All multiplication instructions are fully pipelined, except AVX256
instructions on Zen 1, which issue over two cycles on a 128-bit unit.
Correct the model accordingly to reduce combinatorial explosion in
automaton tables.
Top znver table sizes in insn-automata.o:
Before:
30056 r znver1_fp_min_issue_delay
120224 r znver1_fp_transitions
After:
6720 r znver1_fp_min_issue_delay
53760 r znver1_fp_transitions
gcc/ChangeLog:
PR target/87832
* config/i386/znver.md: (znver1_fp_op_mul): Correct cycles in
the reservation.
(znver1_fp_op_mul_load): Ditto.
(znver1_mmx_mul): Ditto.
(znver1_mmx_load): Ditto.
(znver1_ssemul_ss_ps): Ditto.
(znver1_ssemul_ss_ps_load): Ditto.
(znver1_ssemul_avx256_ps): Ditto.
(znver1_ssemul_avx256_ps_load): Ditto.
(znver1_ssemul_sd_pd): Ditto.
(znver1_ssemul_sd_pd_load): Ditto.
(znver2_ssemul_sd_pd): Ditto.
(znver2_ssemul_sd_pd_load): Ditto.
(znver1_ssemul_avx256_pd): Ditto.
(znver1_ssemul_avx256_pd_load): Ditto.
(znver1_sseimul): Ditto.
(znver1_sseimul_avx256): Ditto.
(znver1_sseimul_load): Ditto.
(znver1_sseimul_avx256_load): Ditto.
(znver1_sseimul_di): Ditto.
(znver1_sseimul_load_di): Ditto.
---
gcc/config/i386/znver.md | 40 ++++++++++++++++++++--------------------
1 file changed, 20 insertions(+), 20 deletions(-)
diff --git a/gcc/config/i386/znver.md b/gcc/config/i386/znver.md
index c52f8b532..882f250f1 100644
--- a/gcc/config/i386/znver.md
+++ b/gcc/config/i386/znver.md
@@ -573,13 +573,13 @@ (define_insn_reservation "znver1_fp_op_mul" 5
(and (eq_attr "cpu" "znver1,znver2,znver3")
(and (eq_attr "type" "fop,fmul")
(eq_attr "memory" "none")))
- "znver1-direct,znver1-fp0*5")
+ "znver1-direct,znver1-fp0")
(define_insn_reservation "znver1_fp_op_mul_load" 12
(and (eq_attr "cpu" "znver1,znver2,znver3")
(and (eq_attr "type" "fop,fmul")
(eq_attr "memory" "load")))
- "znver1-direct,znver1-load,znver1-fp0*5")
+ "znver1-direct,znver1-load,znver1-fp0")
(define_insn_reservation "znver1_fp_op_imul_load" 16
(and (eq_attr "cpu" "znver1,znver2,znver3")
@@ -684,13 +684,13 @@ (define_insn_reservation "znver1_mmx_mul" 3
(and (eq_attr "cpu" "znver1,znver2,znver3")
(and (eq_attr "type" "mmxmul")
(eq_attr "memory" "none")))
- "znver1-direct,znver1-fp0*3")
+ "znver1-direct,znver1-fp0")
(define_insn_reservation "znver1_mmx_load" 10
(and (eq_attr "cpu" "znver1,znver2,znver3")
(and (eq_attr "type" "mmxmul")
(eq_attr "memory" "load")))
- "znver1-direct,znver1-load,znver1-fp0*3")
+ "znver1-direct,znver1-load,znver1-fp0")
;; TODO
(define_insn_reservation "znver1_avx256_log" 1
@@ -1161,7 +1161,7 @@ (define_insn_reservation "znver1_ssemul_ss_ps" 3
(eq_attr "mode"
"V8SF,V4SF,SF,V4DF,V2DF,DF")))
(and (eq_attr "type" "ssemul")
(eq_attr "memory" "none")))
- "znver1-direct,(znver1-fp0|znver1-fp1)*3")
+ "znver1-direct,znver1-fp0|znver1-fp1")
(define_insn_reservation "znver1_ssemul_ss_ps_load" 10
(and (ior (and (eq_attr "cpu" "znver1")
@@ -1172,47 +1172,47 @@ (define_insn_reservation "znver1_ssemul_ss_ps_load" 10
(eq_attr "mode" "V8SF,V4SF,SF")))
(and (eq_attr "type" "ssemul")
(eq_attr "memory" "load")))
- "znver1-direct,znver1-load,(znver1-fp0|znver1-fp1)*3")
+ "znver1-direct,znver1-load,znver1-fp0|znver1-fp1")
(define_insn_reservation "znver1_ssemul_avx256_ps" 3
(and (eq_attr "cpu" "znver1")
(and (eq_attr "mode" "V8SF")
(and (eq_attr "type" "ssemul")
(eq_attr "memory" "none"))))
- "znver1-double,(znver1-fp0|znver1-fp1)*3")
+ "znver1-double,znver1-fp0*2|znver1-fp1*2")
(define_insn_reservation "znver1_ssemul_avx256_ps_load" 10
(and (eq_attr "cpu" "znver1")
(and (eq_attr "mode" "V8SF")
(and (eq_attr "type" "ssemul")
(eq_attr "memory" "load"))))
- "znver1-double,znver1-load,(znver1-fp0|znver1-fp1)*3")
+ "znver1-double,znver1-load,znver1-fp0*2|znver1-fp1*2")
(define_insn_reservation "znver1_ssemul_sd_pd" 4
(and (eq_attr "cpu" "znver1")
(and (eq_attr "mode" "V2DF,DF")
(and (eq_attr "type" "ssemul")
(eq_attr "memory" "none"))))
- "znver1-direct,(znver1-fp0|znver1-fp1)*4")
+ "znver1-direct,znver1-fp0|znver1-fp1")
(define_insn_reservation "znver1_ssemul_sd_pd_load" 11
(and (eq_attr "cpu" "znver1")
(and (eq_attr "mode" "V2DF,DF")
(and (eq_attr "type" "ssemul")
(eq_attr "memory" "load"))))
- "znver1-direct,znver1-load,(znver1-fp0|znver1-fp1)*4")
+ "znver1-direct,znver1-load,znver1-fp0|znver1-fp1")
(define_insn_reservation "znver2_ssemul_sd_pd" 3
(and (eq_attr "cpu" "znver2,znver3")
(and (eq_attr "type" "ssemul")
(eq_attr "memory" "none")))
- "znver1-direct,(znver1-fp0|znver1-fp1)*3")
+ "znver1-direct,znver1-fp0|znver1-fp1")
(define_insn_reservation "znver2_ssemul_sd_pd_load" 10
(and (eq_attr "cpu" "znver2,znver3")
(and (eq_attr "type" "ssemul")
(eq_attr "memory" "load")))
- "znver1-direct,znver1-load,(znver1-fp0|znver1-fp1)*3")
+ "znver1-direct,znver1-load,znver1-fp0|znver1-fp1")
(define_insn_reservation "znver1_ssemul_avx256_pd" 5
@@ -1220,14 +1220,14 @@ (define_insn_reservation "znver1_ssemul_avx256_pd" 5
(and (eq_attr "mode" "V4DF")
(and (eq_attr "type" "ssemul")
(eq_attr "memory" "none"))))
- "znver1-double,(znver1-fp0|znver1-fp1)*4")
+ "znver1-double,znver1-fp0*2|znver1-fp1*2")
(define_insn_reservation "znver1_ssemul_avx256_pd_load" 12
(and (eq_attr "cpu" "znver1")
(and (eq_attr "mode" "V4DF")
(and (eq_attr "type" "ssemul")
(eq_attr "memory" "load"))))
- "znver1-double,znver1-load,(znver1-fp0|znver1-fp1)*4")
+ "znver1-double,znver1-load,znver1-fp0*2|znver1-fp1*2")
;;SSE imul
(define_insn_reservation "znver1_sseimul" 3
@@ -1239,14 +1239,14 @@ (define_insn_reservation "znver1_sseimul" 3
(eq_attr "mode" "TI,OI")))
(and (eq_attr "type" "sseimul")
(eq_attr "memory" "none")))
- "znver1-direct,znver1-fp0*3")
+ "znver1-direct,znver1-fp0")
(define_insn_reservation "znver1_sseimul_avx256" 4
(and (eq_attr "cpu" "znver1,znver2,znver3")
(and (eq_attr "mode" "OI")
(and (eq_attr "type" "sseimul")
(eq_attr "memory" "none"))))
- "znver1-double,znver1-fp0*4")
+ "znver1-double,znver1-fp0*2")
(define_insn_reservation "znver1_sseimul_load" 10
(and (ior (and (eq_attr "cpu" "znver1")
@@ -1257,28 +1257,28 @@ (define_insn_reservation "znver1_sseimul_load" 10
(eq_attr "mode" "TI,OI")))
(and (eq_attr "type" "sseimul")
(eq_attr "memory" "load")))
- "znver1-direct,znver1-load,znver1-fp0*3")
+ "znver1-direct,znver1-load,znver1-fp0")
(define_insn_reservation "znver1_sseimul_avx256_load" 11
(and (eq_attr "cpu" "znver1,znver2,znver3")
(and (eq_attr "mode" "OI")
(and (eq_attr "type" "sseimul")
(eq_attr "memory" "load"))))
- "znver1-double,znver1-load,znver1-fp0*4")
+ "znver1-double,znver1-load,znver1-fp0*2")
(define_insn_reservation "znver1_sseimul_di" 3
(and (eq_attr "cpu" "znver1,znver2,znver3")
(and (eq_attr "mode" "DI")
(and (eq_attr "memory" "none")
(eq_attr "type" "sseimul"))))
- "znver1-direct,znver1-fp0*3")
+ "znver1-direct,znver1-fp0")
(define_insn_reservation "znver1_sseimul_load_di" 10
(and (eq_attr "cpu" "znver1,znver2,znver3")
(and (eq_attr "mode" "DI")
(and (eq_attr "type" "sseimul")
(eq_attr "memory" "load"))))
- "znver1-direct,znver1-load,znver1-fp0*3")
+ "znver1-direct,znver1-load,znver1-fp0")
;; SSE compares
(define_insn_reservation "znver1_sse_cmp" 1
--
2.37.2
