 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssecmp") + (eq_attr "memory" "load"))) + "athlon-direct,athlon-fploadk8,athlon-fadd") (define_insn_reservation "athlon_ssecmpvector" 3 (and (eq_attr "cpu" "athlon") (eq_attr "type" "ssecmp")) @@ -622,6 +758,10 @@ (and (eq_attr "cpu" "k8,generic64") (eq_attr "type" "ssecmp")) "athlon-double,athlon-fpsched,(athlon-fadd*2)") +(define_insn_reservation "athlon_ssecmpvector_amdfam10" 2 + (and (eq_attr "cpu" "amdfam10") + (eq_attr "type" "ssecmp")) + "athlon-direct,athlon-fpsched,athlon-fadd") (define_insn_reservation "athlon_ssecomi_load" 4 (and (eq_attr "cpu" "athlon") (and (eq_attr "type" "ssecomi") @@ -632,10 +772,20 @@ (and (eq_attr "type" "ssecomi") (eq_attr "memory" "load"))) "athlon-vector,athlon-fploadk8,athlon-fadd") +(define_insn_reservation "athlon_ssecomi_load_amdfam10" 5 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssecomi") + (eq_attr "memory" "load"))) + "athlon-direct,athlon-fploadk8,athlon-fadd") (define_insn_reservation "athlon_ssecomi" 4 (and (eq_attr "cpu" "athlon,k8,generic64") (eq_attr "type" "ssecmp")) "athlon-vector,athlon-fpsched,athlon-fadd") +(define_insn_reservation "athlon_ssecomi_amdfam10" 3 + (and (eq_attr "cpu" "amdfam10") +;; It seems athlon_ssecomi has a bug in the attr_type, fixed for amdfam10 + (eq_attr "type" "ssecomi")) + "athlon-direct,athlon-fpsched,athlon-fadd") (define_insn_reservation "athlon_sseadd_load" 4 (and (eq_attr "cpu" "athlon") (and (eq_attr "type" "sseadd") @@ -643,13 +793,13 @@ (eq_attr "memory" "load")))) "athlon-direct,athlon-fpload,athlon-fadd") (define_insn_reservation "athlon_sseadd_load_k8" 6 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "sseadd") (and (eq_attr "mode" "SF,DF,DI") (eq_attr "memory" "load")))) "athlon-direct,athlon-fploadk8,athlon-fadd") (define_insn_reservation "athlon_sseadd" 4 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (and (eq_attr "type" "sseadd") (eq_attr "mode" "SF,DF,DI"))) "athlon-direct,athlon-fpsched,athlon-fadd") @@ -663,6 +813,11 @@ (and (eq_attr "type" "sseadd") (eq_attr "memory" "load"))) "athlon-double,athlon-fpload2k8,(athlon-fadd*2)") +(define_insn_reservation "athlon_sseaddvector_load_amdfam10" 6 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "sseadd") + (eq_attr "memory" "load"))) + "athlon-direct,athlon-fploadk8,athlon-fadd") (define_insn_reservation "athlon_sseaddvector" 5 (and (eq_attr "cpu" "athlon") (eq_attr "type" "sseadd")) @@ -671,6 +826,10 @@ (and (eq_attr "cpu" "k8,generic64") (eq_attr "type" "sseadd")) "athlon-double,athlon-fpsched,(athlon-fadd*2)") +(define_insn_reservation "athlon_sseaddvector_amdfam10" 4 + (and (eq_attr "cpu" "amdfam10") + (eq_attr "type" "sseadd")) + "athlon-direct,athlon-fpsched,athlon-fadd") ;; Conversions behaves very irregularly and the scheduling is critical here. ;; Take each instruction separately. Assume that the mode is always set to the @@ -684,12 +843,25 @@ (and (eq_attr "mode" "DF") (eq_attr "memory" "load"))))) "athlon-direct,athlon-fploadk8,athlon-fstore") +(define_insn_reservation "athlon_ssecvt_cvtss2sd_load_amdfam10" 7 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssecvt") + (and (eq_attr "amdfam10_decode" "double") + (and (eq_attr "mode" "DF") + (eq_attr "memory" "load"))))) + "athlon-double,athlon-fploadk8,(athlon-faddmul+athlon-fstore)") (define_insn_reservation "athlon_ssecvt_cvtss2sd" 2 (and (eq_attr "cpu" "athlon,k8,generic64") (and (eq_attr "type" "ssecvt") (and (eq_attr "athlon_decode" "direct") (eq_attr "mode" "DF")))) "athlon-direct,athlon-fpsched,athlon-fstore") +(define_insn_reservation "athlon_ssecvt_cvtss2sd_amdfam10" 7 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssecvt") + (and (eq_attr "amdfam10_decode" "vector") + (eq_attr "mode" "DF")))) + "athlon-vector,athlon-fpsched,athlon-faddmul,(athlon-fstore*2)") ;; cvtps2pd. Model same way the other double decoded FP conversions. (define_insn_reservation "athlon_ssecvt_cvtps2pd_load_k8" 5 (and (eq_attr "cpu" "k8,athlon,generic64") @@ -698,12 +870,25 @@ (and (eq_attr "mode" "V2DF,V4SF,TI") (eq_attr "memory" "load"))))) "athlon-double,athlon-fpload2k8,(athlon-fstore*2)") +(define_insn_reservation "athlon_ssecvt_cvtps2pd_load_amdfam10" 4 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssecvt") + (and (eq_attr "amdfam10_decode" "direct") + (and (eq_attr "mode" "V2DF,V4SF,TI") + (eq_attr "memory" "load"))))) + "athlon-direct,athlon-fploadk8,athlon-fstore") (define_insn_reservation "athlon_ssecvt_cvtps2pd_k8" 3 (and (eq_attr "cpu" "k8,athlon,generic64") (and (eq_attr "type" "ssecvt") (and (eq_attr "athlon_decode" "double") (eq_attr "mode" "V2DF,V4SF,TI")))) "athlon-double,athlon-fpsched,athlon-fstore,athlon-fstore") +(define_insn_reservation "athlon_ssecvt_cvtps2pd_amdfam10" 2 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssecvt") + (and (eq_attr "amdfam10_decode" "direct") + (eq_attr "mode" "V2DF,V4SF,TI")))) + "athlon-direct,athlon-fpsched,athlon-fstore") ;; cvtsi2sd mem,reg is directpath path (cvtsi2sd reg,reg is doublepath) ;; cvtsi2sd has troughput 1 and is executed in store unit with latency of 6 (define_insn_reservation "athlon_sseicvt_cvtsi2sd_load" 6 @@ -713,6 +898,13 @@ (and (eq_attr "mode" "SF,DF") (eq_attr "memory" "load"))))) "athlon-direct,athlon-fploadk8,athlon-fstore") +(define_insn_reservation "athlon_sseicvt_cvtsi2sd_load_amdfam10" 9 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "sseicvt") + (and (eq_attr "amdfam10_decode" "double") + (and (eq_attr "mode" "SF,DF") + (eq_attr "memory" "load"))))) + "athlon-double,athlon-fploadk8,(athlon-faddmul+athlon-fstore)") ;; cvtsi2ss mem, reg is doublepath (define_insn_reservation "athlon_sseicvt_cvtsi2ss_load" 9 (and (eq_attr "cpu" "athlon") @@ -728,6 +920,13 @@ (and (eq_attr "mode" "SF,DF") (eq_attr "memory" "load"))))) "athlon-double,athlon-fploadk8,(athlon-fstore*2)") +(define_insn_reservation "athlon_sseicvt_cvtsi2ss_load_amdfam10" 9 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "sseicvt") + (and (eq_attr "amdfam10_decode" "double") + (and (eq_attr "mode" "SF,DF") + (eq_attr "memory" "load"))))) + "athlon-double,athlon-fploadk8,(athlon-faddmul+athlon-fstore)") ;; cvtsi2sd reg,reg is double decoded (vector on Athlon) (define_insn_reservation "athlon_sseicvt_cvtsi2sd_k8" 11 (and (eq_attr "cpu" "k8,athlon,generic64") @@ -736,6 +935,13 @@ (and (eq_attr "mode" "SF,DF") (eq_attr "memory" "none"))))) "athlon-double,athlon-fploadk8,athlon-fstore") +(define_insn_reservation "athlon_sseicvt_cvtsi2sd_amdfam10" 14 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "sseicvt") + (and (eq_attr "amdfam10_decode" "vector") + (and (eq_attr "mode" "SF,DF") + (eq_attr "memory" "none"))))) + "athlon-vector,athlon-fploadk8,(athlon-faddmul+athlon-fstore)") ;; cvtsi2ss reg, reg is doublepath (define_insn_reservation "athlon_sseicvt_cvtsi2ss" 14 (and (eq_attr "cpu" "athlon,k8,generic64") @@ -744,6 +950,13 @@ (and (eq_attr "mode" "SF,DF") (eq_attr "memory" "none"))))) "athlon-vector,athlon-fploadk8,(athlon-fvector*2)") +(define_insn_reservation "athlon_sseicvt_cvtsi2ss_amdfam10" 14 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "sseicvt") + (and (eq_attr "amdfam10_decode" "vector") + (and (eq_attr "mode" "SF,DF") + (eq_attr "memory" "none"))))) + "athlon-vector,athlon-fploadk8,(athlon-faddmul+athlon-fstore)") ;; cvtsd2ss mem,reg is doublepath, troughput unknown, latency 9 (define_insn_reservation "athlon_ssecvt_cvtsd2ss_load_k8" 9 (and (eq_attr "cpu" "k8,athlon,generic64") @@ -752,6 +965,13 @@ (and (eq_attr "mode" "SF") (eq_attr "memory" "load"))))) "athlon-double,athlon-fploadk8,(athlon-fstore*3)") +(define_insn_reservation "athlon_ssecvt_cvtsd2ss_load_amdfam10" 9 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssecvt") + (and (eq_attr "amdfam10_decode" "double") + (and (eq_attr "mode" "SF") + (eq_attr "memory" "load"))))) + "athlon-double,athlon-fploadk8,(athlon-faddmul+athlon-fstore)") ;; cvtsd2ss reg,reg is vectorpath, troughput unknown, latency 12 (define_insn_reservation "athlon_ssecvt_cvtsd2ss" 12 (and (eq_attr "cpu" "athlon,k8,generic64") @@ -760,6 +980,13 @@ (and (eq_attr "mode" "SF") (eq_attr "memory" "none"))))) "athlon-vector,athlon-fpsched,(athlon-fvector*3)") +(define_insn_reservation "athlon_ssecvt_cvtsd2ss_amdfam10" 8 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssecvt") + (and (eq_attr "amdfam10_decode" "vector") + (and (eq_attr "mode" "SF") + (eq_attr "memory" "none"))))) + "athlon-vector,athlon-fpsched,athlon-faddmul,(athlon-fstore*2)") (define_insn_reservation "athlon_ssecvt_cvtpd2ps_load_k8" 8 (and (eq_attr "cpu" "athlon,k8,generic64") (and (eq_attr "type" "ssecvt") @@ -767,6 +994,13 @@ (and (eq_attr "mode" "V4SF,V2DF,TI") (eq_attr "memory" "load"))))) "athlon-double,athlon-fpload2k8,(athlon-fstore*3)") +(define_insn_reservation "athlon_ssecvt_cvtpd2ps_load_amdfam10" 9 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssecvt") + (and (eq_attr "amdfam10_decode" "double") + (and (eq_attr "mode" "V4SF,V2DF,TI") + (eq_attr "memory" "load"))))) + "athlon-double,athlon-fploadk8,(athlon-faddmul+athlon-fstore)") ;; cvtpd2ps mem,reg is vectorpath, troughput unknown, latency 10 ;; ??? Why it is fater than cvtsd2ss? (define_insn_reservation "athlon_ssecvt_cvtpd2ps" 8 @@ -776,6 +1010,13 @@ (and (eq_attr "mode" "V4SF,V2DF,TI") (eq_attr "memory" "none"))))) "athlon-vector,athlon-fpsched,athlon-fvector*2") +(define_insn_reservation "athlon_ssecvt_cvtpd2ps_amdfam10" 7 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssecvt") + (and (eq_attr "amdfam10_decode" "double") + (and (eq_attr "mode" "V4SF,V2DF,TI") + (eq_attr "memory" "none"))))) + "athlon-double,athlon-fpsched,(athlon-faddmul+athlon-fstore)") ;; cvtsd2si mem,reg is doublepath, troughput 1, latency 9 (define_insn_reservation "athlon_secvt_cvtsX2si_load" 9 (and (eq_attr "cpu" "athlon,k8,generic64") @@ -784,6 +1025,13 @@ (and (eq_attr "mode" "SI,DI") (eq_attr "memory" "load"))))) "athlon-vector,athlon-fploadk8,athlon-fvector") +(define_insn_reservation "athlon_secvt_cvtsX2si_load_amdfam10" 10 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "sseicvt") + (and (eq_attr "amdfam10_decode" "double") + (and (eq_attr "mode" "SI,DI") + (eq_attr "memory" "load"))))) + "athlon-double,athlon-fploadk8,(athlon-fadd+athlon-fstore)") ;; cvtsd2si reg,reg is doublepath, troughput 1, latency 9 (define_insn_reservation "athlon_ssecvt_cvtsX2si" 9 (and (eq_attr "cpu" "athlon") @@ -799,6 +1047,29 @@ (and (eq_attr "mode" "SI,DI") (eq_attr "memory" "none"))))) "athlon-double,athlon-fpsched,athlon-fstore") +(define_insn_reservation "athlon_ssecvt_cvtsX2si_amdfam10" 8 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "sseicvt") + (and (eq_attr "amdfam10_decode" "double") + (and (eq_attr "mode" "SI,DI") + (eq_attr "memory" "none"))))) + "athlon-double,athlon-fpsched,(athlon-fadd+athlon-fstore)") +;; cvtpd2dq reg,mem is doublepath, troughput 1, latency 9 on amdfam10 +(define_insn_reservation "athlon_sseicvt_cvtpd2dq_load_amdfam10" 9 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "sseicvt") + (and (eq_attr "amdfam10_decode" "double") + (and (eq_attr "mode" "TI") + (eq_attr "memory" "load"))))) + "athlon-double,athlon-fploadk8,(athlon-faddmul+athlon-fstore)") +;; cvtpd2dq reg,mem is doublepath, troughput 1, latency 7 on amdfam10 +(define_insn_reservation "athlon_sseicvt_cvtpd2dq_amdfam10" 7 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "sseicvt") + (and (eq_attr "amdfam10_decode" "double") + (and (eq_attr "mode" "TI") + (eq_attr "memory" "none"))))) + "athlon-double,athlon-fpsched,(athlon-faddmul+athlon-fstore)") (define_insn_reservation "athlon_ssemul_load" 4 @@ -808,13 +1079,13 @@ (eq_attr "memory" "load")))) "athlon-direct,athlon-fpload,athlon-fmul") (define_insn_reservation "athlon_ssemul_load_k8" 6 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "ssemul") (and (eq_attr "mode" "SF,DF") (eq_attr "memory" "load")))) "athlon-direct,athlon-fploadk8,athlon-fmul") (define_insn_reservation "athlon_ssemul" 4 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (and (eq_attr "type" "ssemul") (eq_attr "mode" "SF,DF"))) "athlon-direct,athlon-fpsched,athlon-fmul") @@ -828,6 +1099,11 @@ (and (eq_attr "type" "ssemul") (eq_attr "memory" "load"))) "athlon-double,athlon-fpload2k8,(athlon-fmul*2)") +(define_insn_reservation "athlon_ssemulvector_load_amdfam10" 6 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssemul") + (eq_attr "memory" "load"))) + "athlon-direct,athlon-fploadk8,athlon-fmul") (define_insn_reservation "athlon_ssemulvector" 5 (and (eq_attr "cpu" "athlon") (eq_attr "type" "ssemul")) @@ -836,6 +1112,10 @@ (and (eq_attr "cpu" "k8,generic64") (eq_attr "type" "ssemul")) "athlon-double,athlon-fpsched,(athlon-fmul*2)") +(define_insn_reservation "athlon_ssemulvector_amdfam10" 4 + (and (eq_attr "cpu" "amdfam10") + (eq_attr "type" "ssemul")) + "athlon-direct,athlon-fpsched,athlon-fmul") ;; divsd timings. divss is faster (define_insn_reservation "athlon_ssediv_load" 20 (and (eq_attr "cpu" "athlon") @@ -844,13 +1124,13 @@ (eq_attr "memory" "load")))) "athlon-direct,athlon-fpload,athlon-fmul*17") (define_insn_reservation "athlon_ssediv_load_k8" 22 - (and (eq_attr "cpu" "k8,generic64") + (and (eq_attr "cpu" "k8,generic64,amdfam10") (and (eq_attr "type" "ssediv") (and (eq_attr "mode" "SF,DF") (eq_attr "memory" "load")))) "athlon-direct,athlon-fploadk8,athlon-fmul*17") (define_insn_reservation "athlon_ssediv" 20 - (and (eq_attr "cpu" "athlon,k8,generic64") + (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10") (and (eq_attr "type" "ssediv") (eq_attr "mode" "SF,DF"))) "athlon-direct,athlon-fpsched,athlon-fmul*17") @@ -864,6 +1144,11 @@ (and (eq_attr "type" "ssediv") (eq_attr "memory" "load"))) "athlon-double,athlon-fpload2k8,athlon-fmul*34") +(define_insn_reservation "athlon_ssedivvector_load_amdfam10" 22 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "ssediv") + (eq_attr "memory" "load"))) + "athlon-direct,athlon-fploadk8,athlon-fmul*17") (define_insn_reservation "athlon_ssedivvector" 39 (and (eq_attr "cpu" "athlon") (eq_attr "type" "ssediv")) @@ -872,3 +1157,12 @@ (and (eq_attr "cpu" "k8,generic64") (eq_attr "type" "ssediv")) "athlon-double,athlon-fmul*34") +(define_insn_reservation "athlon_ssedivvector_amdfam10" 20 + (and (eq_attr "cpu" "amdfam10") + (eq_attr "type" "ssediv")) + "athlon-direct,athlon-fmul*17") +(define_insn_reservation "athlon_sseins_amdfam10" 5 + (and (eq_attr "cpu" "amdfam10") + (and (eq_attr "type" "sseins") + (eq_attr "mode" "TI"))) + "athlon-vector,athlon-fpsched,athlon-faddmul") diff --git a/contrib/gcc/config/i386/driver-i386.c b/contrib/gcc/config/i386/driver-i386.c index cb9c6c3f3..665826318 100644 --- a/contrib/gcc/config/i386/driver-i386.c +++ b/contrib/gcc/config/i386/driver-i386.c @@ -1,5 +1,5 @@ /* Subroutines for the gcc driver. - Copyright (C) 2006 Free Software Foundation, Inc. + Copyright (C) 2006, 2007 Free Software Foundation, Inc. This file is part of GCC. @@ -40,6 +40,7 @@ const char *host_detect_local_cpu (int argc, const char **argv); #define bit_SSE3 (1 << 0) #define bit_SSSE3 (1 << 9) +#define bit_SSE4a (1 << 6) #define bit_CMPXCHG16B (1 << 13) #define bit_3DNOW (1 << 31) @@ -68,7 +69,7 @@ const char *host_detect_local_cpu (int argc, const char **argv) unsigned int ext_level; unsigned char has_mmx = 0, has_3dnow = 0, has_3dnowp = 0, has_sse = 0; unsigned char has_sse2 = 0, has_sse3 = 0, has_ssse3 = 0, has_cmov = 0; - unsigned char has_longmode = 0, has_cmpxchg8b = 0; + unsigned char has_longmode = 0, has_cmpxchg8b = 0, has_sse4a = 0; unsigned char is_amd = 0; unsigned int family = 0; bool arch; @@ -120,6 +121,7 @@ const char *host_detect_local_cpu (int argc, const char **argv) has_3dnow = !!(edx & bit_3DNOW); has_3dnowp = !!(edx & bit_3DNOWP); has_longmode = !!(edx & bit_LM); + has_sse4a = !!(ecx & bit_SSE4a); } is_amd = vendor == *(unsigned int*)"Auth"; @@ -132,6 +134,8 @@ const char *host_detect_local_cpu (int argc, const char **argv) processor = PROCESSOR_ATHLON; if (has_sse2 || has_longmode) processor = PROCESSOR_K8; + if (has_sse4a) + processor = PROCESSOR_AMDFAM10; } else { @@ -266,6 +270,9 @@ const char *host_detect_local_cpu (int argc, const char **argv) case PROCESSOR_NOCONA: cpu = "nocona"; break; + case PROCESSOR_AMDFAM10: + cpu = "amdfam10"; + break; case PROCESSOR_GENERIC32: case PROCESSOR_GENERIC64: cpu = "generic"; diff --git a/contrib/gcc/config/i386/emmintrin.h b/contrib/gcc/config/i386/emmintrin.h index d30184bc8..acab0a170 100644 --- a/contrib/gcc/config/i386/emmintrin.h +++ b/contrib/gcc/config/i386/emmintrin.h @@ -30,7 +30,11 @@ #ifndef _EMMINTRIN_H_INCLUDED #define _EMMINTRIN_H_INCLUDED -#ifdef __SSE2__ +#ifndef __SSE2__ +# error "SSE2 instruction set not enabled" +#else + +/* We need definitions from the SSE header files*/ #include /* SSE2 */ diff --git a/contrib/gcc/config/i386/i386.c b/contrib/gcc/config/i386/i386.c index 2567fca20..0187cb25d 100644 --- a/contrib/gcc/config/i386/i386.c +++ b/contrib/gcc/config/i386/i386.c @@ -548,6 +548,71 @@ struct processor_costs k8_cost = { COSTS_N_INSNS (35), /* cost of FSQRT instruction. */ }; +struct processor_costs amdfam10_cost = { + COSTS_N_INSNS (1), /* cost of an add instruction */ + COSTS_N_INSNS (2), /* cost of a lea instruction */ + COSTS_N_INSNS (1), /* variable shift costs */ + COSTS_N_INSNS (1), /* constant shift costs */ + {COSTS_N_INSNS (3), /* cost of starting multiply for QI */ + COSTS_N_INSNS (4), /* HI */ + COSTS_N_INSNS (3), /* SI */ + COSTS_N_INSNS (4), /* DI */ + COSTS_N_INSNS (5)}, /* other */ + 0, /* cost of multiply per each bit set */ + {COSTS_N_INSNS (19), /* cost of a divide/mod for QI */ + COSTS_N_INSNS (35), /* HI */ + COSTS_N_INSNS (51), /* SI */ + COSTS_N_INSNS (83), /* DI */ + COSTS_N_INSNS (83)}, /* other */ + COSTS_N_INSNS (1), /* cost of movsx */ + COSTS_N_INSNS (1), /* cost of movzx */ + 8, /* "large" insn */ + 9, /* MOVE_RATIO */ + 4, /* cost for loading QImode using movzbl */ + {3, 4, 3}, /* cost of loading integer registers + in QImode, HImode and SImode. + Relative to reg-reg move (2). */ + {3, 4, 3}, /* cost of storing integer registers */ + 4, /* cost of reg,reg fld/fst */ + {4, 4, 12}, /* cost of loading fp registers + in SFmode, DFmode and XFmode */ + {6, 6, 8}, /* cost of storing fp registers + in SFmode, DFmode and XFmode */ + 2, /* cost of moving MMX register */ + {3, 3}, /* cost of loading MMX registers + in SImode and DImode */ + {4, 4}, /* cost of storing MMX registers + in SImode and DImode */ + 2, /* cost of moving SSE register */ + {4, 4, 3}, /* cost of loading SSE registers + in SImode, DImode and TImode */ + {4, 4, 5}, /* cost of storing SSE registers + in SImode, DImode and TImode */ + 3, /* MMX or SSE register to integer */ + /* On K8 + MOVD reg64, xmmreg Double FSTORE 4 + MOVD reg32, xmmreg Double FSTORE 4 + On AMDFAM10 + MOVD reg64, xmmreg Double FADD 3 + 1/1 1/1 + MOVD reg32, xmmreg Double FADD 3 + 1/1 1/1 */ + 64, /* size of prefetch block */ + /* New AMD processors never drop prefetches; if they cannot be performed + immediately, they are queued. We set number of simultaneous prefetches + to a large constant to reflect this (it probably is not a good idea not + to limit number of prefetches at all, as their execution also takes some + time). */ + 100, /* number of parallel prefetches */ + 5, /* Branch cost */ + COSTS_N_INSNS (4), /* cost of FADD and FSUB insns. */ + COSTS_N_INSNS (4), /* cost of FMUL instruction. */ + COSTS_N_INSNS (19), /* cost of FDIV instruction. */ + COSTS_N_INSNS (2), /* cost of FABS instruction. */ + COSTS_N_INSNS (2), /* cost of FCHS instruction. */ + COSTS_N_INSNS (35), /* cost of FSQRT instruction. */ +}; + static const struct processor_costs pentium4_cost = { COSTS_N_INSNS (1), /* cost of an add instruction */ @@ -834,11 +899,13 @@ const struct processor_costs *ix86_cost = &pentium_cost; #define m_PENT4 (1< #include diff --git a/contrib/gcc/config/i386/sse.md b/contrib/gcc/config/i386/sse.md index 4e25280ce..cbb5f4dff 100644 --- a/contrib/gcc/config/i386/sse.md +++ b/contrib/gcc/config/i386/sse.md @@ -1,5 +1,5 @@ ;; GCC machine description for SSE instructions -;; Copyright (C) 2005, 2006 +;; Copyright (C) 2005, 2006, 2007 ;; Free Software Foundation, Inc. ;; ;; This file is part of GCC. @@ -920,6 +920,7 @@ "cvtsi2ss\t{%2, %0|%0, %2}" [(set_attr "type" "sseicvt") (set_attr "athlon_decode" "vector,double") + (set_attr "amdfam10_decode" "vector,double") (set_attr "mode" "SF")]) (define_insn "sse_cvtsi2ssq" @@ -933,6 +934,7 @@ "cvtsi2ssq\t{%2, %0|%0, %2}" [(set_attr "type" "sseicvt") (set_attr "athlon_decode" "vector,double") + (set_attr "amdfam10_decode" "vector,double") (set_attr "mode" "SF")]) (define_insn "sse_cvtss2si" @@ -946,6 +948,7 @@ "cvtss2si\t{%1, %0|%0, %1}" [(set_attr "type" "sseicvt") (set_attr "athlon_decode" "double,vector") + (set_attr "amdfam10_decode" "double,double") (set_attr "mode" "SI")]) (define_insn "sse_cvtss2siq" @@ -959,6 +962,7 @@ "cvtss2siq\t{%1, %0|%0, %1}" [(set_attr "type" "sseicvt") (set_attr "athlon_decode" "double,vector") + (set_attr "amdfam10_decode" "double,double") (set_attr "mode" "DI")]) (define_insn "sse_cvttss2si" @@ -971,6 +975,7 @@ "cvttss2si\t{%1, %0|%0, %1}" [(set_attr "type" "sseicvt") (set_attr "athlon_decode" "double,vector") + (set_attr "amdfam10_decode" "double,double") (set_attr "mode" "SI")]) (define_insn "sse_cvttss2siq" @@ -983,6 +988,7 @@ "cvttss2siq\t{%1, %0|%0, %1}" [(set_attr "type" "sseicvt") (set_attr "athlon_decode" "double,vector") + (set_attr "amdfam10_decode" "double,double") (set_attr "mode" "DI")]) (define_insn "sse2_cvtdq2ps" @@ -1852,7 +1858,8 @@ "cvtsi2sd\t{%2, %0|%0, %2}" [(set_attr "type" "sseicvt") (set_attr "mode" "DF") - (set_attr "athlon_decode" "double,direct")]) + (set_attr "athlon_decode" "double,direct") + (set_attr "amdfam10_decode" "vector,double")]) (define_insn "sse2_cvtsi2sdq" [(set (match_operand:V2DF 0 "register_operand" "=x,x") @@ -1865,7 +1872,8 @@ "cvtsi2sdq\t{%2, %0|%0, %2}" [(set_attr "type" "sseicvt") (set_attr "mode" "DF") - (set_attr "athlon_decode" "double,direct")]) + (set_attr "athlon_decode" "double,direct") + (set_attr "amdfam10_decode" "vector,double")]) (define_insn "sse2_cvtsd2si" [(set (match_operand:SI 0 "register_operand" "=r,r") @@ -1878,6 +1886,7 @@ "cvtsd2si\t{%1, %0|%0, %1}" [(set_attr "type" "sseicvt") (set_attr "athlon_decode" "double,vector") + (set_attr "amdfam10_decode" "double,double") (set_attr "mode" "SI")]) (define_insn "sse2_cvtsd2siq" @@ -1891,6 +1900,7 @@ "cvtsd2siq\t{%1, %0|%0, %1}" [(set_attr "type" "sseicvt") (set_attr "athlon_decode" "double,vector") + (set_attr "amdfam10_decode" "double,double") (set_attr "mode" "DI")]) (define_insn "sse2_cvttsd2si" @@ -1903,7 +1913,8 @@ "cvttsd2si\t{%1, %0|%0, %1}" [(set_attr "type" "sseicvt") (set_attr "mode" "SI") - (set_attr "athlon_decode" "double,vector")]) + (set_attr "athlon_decode" "double,vector") + (set_attr "amdfam10_decode" "double,double")]) (define_insn "sse2_cvttsd2siq" [(set (match_operand:DI 0 "register_operand" "=r,r") @@ -1915,7 +1926,8 @@ "cvttsd2siq\t{%1, %0|%0, %1}" [(set_attr "type" "sseicvt") (set_attr "mode" "DI") - (set_attr "athlon_decode" "double,vector")]) + (set_attr "athlon_decode" "double,vector") + (set_attr "amdfam10_decode" "double,double")]) (define_insn "sse2_cvtdq2pd" [(set (match_operand:V2DF 0 "register_operand" "=x") @@ -1946,7 +1958,8 @@ "TARGET_SSE2" "cvtpd2dq\t{%1, %0|%0, %1}" [(set_attr "type" "ssecvt") - (set_attr "mode" "TI")]) + (set_attr "mode" "TI") + (set_attr "amdfam10_decode" "double")]) (define_expand "sse2_cvttpd2dq" [(set (match_operand:V4SI 0 "register_operand" "") @@ -1964,7 +1977,8 @@ "TARGET_SSE2" "cvttpd2dq\t{%1, %0|%0, %1}" [(set_attr "type" "ssecvt") - (set_attr "mode" "TI")]) + (set_attr "mode" "TI") + (set_attr "amdfam10_decode" "double")]) (define_insn "sse2_cvtsd2ss" [(set (match_operand:V4SF 0 "register_operand" "=x,x") @@ -1978,20 +1992,22 @@ "cvtsd2ss\t{%2, %0|%0, %2}" [(set_attr "type" "ssecvt") (set_attr "athlon_decode" "vector,double") + (set_attr "amdfam10_decode" "vector,double") (set_attr "mode" "SF")]) (define_insn "sse2_cvtss2sd" - [(set (match_operand:V2DF 0 "register_operand" "=x") + [(set (match_operand:V2DF 0 "register_operand" "=x,x") (vec_merge:V2DF (float_extend:V2DF (vec_select:V2SF - (match_operand:V4SF 2 "nonimmediate_operand" "xm") + (match_operand:V4SF 2 "nonimmediate_operand" "x,m") (parallel [(const_int 0) (const_int 1)]))) - (match_operand:V2DF 1 "register_operand" "0") + (match_operand:V2DF 1 "register_operand" "0,0") (const_int 1)))] "TARGET_SSE2" "cvtss2sd\t{%2, %0|%0, %2}" [(set_attr "type" "ssecvt") + (set_attr "amdfam10_decode" "vector,double") (set_attr "mode" "DF")]) (define_expand "sse2_cvtpd2ps" @@ -2012,7 +2028,8 @@ "TARGET_SSE2" "cvtpd2ps\t{%1, %0|%0, %1}" [(set_attr "type" "ssecvt") - (set_attr "mode" "V4SF")]) + (set_attr "mode" "V4SF") + (set_attr "amdfam10_decode" "double")]) (define_insn "sse2_cvtps2pd" [(set (match_operand:V2DF 0 "register_operand" "=x") @@ -2023,7 +2040,8 @@ "TARGET_SSE2" "cvtps2pd\t{%1, %0|%0, %1}" [(set_attr "type" "ssecvt") - (set_attr "mode" "V2DF")]) + (set_attr "mode" "V2DF") + (set_attr "amdfam10_decode" "direct")]) ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; ;; @@ -4524,3 +4542,92 @@ "pabs\t{%1, %0|%0, %1}"; [(set_attr "type" "sselog1") (set_attr "mode" "DI")]) + +;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; +;; +;; AMD SSE4A instructions +;; +;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; + +(define_insn "sse4a_vmmovntv2df" + [(set (match_operand:DF 0 "memory_operand" "=m") + (unspec:DF [(vec_select:DF + (match_operand:V2DF 1 "register_operand" "x") + (parallel [(const_int 0)]))] + UNSPEC_MOVNT))] + "TARGET_SSE4A" + "movntsd\t{%1, %0|%0, %1}" + [(set_attr "type" "ssemov") + (set_attr "mode" "DF")]) + +(define_insn "sse4a_movntdf" + [(set (match_operand:DF 0 "memory_operand" "=m") + (unspec:DF [(match_operand:DF 1 "register_operand" "x")] + UNSPEC_MOVNT))] + "TARGET_SSE4A" + "movntsd\t{%1, %0|%0, %1}" + [(set_attr "type" "ssemov") + (set_attr "mode" "DF")]) + +(define_insn "sse4a_vmmovntv4sf" + [(set (match_operand:SF 0 "memory_operand" "=m") + (unspec:SF [(vec_select:SF + (match_operand:V4SF 1 "register_operand" "x") + (parallel [(const_int 0)]))] + UNSPEC_MOVNT))] + "TARGET_SSE4A" + "movntss\t{%1, %0|%0, %1}" + [(set_attr "type" "ssemov") + (set_attr "mode" "SF")]) + +(define_insn "sse4a_movntsf" + [(set (match_operand:SF 0 "memory_operand" "=m") + (unspec:SF [(match_operand:SF 1 "register_operand" "x")] + UNSPEC_MOVNT))] + "TARGET_SSE4A" + "movntss\t{%1, %0|%0, %1}" + [(set_attr "type" "ssemov") + (set_attr "mode" "SF")]) + +(define_insn "sse4a_extrqi" + [(set (match_operand:V2DI 0 "register_operand" "=x") + (unspec:V2DI [(match_operand:V2DI 1 "register_operand" "0") + (match_operand 2 "const_int_operand" "") + (match_operand 3 "const_int_operand" "")] + UNSPEC_EXTRQI))] + "TARGET_SSE4A" + "extrq\t{%3, %2, %0|%0, %2, %3}" + [(set_attr "type" "sse") + (set_attr "mode" "TI")]) + +(define_insn "sse4a_extrq" + [(set (match_operand:V2DI 0 "register_operand" "=x") + (unspec:V2DI [(match_operand:V2DI 1 "register_operand" "0") + (match_operand:V16QI 2 "register_operand" "x")] + UNSPEC_EXTRQ))] + "TARGET_SSE4A" + "extrq\t{%2, %0|%0, %2}" + [(set_attr "type" "sse") + (set_attr "mode" "TI")]) + +(define_insn "sse4a_insertqi" + [(set (match_operand:V2DI 0 "register_operand" "=x") + (unspec:V2DI [(match_operand:V2DI 1 "register_operand" "0") + (match_operand:V2DI 2 "register_operand" "x") + (match_operand 3 "const_int_operand" "") + (match_operand 4 "const_int_operand" "")] + UNSPEC_INSERTQI))] + "TARGET_SSE4A" + "insertq\t{%4, %3, %2, %0|%0, %2, %3, %4}" + [(set_attr "type" "sseins") + (set_attr "mode" "TI")]) + +(define_insn "sse4a_insertq" + [(set (match_operand:V2DI 0 "register_operand" "=x") + (unspec:V2DI [(match_operand:V2DI 1 "register_operand" "0") + (match_operand:V2DI 2 "register_operand" "x")] + UNSPEC_INSERTQ))] + "TARGET_SSE4A" + "insertq\t{%2, %0|%0, %2}" + [(set_attr "type" "sseins") + (set_attr "mode" "TI")]) diff --git a/contrib/gcc/config/i386/tmmintrin.h b/contrib/gcc/config/i386/tmmintrin.h index e53dd0f5c..cf9d99d09 100644 --- a/contrib/gcc/config/i386/tmmintrin.h +++ b/contrib/gcc/config/i386/tmmintrin.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006 Free Software Foundation, Inc. +/* Copyright (C) 2006, 2007 Free Software Foundation, Inc. This file is part of GCC. @@ -30,7 +30,11 @@ #ifndef _TMMINTRIN_H_INCLUDED #define _TMMINTRIN_H_INCLUDED -#ifdef __SSSE3__ +#ifndef __SSSE3__ +# error "SSSE3 instruction set not enabled" +#else + +/* We need definitions from the SSE3, SSE2 and SSE header files*/ #include static __inline __m128i __attribute__((__always_inline__)) diff --git a/contrib/gcc/doc/extend.texi b/contrib/gcc/doc/extend.texi index 0c8bb7d09..d7a1494ee 100644 --- a/contrib/gcc/doc/extend.texi +++ b/contrib/gcc/doc/extend.texi @@ -7255,6 +7255,23 @@ v4si __builtin_ia32_pabsd128 (v4si) v8hi __builtin_ia32_pabsw128 (v8hi) @end smallexample +The following built-in functions are available when @option{-msse4a} is used. + +@smallexample +void _mm_stream_sd (double*,__m128d); +Generates the @code{movntsd} machine instruction. +void _mm_stream_ss (float*,__m128); +Generates the @code{movntss} machine instruction. +__m128i _mm_extract_si64 (__m128i, __m128i); +Generates the @code{extrq} machine instruction with only SSE register operands. +__m128i _mm_extracti_si64 (__m128i, int, int); +Generates the @code{extrq} machine instruction with SSE register and immediate operands. +__m128i _mm_insert_si64 (__m128i, __m128i); +Generates the @code{insertq} machine instruction with only SSE register operands. +__m128i _mm_inserti_si64 (__m128i, __m128i, int, int); +Generates the @code{insertq} machine instruction with SSE register and immediate operands. +@end smallexample + The following built-in functions are available when @option{-m3dnow} is used. All of them generate the machine instruction that is part of the name. diff --git a/contrib/gcc/doc/invoke.texi b/contrib/gcc/doc/invoke.texi index 0c391369d..0f66c3dc2 100644 --- a/contrib/gcc/doc/invoke.texi +++ b/contrib/gcc/doc/invoke.texi @@ -513,7 +513,7 @@ in the following sections. -mno-fp-ret-in-387 -msoft-float -msvr3-shlib @gol -mno-wide-multiply -mrtd -malign-double @gol -mpreferred-stack-boundary=@var{num} @gol --mmmx -msse -msse2 -msse3 -mssse3 -m3dnow @gol +-mmmx -msse -msse2 -msse3 -mssse3 -msse4a -m3dnow -mpopcnt -mabm @gol -mthreads -mno-align-stringops -minline-all-stringops @gol -mpush-args -maccumulate-outgoing-args -m128bit-long-double @gol -m96bit-long-double -mregparm=@var{num} -msseregparm @gol @@ -9061,6 +9061,10 @@ AMD K8 core based CPUs with x86-64 instruction set support. (This supersets MMX, SSE, SSE2, 3dNOW!, enhanced 3dNOW! and 64-bit instruction set extensions.) @item k8-sse3, opteron-sse3, athlon64-sse3 Improved versions of k8, opteron and athlon64 with SSE3 instruction set support. +@item amdfam10, barcelona +AMD Family 10h core based CPUs with x86-64 instruction set support. (This +supersets MMX, SSE, SSE2, SSE3, SSE4A, 3dNOW!, enhanced 3dNOW!, ABM and 64-bit +instruction set extensions.) @item winchip-c6 IDT Winchip C6 CPU, dealt in same way as i486 with additional MMX instruction set support. @@ -9355,8 +9359,14 @@ preferred alignment to @option{-mpreferred-stack-boundary=2}. @itemx -mno-sse3 @item -mssse3 @itemx -mno-ssse3 +@item -msse4a +@item -mno-sse4a @item -m3dnow @itemx -mno-3dnow +@item -mpopcnt +@itemx -mno-popcnt +@item -mabm +@itemx -mno-abm @opindex mmmx @opindex mno-mmx @opindex msse @@ -9364,7 +9374,7 @@ preferred alignment to @option{-mpreferred-stack-boundary=2}. @opindex m3dnow @opindex mno-3dnow These switches enable or disable the use of instructions in the MMX, -SSE, SSE2, SSE3, SSSE3 or 3DNow! extended instruction sets. +SSE, SSE2, SSE3, SSSE3, SSE4A, ABM or 3DNow! extended instruction sets. These extensions are also available as built-in functions: see @ref{X86 Built-in Functions}, for details of the functions enabled and disabled by these switches. diff --git a/gnu/usr.bin/cc/include/Makefile b/gnu/usr.bin/cc/include/Makefile index d436a304e..e8a666fc8 100644 --- a/gnu/usr.bin/cc/include/Makefile +++ b/gnu/usr.bin/cc/include/Makefile @@ -7,8 +7,8 @@ INCSDIR=${INCLUDEDIR}/gcc/${GCCVER} .PATH: ${GCCDIR}/config/${GCC_CPU} .if ${TARGET_ARCH} == "i386" || ${TARGET_ARCH} == "amd64" -INCS= emmintrin.h mmintrin.h mm3dnow.h pmmintrin.h tmmintrin.h xmmintrin.h \ - mm_malloc.h +INCS= ammintrin.h emmintrin.h mmintrin.h mm3dnow.h pmmintrin.h \ + tmmintrin.h xmmintrin.h mm_malloc.h .elif ${TARGET_ARCH} == "ia64" INCS= ia64intrin.h .elif ${TARGET_ARCH} == "arm" -- 2.45.0