Icestorm: FCMP (scalar, S) measurements

Code:

  fcmp s0, s1

Initialization

  mov x0, 1
  mov x1, 2
  mov x2, 3
  mov x3, 4

(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)
1004	1034	1001	1	1000	1000	4000	1000	1000	2000	1
1004	1034	1001	1	1000	1000	4000	1000	1000	2000	1
1004	1034	1001	1	1000	1000	4000	1000	1000	2000	1
1004	1034	1001	1	1000	1000	4000	1000	1000	2000	1
1004	1034	1001	1	1000	1000	4000	1000	1000	2000	1
1004	1034	1001	1	1000	1000	4000	1000	1000	2000	1
1004	1034	1001	1	1000	1000	4000	1000	1000	2000	1
1004	1034	1001	1	1000	1000	4000	1000	1000	2000	1
1004	1034	1001	1	1000	1000	4000	1000	1000	2000	1
1004	1034	1001	1	1000	1000	4000	1000	1000	2000	1

Test 2: Latency 3->1

Chain cycles: 2

Code:

  fcmp s0, s1
  fcsel d0, d2, d3, eq

Initialization

  mov x0, 1
  mov x1, 2
  mov x2, 3
  mov x3, 4

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code, minus 2 chain cycles): 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)
20204	40033	20101	101	20000	100	20000	300	1019248	20100	200	20006	200	50115	1	10000	100
20204	40033	20101	101	20000	100	20000	300	1019248	20100	200	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	300	1019248	20100	200	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	300	1019248	20100	200	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	300	1019248	20100	200	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	300	1019248	20100	200	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	300	1019248	20100	200	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	300	1019248	20100	200	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	300	1019248	20100	200	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	300	1019248	20100	200	20004	200	50010	1	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code, minus 2 chain cycles): 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)
20025	40066	20019	11	20008	10	20034	30	1019248	20010	20	20004	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	30	1019248	20010	20	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	30	1019248	20010	20	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	30	1019248	20010	20	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	30	1019248	20010	20	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	30	1019248	20010	20	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	30	1019248	20010	20	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	30	1019248	20010	20	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	30	1019248	20010	20	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	30	1019248	20010	20	20000	20	50000	1	10000	10

Test 3: Latency 3->2

Chain cycles: 2

Code:

  fcmp s0, s1
  fcsel d1, d2, d3, eq

Initialization

  mov x0, 1
  mov x1, 2
  mov x2, 3
  mov x3, 4

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code, minus 2 chain cycles): 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)	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)
20204	40033	20101	101	20000	100	20000	0	300	0	1019248	20100	200	0	20004	200	50015	1	10000	100
20204	40033	20101	101	20000	100	20000	0	307	0	1019580	20136	202	0	20046	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	731	32431	14538	1020131	22011	1708	846	20128	202	50123	2	10000	100
20204	40033	20101	101	20000	100	20000	0	300	0	1019248	20100	200	0	20006	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	0	300	0	1019248	20100	200	0	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	0	300	0	1019248	20100	200	0	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	0	300	0	1019248	20100	200	0	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	0	300	0	1019248	20100	200	0	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	0	300	0	1019248	20100	200	0	20004	200	50010	1	10000	100
20204	40033	20101	101	20000	100	20000	0	300	0	1019580	20134	200	0	20044	200	50010	1	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code, minus 2 chain cycles): 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)	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)
20024	40239	20059	11	20048	10	20144	0	30	0	1019248	20010	20	0	20006	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	0	30	0	1019248	20010	20	0	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	0	30	0	1019248	20010	20	0	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	0	30	0	1019248	20010	20	0	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	0	30	0	1019248	20010	20	0	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	0	30	0	1019248	20010	20	0	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	0	30	0	1019248	20010	20	0	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	0	30	0	1019248	20010	20	0	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	0	30	0	1019248	20010	20	0	20000	20	50000	1	10000	10
20024	40033	20011	11	20000	10	20000	0	30	0	1019248	20010	20	0	20000	20	50000	1	10000	10

Test 4: throughput

Count: 8

Code:

  fcmp s0, s1
  fcmp s0, s1
  fcmp s0, s1
  fcmp s0, s1
  fcmp s0, s1
  fcmp s0, s1
  fcmp s0, s1
  fcmp s0, s1

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 1.0004

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)	? int retires (ef)
80204	80048	80101	101	80000	100	80001	0	300	0	320014	80103	200	0	80010	200	160020	1	100
80204	80041	80102	101	80001	100	80003	0	300	0	320005	80101	200	0	80008	200	160016	1	100
80204	80034	80101	101	80000	100	80001	0	300	0	320005	80101	200	0	80008	200	160016	1	100
80204	80034	80101	101	80000	100	80001	0	300	0	320005	80101	200	0	80008	200	160016	1	100
80204	80034	80101	101	80000	100	80001	0	300	0	320005	80101	200	0	80008	200	160016	1	100
80204	80034	80101	101	80000	100	80001	0	300	0	320005	80101	200	0	80008	200	160020	1	100
80204	80041	80102	101	80001	100	80003	0	300	0	320005	80101	200	0	80008	200	160016	1	100
80204	80034	80101	101	80000	100	80001	0	300	0	320005	80101	200	0	80008	200	160016	1	100
80204	80034	80101	101	80000	100	80001	0	300	0	320005	80101	200	0	80008	200	160016	1	100
80205	80068	80118	101	80017	100	80022	0	300	0	320005	80101	200	0	80008	200	160016	1	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0004

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)	? int retires (ef)
80024	80049	80021	21	80000	20	80002	70	320018	80024	20	80010	20	160000	11	10
80024	80034	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	10
80024	80034	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	10
80024	80034	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	10
80024	80034	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160072	11	10
80024	80034	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	10
80024	80034	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	10
80024	80034	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	10
80024	80034	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	10
80024	80034	80021	21	80000	20	80000	70	320000	80020	20	80000	20	160000	11	10

FCMP (scalar, S)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 3->1

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: Latency 3->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations