Icestorm: SHRN2 (8H) measurements

Code:

  shrn2 v0.16b, v1.8h, #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:

  shrn2 v0.16b, v1.8h, #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 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	20012	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 ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
10025	30066	10027	21	10006	20	10031	70	768905	10020	20	10006	20	0	20000	11	0	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	0	20000	11	0	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	0	20000	11	0	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	0	20000	11	0	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	0	20000	11	0	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	0	20000	11	0	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	0	20000	11	0	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	0	20000	11	0	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	0	20000	11	0	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	0	20000	11	0	10000	10

Test 3: Latency 1->2

Code:

  shrn2 v0.16b, v0.8h, #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)	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)
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	0	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	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	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

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  shrn2 v0.16b, v8.8h, #3
  movi v1.16b, 0
  shrn2 v1.16b, v8.8h, #3
  movi v2.16b, 0
  shrn2 v2.16b, v8.8h, #3
  movi v3.16b, 0
  shrn2 v3.16b, v8.8h, #3
  movi v4.16b, 0
  shrn2 v4.16b, v8.8h, #3
  movi v5.16b, 0
  shrn2 v5.16b, v8.8h, #3
  movi v6.16b, 0
  shrn2 v6.16b, v8.8h, #3
  movi v7.16b, 0
  shrn2 v7.16b, v8.8h, #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 ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
160204	40488	80110	101	80009	100	80013	300	320052	80112	200	80012	200	0	160024	1	0	160000	100
160204	40110	80110	101	80009	100	80013	300	320052	80112	200	80012	200	0	160024	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	160024	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	160024	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	160024	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	160024	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	160024	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	160024	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	160024	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	160024	1	0	160000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5054

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)
160024	43898	80031	21	80010	20	80014	70	320060	80034	20	80014	20	160000	11	160000	10
160024	41327	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	160000	10
160024	40388	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	160000	10
160024	40390	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	160000	10
160024	40428	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	160000	10
160024	40436	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	160000	10
160024	40425	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	160000	10
160024	40425	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	160000	10
160024	41570	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	160000	10
160024	40426	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	160000	10

Test 5: throughput

Count: 16

Code:

  shrn2 v0.16b, v16.8h, #3
  shrn2 v1.16b, v16.8h, #3
  shrn2 v2.16b, v16.8h, #3
  shrn2 v3.16b, v16.8h, #3
  shrn2 v4.16b, v16.8h, #3
  shrn2 v5.16b, v16.8h, #3
  shrn2 v6.16b, v16.8h, #3
  shrn2 v7.16b, v16.8h, #3
  shrn2 v8.16b, v16.8h, #3
  shrn2 v9.16b, v16.8h, #3
  shrn2 v10.16b, v16.8h, #3
  shrn2 v11.16b, v16.8h, #3
  shrn2 v12.16b, v16.8h, #3
  shrn2 v13.16b, v16.8h, #3
  shrn2 v14.16b, v16.8h, #3
  shrn2 v15.16b, v16.8h, #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)	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)
160204	80077	160107	101	160006	100	160010	300	640036	160108	200	160012	200	0	320028	1	0	160000	100
160204	80035	160107	101	160006	100	160010	300	640036	160108	200	160012	200	0	320024	1	0	160000	100
160204	80035	160107	101	160006	100	160010	300	640036	160108	200	160012	200	0	320024	1	0	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	0	320024	1	0	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	0	320024	1	0	160000	100
160204	80035	160105	101	160004	100	160008	300	640216	160156	200	160064	200	0	320024	1	0	160000	100
160204	80035	160107	101	160006	100	160010	300	640036	160108	200	160012	200	0	320024	1	0	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	0	320024	1	0	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	0	320024	1	0	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	0	320024	1	0	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	80218	160052	11	160041	10	160053	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	320128	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

SHRN2 (8H)

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