Icestorm: UZP2 (vector, 4H) measurements

Code:

  uzp2 v0.4h, v0.4h, v1.4h

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	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000

Test 2: Latency 1->2

Code:

  uzp2 v0.4h, v0.4h, v1.4h

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0033

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	20033	10101	101	10000	100	10000	300	509248	10100	200	10006	200	20012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0033

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)	schedule ldst uop (55)	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	20033	10021	21	10000	0	20	10000	70	509247	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	0	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	0	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	0	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	0	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	0	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	0	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	0	20	10000	70	509248	10020	20	10000	20	20094	11	10000	10
10024	20033	10021	21	10000	0	20	10000	70	509247	10020	20	10006	20	20000	11	10000	10
10024	20033	10021	21	10000	0	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10

Test 3: Latency 1->3

Code:

  uzp2 v0.4h, v1.4h, v0.4h

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0033

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	20033	10101	101	10000	100	10000	300	509248	10100	200	10006	200	20012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	307	509580	10136	202	10050	200	20096	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0033

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	20033	10021	21	10000	20	10000	70	509247	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10025	20066	10029	21	10008	20	10034	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20084	10033	21	10012	20	10036	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10

Test 4: throughput

Count: 8

Code:

  uzp2 v0.4h, v8.4h, v9.4h
  uzp2 v1.4h, v8.4h, v9.4h
  uzp2 v2.4h, v8.4h, v9.4h
  uzp2 v3.4h, v8.4h, v9.4h
  uzp2 v4.4h, v8.4h, v9.4h
  uzp2 v5.4h, v8.4h, v9.4h
  uzp2 v6.4h, v8.4h, v9.4h
  uzp2 v7.4h, v8.4h, v9.4h

Initialization

  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.5004

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)
80204	40080	80105	101	80004	100	80008	300	320044	80110	200	80014	200	160028	1	80000	100
80204	40044	80107	101	80006	100	80010	300	320044	80110	200	80013	200	160024	1	80000	100
80204	40034	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40034	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40034	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40034	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40034	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40034	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40034	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40034	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5004

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)
80024	40220	80029	21	80008	20	80012	68	320200	80072	20	80062	20	160036	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10

UZP2 (vector, 4H)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: Latency 1->3

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations