From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 1592) id E3AB0395A07B; Wed, 16 Nov 2022 13:41:52 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org E3AB0395A07B DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1668606112; bh=46J3oKf7kEBkwy7vcA2I4mNl9xxRQbZwRphIRaI/TkI=; h=From:To:Subject:Date:From; b=OhROFzSrBIDREQEmJbQ9pxe2/f1B+Tw6izXVKTTDFJdGhLWMDDh3x5dEfEfZtRKv1 0GIgIRFle17ShpYXOTv1/wV5USz/GtCCcqiRgaOvLhvM8exPYShfvfn7uuImlsVC+z d7vrworRV95aYKVDF17w+5DQdTeCIm2EM387veDA= MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset="utf-8" From: Alexander Monakov To: gcc-cvs@gcc.gnu.org Subject: [gcc r13-4092] i386: correct x87&SSE division modeling in znver.md X-Act-Checkin: gcc X-Git-Author: Alexander Monakov X-Git-Refname: refs/heads/master X-Git-Oldrev: 3c54805d03ac1bcc3d8547ffb5e6c4e1f301a7a2 X-Git-Newrev: dd744f06c9952f92738b0860630085f0f0b99574 Message-Id: <20221116134152.E3AB0395A07B@sourceware.org> Date: Wed, 16 Nov 2022 13:41:52 +0000 (GMT) List-Id: https://gcc.gnu.org/g:dd744f06c9952f92738b0860630085f0f0b99574 commit r13-4092-gdd744f06c9952f92738b0860630085f0f0b99574 Author: Alexander Monakov Date: Tue Nov 1 17:04:25 2022 +0300 i386: correct x87&SSE division modeling in znver.md Correct modeling of division instructions in the SIMD/FP domain for AMD Zen architectures and avoid combinatorial explosion of automaton tables by modeling the separate floating-point division unit and correcting reservations to reflect reciprocal throughput of the corresponding instructions, similar to earlier commit 5cee5f94000 ("i386: correct integer division modeling in znver.md"). Division is partially pipelined and some instructions have fractional throughput (e.g. Zen 3 can issue divss and divsd each 3.5 and 4.5 cycles on average, respectively). Considering these CPUs implement out-of-order execution, the model doesn't need to be exact to the last cycle, so simplify it by using 4/5 cycles for SF/DF modes, and not modeling the fact that FP3 pipe is occupied for one cycle. Top znver table sizes in insn-automata.o: Before: 428108 r znver1_fp_min_issue_delay 856216 r znver1_fp_transitions After: 30056 r znver1_fp_min_issue_delay 120224 r znver1_fp_transitions gcc/ChangeLog: PR target/87832 * config/i386/znver.md (znver1_fdiv): New automaton. (znver1-fdiv): New unit. (znver1_fp_op_div): Correct unit and cycles in the reservation. (znver1_fp_op_div_load): Ditto. (znver1_fp_op_idiv_load): Ditto. (znver2_fp_op_idiv_load): Ditto. (znver1_ssediv_ss_ps): Ditto. (znver1_ssediv_ss_ps_load): Ditto. (znver1_ssediv_sd_pd): Ditto. (znver1_ssediv_sd_pd_load): Ditto. (znver1_ssediv_avx256_ps): Ditto. (znver1_ssediv_avx256_ps_load): Ditto. (znver1_ssediv_avx256_pd): Ditto. (znver1_ssediv_avx256_pd_load): Ditto. Diff: --- gcc/config/i386/znver.md | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/gcc/config/i386/znver.md b/gcc/config/i386/znver.md index 4aa098fd80c..c52f8b532ec 100644 --- a/gcc/config/i386/znver.md +++ b/gcc/config/i386/znver.md @@ -24,7 +24,7 @@ ;; AMD znver1, znver2 and znver3 Scheduling ;; Modeling automatons for zen decoders, integer execution pipes, ;; SIMD/FP domain, AGU pipes, and dividers. -(define_automaton "znver1, znver1_ieu, znver1_fp, znver1_agu, znver1_idiv") +(define_automaton "znver1, znver1_ieu, znver1_fp, znver1_agu, znver1_idiv, znver1_fdiv") ;; Decoders unit has 4 decoders and all of them can decode fast path ;; and vector type instructions. @@ -95,6 +95,7 @@ ;; Dividers (define_cpu_unit "znver1-idiv" "znver1_idiv") +(define_cpu_unit "znver1-fdiv" "znver1_fdiv") ;; Call instruction (define_insn_reservation "znver1_call" 1 @@ -591,27 +592,27 @@ (and (eq_attr "cpu" "znver1,znver2,znver3") (and (eq_attr "type" "fdiv") (eq_attr "memory" "none"))) - "znver1-direct,znver1-fp3*15") + "znver1-direct,znver1-fdiv*6") (define_insn_reservation "znver1_fp_op_div_load" 22 (and (eq_attr "cpu" "znver1,znver2,znver3") (and (eq_attr "type" "fdiv") (eq_attr "memory" "load"))) - "znver1-direct,znver1-load,znver1-fp3*15") + "znver1-direct,znver1-load,znver1-fdiv*6") (define_insn_reservation "znver1_fp_op_idiv_load" 27 (and (eq_attr "cpu" "znver1") (and (eq_attr "type" "fdiv") (and (eq_attr "fp_int_src" "true") (eq_attr "memory" "load")))) - "znver1-double,znver1-load,znver1-fp3*19") + "znver1-double,znver1-load,znver1-fdiv*6") (define_insn_reservation "znver2_fp_op_idiv_load" 26 (and (eq_attr "cpu" "znver2,znver3") (and (eq_attr "type" "fdiv") (and (eq_attr "fp_int_src" "true") (eq_attr "memory" "load")))) - "znver1-double,znver1-load,znver1-fp3*19") + "znver1-double,znver1-load,znver1-fdiv*6") ;; MMX, SSE, SSEn.n, AVX, AVX2 instructions @@ -1088,7 +1089,7 @@ (eq_attr "mode" "V8SF,V4SF,SF"))) (and (eq_attr "type" "ssediv") (eq_attr "memory" "none"))) - "znver1-direct,znver1-fp3*10") + "znver1-direct,znver1-fdiv*4") (define_insn_reservation "znver1_ssediv_ss_ps_load" 17 (and (ior (and (eq_attr "cpu" "znver1") @@ -1099,7 +1100,7 @@ (eq_attr "mode" "V8SF,V4SF,SF"))) (and (eq_attr "type" "ssediv") (eq_attr "memory" "load"))) - "znver1-direct,znver1-load,znver1-fp3*10") + "znver1-direct,znver1-load,znver1-fdiv*4") (define_insn_reservation "znver1_ssediv_sd_pd" 13 (and (ior (and (eq_attr "cpu" "znver1") @@ -1110,7 +1111,7 @@ (eq_attr "mode" "V4DF,V2DF,DF"))) (and (eq_attr "type" "ssediv") (eq_attr "memory" "none"))) - "znver1-direct,znver1-fp3*13") + "znver1-direct,znver1-fdiv*5") (define_insn_reservation "znver1_ssediv_sd_pd_load" 20 (and (ior (and (eq_attr "cpu" "znver1") @@ -1121,35 +1122,35 @@ (eq_attr "mode" "V4DF,V2DF,DF"))) (and (eq_attr "type" "ssediv") (eq_attr "memory" "load"))) - "znver1-direct,znver1-load,znver1-fp3*13") + "znver1-direct,znver1-load,znver1-fdiv*5") (define_insn_reservation "znver1_ssediv_avx256_ps" 12 (and (eq_attr "cpu" "znver1") (and (eq_attr "mode" "V8SF") (and (eq_attr "memory" "none") (eq_attr "type" "ssediv")))) - "znver1-double,znver1-fp3*12") + "znver1-double,znver1-fdiv*8") (define_insn_reservation "znver1_ssediv_avx256_ps_load" 19 (and (eq_attr "cpu" "znver1") (and (eq_attr "mode" "V8SF") (and (eq_attr "type" "ssediv") (eq_attr "memory" "load")))) - "znver1-double,znver1-load,znver1-fp3*12") + "znver1-double,znver1-load,znver1-fdiv*8") (define_insn_reservation "znver1_ssediv_avx256_pd" 15 (and (eq_attr "cpu" "znver1") (and (eq_attr "mode" "V4DF") (and (eq_attr "type" "ssediv") (eq_attr "memory" "none")))) - "znver1-double,znver1-fp3*15") + "znver1-double,znver1-fdiv*10") (define_insn_reservation "znver1_ssediv_avx256_pd_load" 22 (and (eq_attr "cpu" "znver1") (and (eq_attr "mode" "V4DF") (and (eq_attr "type" "ssediv") (eq_attr "memory" "load")))) - "znver1-double,znver1-load,znver1-fp3*15") + "znver1-double,znver1-load,znver1-fdiv*10") ;; SSE MUL (define_insn_reservation "znver1_ssemul_ss_ps" 3 (and (ior (and (eq_attr "cpu" "znver1")