Icestorm: DUP (general, 4H) measurements

Code:

  dup v0.4h, w0

Initialization

  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 2.000

Issues: 2.000

Integer unit issues: 0.001

Load/store unit issues: 1.000

SIMD/FP unit issues: 1.000

Recorded non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	schedule ldst uop (55)	dispatch simd uop (57)	dispatch ldst uop (58)	simd uops in schedulers (5a)	ldst uops in schedulers (5b)	dispatch uop (78)	map ldst uop (7d)	map simd uop (7e)	map ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)
2004	640	2001	1	1000	1000	1000	1000	3000	8000	2000	1000	1000	1000	1000	1	1000	1000
2004	538	2001	1	1000	1000	1000	1000	3000	8000	2000	1000	1000	1000	1000	1	1000	1000
2004	542	2001	1	1000	1000	1000	1000	3000	8000	2000	1000	1000	1000	1000	1	1000	1000
2004	542	2001	1	1000	1000	1000	1000	3000	8000	2000	1000	1000	1000	1000	1	1000	1000
2004	542	2001	1	1000	1000	1000	1000	3000	8000	2000	1000	1000	1000	1000	1	1000	1000
2004	543	2001	1	1000	1000	1000	1000	3000	8000	2000	1000	1000	1000	1000	1	1000	1000
2004	542	2001	1	1000	1000	1000	1000	3000	8000	2000	1000	1000	1000	1000	1	1000	1000
2004	543	2001	1	1000	1000	1000	1000	3000	8000	2000	1000	1000	1000	1000	1	1000	1000
2004	542	2001	1	1000	1000	1000	1000	3000	8000	2000	1000	1000	1000	1000	1	1000	1000
2004	542	2001	1	1000	1000	1000	1000	3000	8000	2000	1000	1000	1000	1000	1	1000	1000

Test 2: Latency 1->2 roundtrip

Code:

  dup v0.4h, w0
  fmov x0, d0

Initialization

  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 9.0030

Recorded non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	schedule ldst uop (55)	dispatch int uop (56)	dispatch simd uop (57)	dispatch ldst uop (58)	int uops in schedulers (59)	simd uops in schedulers (5a)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map ldst uop (7d)	map simd uop (7e)	map int uop inputs (7f)	map ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
30204	90030	40101	10101	20000	10000	100	20000	10018	300	1376525	2318813	30147	200	10021	20040	200	10002	20004	10001	10000	10000	10100
30204	90030	40101	10101	20000	10000	100	20000	10017	300	1377617	2320529	30146	200	10021	20039	200	10002	20002	10001	10000	10000	10100
30204	90030	40101	10101	20000	10000	100	20000	10000	300	1376360	2318512	30100	200	10002	20002	200	10002	20002	10001	10000	10000	10100
30204	90030	40101	10101	20000	10000	100	20000	10000	300	1376328	2318460	30100	200	10002	20002	200	10002	20002	10001	10000	10000	10100
30204	90030	40101	10101	20000	10000	100	20000	10000	300	1376328	2318460	30100	200	10002	20002	200	10002	20002	10001	10000	10000	10100
30204	90033	40101	10101	20000	10000	100	20000	10019	300	1376650	2318995	30148	200	10021	20042	200	10002	20002	10001	10000	10000	10100
30204	90030	40101	10101	20000	10000	100	20000	10000	300	1376328	2318460	30100	200	10002	20002	200	10002	20002	10001	10000	10000	10100
30204	90030	40101	10101	20000	10000	100	20000	10000	300	1376328	2318460	30100	200	10002	20002	200	10002	20002	10001	10000	10000	10100
30204	90030	40101	10101	20000	10000	100	20000	10000	300	1376328	2318460	30100	200	10002	20002	200	10002	20002	10001	10000	10000	10100
30204	90045	40101	10101	20000	10000	100	20000	10000	300	1376345	2318486	30100	200	10002	20002	200	10002	20002	10001	10000	10000	10100

1000 unrolls and 10 iterations

Result (median cycles for code): 9.0030

Recorded non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	schedule ldst uop (55)	dispatch int uop (56)	dispatch simd uop (57)	dispatch ldst uop (58)	int uops in schedulers (59)	simd uops in schedulers (5a)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map ldst uop (7d)	map simd uop (7e)	map int uop inputs (7f)	map ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
30025	90071	40018	10013	20003	10002	10	20029	10001	30	1376379	2318538	30011	20	10002	20004	20	10000	20000	10001	10000	10000	10010
30024	90030	40011	10011	20000	10000	10	20000	10000	30	1376328	2318460	30010	20	10000	20000	20	10000	20000	10001	10000	10000	10010
30025	90063	40018	10013	20003	10002	10	20029	10000	30	1376328	2318460	30010	20	10000	20000	20	10000	20000	10001	10000	10000	10010
30024	90032	40011	10011	20000	10000	10	20000	10017	30	1376536	2318813	30056	20	10021	20039	1533	11199	20113	10679	10596	10003	10940
30024	90033	40011	10011	20000	10000	10	20000	10000	30	1376328	2318460	30010	20	10000	20000	20	10000	20000	10001	10000	10000	10010
30024	90030	40011	10011	20000	10000	10	20000	10000	30	1376328	2318460	30010	20	10000	20000	20	10000	20000	10001	10000	10000	10010
30024	90030	40011	10011	20000	10000	10	20000	10000	30	1376328	2318460	30010	20	10000	20000	20	10000	20000	10001	10000	10000	10010
30024	90033	40011	10011	20000	10000	10	20000	10000	30	1376328	2318460	30010	20	10000	20000	20	10000	20000	10001	10000	10000	10010
30024	90030	40011	10011	20000	10000	10	20000	10000	30	1376328	2318460	30010	20	10000	20000	20	10000	20000	10001	10000	10000	10010
30025	90063	40018	10013	20003	10002	10	20029	10000	30	1376322	2318460	30010	20	10002	20002	20	10000	20000	10001	10000	10000	10010

Test 3: throughput

Count: 8

Code:

  dup v0.4h, w8
  dup v1.4h, w8
  dup v2.4h, w8
  dup v3.4h, w8
  dup v4.4h, w8
  dup v5.4h, w8
  dup v6.4h, w8
  dup v7.4h, w8

Initialization

  mov x8, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.5011

Recorded non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	schedule ldst uop (55)	dispatch int uop (56)	dispatch simd uop (57)	dispatch ldst uop (58)	int uops in schedulers (59)	simd uops in schedulers (5a)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map ldst uop (7d)	map simd uop (7e)	map int uop inputs (7f)	map ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
160204	40150	160115	101	80006	80008	100	80012	80012	300	259427	664596	160124	200	80012	80012	200	80012	80012	1	80000	80000	100
160204	40090	160115	101	80006	80008	100	80012	80012	300	240036	640080	160124	200	80012	80012	200	80012	80012	1	80000	80000	100
160204	40090	160115	101	80006	80008	100	80012	80012	300	240036	640080	160124	200	80012	80012	200	80012	80012	1	80000	80000	100
160204	40090	160115	101	80006	80008	100	80012	80012	300	240036	640080	160124	200	80012	80012	200	80012	80012	1	80000	80000	100
160204	40090	160115	101	80006	80008	100	80012	80012	300	240036	640080	160124	200	80012	80012	200	80012	80012	1	80000	80000	100
160204	40090	160115	101	80006	80008	100	80012	80012	300	240036	640080	160124	200	80012	80012	200	80012	80012	1	80000	80000	100
160204	40090	160115	101	80006	80008	100	80012	80012	300	240036	640080	160124	200	80012	80012	200	80012	80012	1	80000	80000	100
160204	40090	160115	101	80006	80008	100	80012	80012	300	240036	640080	160124	200	80012	80012	200	80012	80012	1	80000	80000	100
160204	40090	160115	101	80006	80008	100	80012	80012	300	240036	640080	160124	200	80012	80012	200	80012	80012	1	80000	80000	100
160204	40090	160115	101	80006	80008	100	80012	80012	300	240036	640080	160124	200	80012	80012	200	80012	80012	1	80000	80000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5006

Recorded non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	schedule ldst uop (55)	dispatch int uop (56)	dispatch simd uop (57)	dispatch ldst uop (58)	int uops in schedulers (59)	simd uops in schedulers (5a)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map ldst uop (7d)	map simd uop (7e)	map int uop inputs (7f)	map ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
160024	40434	160027	11	80007	80009	10	80013	80012	30	240036	640080	160034	20	80012	80012	20	80012	80012	1	80000	80000	10
160024	40063	160011	11	80000	80000	10	80000	80000	30	240000	640000	160010	20	80000	80000	20	80000	80000	1	80000	80000	10
160024	40045	160011	11	80000	80000	10	80000	80966	36186	347709	758973	162902	2533	81137	80060	20	80000	80000	1	80000	80000	10
160025	40103	160087	11	80037	80039	10	80055	80042	30	306028	711019	160094	20	80042	80042	20	80055	80055	1	80000	80000	10
160025	40153	160082	11	80033	80038	10	80055	80055	30	314685	722789	160120	20	80055	80055	20	80000	80000	1	80000	80000	10
160024	40047	160011	11	80000	80000	10	80000	80000	30	240000	640000	160010	20	80000	80000	20	80000	80000	1	80000	80000	10
160024	40045	160011	11	80000	80000	10	80000	80000	30	240000	640000	160010	20	80000	80000	20	80000	80000	1	80000	80000	10
160024	40081	160011	11	80000	80000	10	80000	80000	30	240000	640000	160010	20	80000	80000	20	80000	80000	1	80000	80000	10
160024	40088	160011	11	80000	80000	10	80000	80168	30	283794	685366	160346	20	80168	80168	20	80000	80000	1	80000	80000	10
160024	40074	160011	11	80000	80000	10	80000	80000	30	344574	780241	160010	20	80000	80000	20	80000	80000	1	80000	80000	10

DUP (general, 4H)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->2 roundtrip

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations