Icestorm: SQSHRUN2 (4S) measurements

Code:

  sqshrun2 v0.8h, v1.4s, #3

Initialization

  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.001

Load/store unit issues: 0.000

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)	dispatch simd uop (57)	ldst uops in schedulers (5b)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000

Test 2: Latency 1->1

Code:

  sqshrun2 v0.8h, v1.4s, #3

Initialization

  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0033

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)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	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)
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10006	200	0	20012	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	20008	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	20008	1	0	10000	100
10205	30066	10107	101	10006	100	10031	300	768905	10100	200	10004	200	0	20008	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	20008	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	20008	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	20008	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	20008	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	20010	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	20012	1	0	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0033

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)	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 simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
10024	30033	10021	21	10000	20	10000	0	70	0	768905	10020	20	0	10006	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	0	70	0	768905	10020	20	0	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	0	70	0	768905	10020	20	0	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	0	70	0	768905	10020	20	0	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	0	70	0	768905	10020	20	0	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	0	70	0	768905	10020	20	0	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	0	70	0	768905	10020	20	0	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	0	70	0	768905	10020	20	0	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	0	70	0	769247	10051	20	0	10044	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	0	70	0	768905	10020	20	0	10000	20	20000	11	10000	10

Test 3: Latency 1->2

Code:

  sqshrun2 v0.8h, v0.4s, #3

Initialization

  movi v0.16b, 1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0033

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)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0033

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)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10004	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	769247	10051	20	10044	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqshrun2 v0.8h, v8.4s, #3
  movi v1.16b, 0
  sqshrun2 v1.8h, v8.4s, #3
  movi v2.16b, 0
  sqshrun2 v2.8h, v8.4s, #3
  movi v3.16b, 0
  sqshrun2 v3.8h, v8.4s, #3
  movi v4.16b, 0
  sqshrun2 v4.8h, v8.4s, #3
  movi v5.16b, 0
  sqshrun2 v5.8h, v8.4s, #3
  movi v6.16b, 0
  sqshrun2 v6.8h, v8.4s, #3
  movi v7.16b, 0
  sqshrun2 v7.8h, v8.4s, #3

Initialization

  movi v8.16b, 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)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
160204	40476	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160026	1	160000	100
160204	40110	80110	101	80009	100	80013	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320056	80113	200	80013	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320204	80150	200	80050	200	160024	1	160000	100
160204	40101	80110	101	80009	100	80013	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320056	80113	200	80013	200	160024	1	160000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5053

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)	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 simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
160024	43854	80019	11	80008	10	80012	0	30	0	320052	80022	20	0	80012	20	160000	1	160000	10
160024	41282	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	160000	1	160000	10
160024	40436	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	160000	1	160000	10
160024	40432	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	160000	1	160000	10
160024	40436	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	160000	1	160000	10
160024	40427	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	160000	1	160000	10
160024	40388	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	160000	1	160000	10
160024	40427	80011	11	80000	10	80000	0	30	0	320200	80059	20	0	80049	20	160000	1	160000	10
160024	40390	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	160000	1	160000	10
160024	40434	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	160000	1	160000	10

Test 5: throughput

Count: 16

Code:

  sqshrun2 v0.8h, v16.4s, #3
  sqshrun2 v1.8h, v16.4s, #3
  sqshrun2 v2.8h, v16.4s, #3
  sqshrun2 v3.8h, v16.4s, #3
  sqshrun2 v4.8h, v16.4s, #3
  sqshrun2 v5.8h, v16.4s, #3
  sqshrun2 v6.8h, v16.4s, #3
  sqshrun2 v7.8h, v16.4s, #3
  sqshrun2 v8.8h, v16.4s, #3
  sqshrun2 v9.8h, v16.4s, #3
  sqshrun2 v10.8h, v16.4s, #3
  sqshrun2 v11.8h, v16.4s, #3
  sqshrun2 v12.8h, v16.4s, #3
  sqshrun2 v13.8h, v16.4s, #3
  sqshrun2 v14.8h, v16.4s, #3
  sqshrun2 v15.8h, v16.4s, #3

Initialization

  movi v16.16b, 17

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.5002

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)	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 simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
160204	80076	160107	101	160006	100	160010	0	300	0	640036	160108	200	0	160012	200	320122	1	160000	100
160204	80054	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	320122	1	160000	100
160204	80035	160107	101	160006	100	160010	0	300	0	640036	160108	200	0	160012	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640208	160154	200	0	160064	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	320024	1	160000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5002

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)	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 simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
160025	80173	160053	11	160042	10	160054	0	30	0	640036	160018	20	0	160012	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	320000	1	160000	10
160024	80048	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	320000	1	160000	10

SQSHRUN2 (4S)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->1

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: Latency 1->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 5: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations