This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

RE: [patch] tuning gcc for AMDFAM10 processor (patches 4 to 11)


These are patches 4 to 11 of 11 patches to tune gcc for AMD's AMDFAM10
processor (based on mainline rev 121295). These patches tune scheduling
for amdfam10.

Patches have been reviewed by Richard Henderson and Jan Hubicka and also
pre-reviewed by Diego Novillo. 

Patch 4
-------
2007-01-29      Harsha Jagasia  <harsha.jagasia@amd.com>


        * gcc/gcc/config/i386/athlon.md (athlon_ssedivvector_amdfam10,
        athlon_ssedivvector_load_amdfam10, athlon_ssemulvector_amdfam10,
        athlon_ssemulvector_load_amdfam10): new.
        (athlon_ssediv, athlon_ssediv_load_k8, athlon_ssemul,
        athlon_ssemul_load_k8): added amdfam10.

Patch 5
-------
2007-01-29      Harsha Jagasia  <harsha.jagasia@amd.com>


        * gcc/gcc/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

        * gcc/gcc/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

Patch 6
-------
2007-01-29      Harsha Jagasia  <harsha.jagasia@amd.com>


        * gcc/gcc/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


Patch 7
-------
2007-01-29      Harsha Jagasia  <harsha.jagasia@amd.com>


        * gcc/gcc/config/i386/athlon.md (athlon_sseins_amdfam10
        ): new define_insn_reservation

        * gcc/gcc/config/i386/i38.md (sseins: added sseins to
        define_attr type and define_attr unit

        * gcc/gcc/config/i386/sse.md: set type attribute to
        sseins for insertq and insertqi

Patch 8
-------
2007-01-29      Harsha Jagasia  <harsha.jagasia@amd.com>


        * gcc/gcc/config/i386/athlon.md (athlon_sseld_amdfam10,
        athlon_mmxld_amdfam10, athlon_ssest_amdfam10,
        athlon_mmxssest_short_amdfam10): new

Patch 9
-------
2007-01-29      Harsha Jagasia  <harsha.jagasia@amd.com>


        * gcc/gcc/config/i386/athlon.md (athlon_call_amdfam10,
        athlon_pop_amdfam10, athlon_lea_amdfam10): new
        (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

Patch 10
--------
2007-01-29      Harsha Jagasia  <harsha.jagasia@amd.com>


        * gcc/gcc/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

        * gcc/gcc/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
        (athlon_idirect_loadmov, athlon_idirect_movstore): added
        amdfam10

Patch 11
--------
2007-01-29      Harsha Jagasia  <harsha.jagasia@amd.com>


        * gcc/gcc/config/i386/athlon.md (athlon_fldxf_k8,
        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_load, athlon_fmul_load_k8, athlon_fmul,
        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

Thanks,
Harsha Jagasia

Attachment: gcc-amdfam10-4.patch
Description: gcc-amdfam10-4.patch

Attachment: gcc-amdfam10-5.patch
Description: gcc-amdfam10-5.patch

Attachment: gcc-amdfam10-6.patch
Description: gcc-amdfam10-6.patch

Attachment: gcc-amdfam10-7.patch
Description: gcc-amdfam10-7.patch

Attachment: gcc-amdfam10-8.patch
Description: gcc-amdfam10-8.patch

Attachment: gcc-amdfam10-9.patch
Description: gcc-amdfam10-9.patch

Attachment: gcc-amdfam10-10.patch
Description: gcc-amdfam10-10.patch

Attachment: gcc-amdfam10-11.patch
Description: gcc-amdfam10-11.patch


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]