Icestorm: MADD (32-bit) measurements

Code:

  madd w0, w0, w1, w2

Initialization

  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 1.001

Load/store unit issues: 0.000

SIMD/FP unit issues: 0.000

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	? int output thing (e9)	? int retires (ef)
1004	3030	1001	1001	1000	25856	1000	1000	3000	1001	1000
1004	3030	1001	1001	1000	25856	1000	1000	3000	1001	1000
1004	3030	1001	1001	1000	25856	1000	1000	3000	1001	1000
1004	3030	1001	1001	1000	25856	1000	1000	3000	1001	1000
1004	3030	1001	1001	1000	25856	1000	1000	3000	1001	1000
1004	3030	1001	1001	1000	25856	1000	1000	3000	1001	1000
1004	3030	1001	1001	1000	25856	1000	1000	3000	1001	1000
1004	3030	1001	1001	1000	25856	1000	1000	3000	1001	1000
1004	3030	1001	1001	1000	25856	1000	1000	3000	1001	1000
1004	3030	1001	1001	1000	25856	1000	1000	3000	1001	1000

Test 2: Latency 1->2

Code:

  madd w0, w0, w1, w2

Initialization

  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0030

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	? int output thing (e9)	? int retires (ef)
10204	30030	10101	10101	10100	260150	10100	10206	30218	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260259	10114	10228	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0030

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	dispatch ldst uop (58)	int uops in schedulers (59)	simd uops in schedulers (5a)	dispatch uop (78)	map int uop (7c)	map ldst uop (7d)	map int uop inputs (7f)	? int output thing (e9)	? int retires (ef)
10024	30030	10021	10021	10020	0	259907	0	10020	10030	0	30020	10011	10010
10024	30030	10021	10021	10020	0	259916	0	10020	10020	0	30020	10011	10010
10024	30030	10021	10021	10020	0	259916	0	10020	10020	0	30020	10011	10010
10024	30030	10021	10021	10020	0	259898	0	10020	10028	0	30050	10011	10010
10024	30030	10021	10021	10020	661	284840	8066	11686	11491	769	30044	10011	10010
10024	30030	10021	10021	10020	0	259916	0	10020	10028	0	30020	10011	10010
10024	30030	10021	10021	10020	0	259916	0	10020	10020	0	30020	10011	10010
10024	30030	10021	10021	10020	0	259916	0	10020	10020	0	30104	10016	10010
10024	30030	10021	10021	10020	0	259916	0	10020	10020	0	30020	10011	10010
10024	30030	10021	10021	10020	0	259916	0	10020	10020	0	30020	10011	10010

Test 3: Latency 1->3

Code:

  madd w0, w1, w0, w2

Initialization

  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0030

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	? int output thing (e9)	? int retires (ef)
10204	30030	10101	10101	10100	260144	10100	10206	30218	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10205	30060	10106	10106	10114	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260778	10162	10289	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100
10204	30030	10101	10101	10100	260156	10100	10208	30224	10001	10100

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0030

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	? int output thing (e9)	? int retires (ef)
10024	30030	10021	10021	10020	259898	10020	10020	30020	10011	10010
10024	30030	10021	10021	10020	259916	10020	10020	30020	10011	10010
10024	30030	10021	10021	10020	259916	10020	10020	30020	10011	10010
10024	30030	10021	10021	10020	259916	10020	10020	30020	10011	10010
10024	30030	10021	10021	10020	259916	10020	10020	30020	10011	10010
10024	30030	10021	10021	10020	259916	10020	10020	30020	10011	10010
10024	30030	10021	10021	10020	259916	10020	10020	30020	10011	10010
10024	30030	10021	10021	10020	259916	10020	10020	30020	10011	10010
10024	30030	10021	10021	10020	259916	10020	10020	30020	10011	10010
10024	30030	10021	10021	10020	259916	10020	10020	30020	10011	10010

Test 4: Latency 1->4

Code:

  madd w0, w1, w2, w0

Initialization

  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 1.0034

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	? int output thing (e9)	? int retires (ef)
10204	10034	10104	10104	10105	30315	10105	10210	30236	10004	10100
10204	10044	10104	10104	10105	30315	10105	10212	30236	10004	10100
10204	10034	10104	10104	10105	30315	10105	10212	30236	10004	10100
10204	10034	10104	10104	10105	30315	10105	10212	30236	10004	10100
10204	10034	10104	10104	10105	30315	10105	10212	30236	10004	10100
10204	10034	10104	10104	10105	30315	10105	10212	30236	10004	10100
10204	10034	10104	10104	10105	30315	10105	10212	30236	10004	10100
10204	10034	10104	10104	10105	30315	10105	10212	30236	10004	10100
10204	10034	10104	10104	10105	30315	10105	10212	30236	10004	10100
10204	10034	10104	10104	10105	30315	10105	10212	30236	10004	10100

1000 unrolls and 10 iterations

Result (median cycles for code): 1.0032

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	? int output thing (e9)	? int retires (ef)
10024	10035	10025	10025	10026	30078	10026	10034	30020	10011	10010
10024	10032	10021	10021	10020	30060	10020	10020	30020	10011	10010
10024	10032	10021	10021	10020	30060	10020	10020	30020	10011	10010
10024	10032	10021	10021	10020	30060	10020	10020	30020	10011	10010
10024	10032	10021	10021	10020	30060	10020	10020	30020	10011	10010
10024	10032	10021	10021	10020	30060	10020	10020	30020	10011	10010
10024	10032	10021	10021	10020	30060	10020	10020	30020	10011	10010
10024	10032	10021	10021	10020	30060	10020	10020	30020	10011	10010
10024	10032	10021	10021	10020	30060	10020	10020	30020	10011	10010
10024	10032	10021	10021	10020	30060	10020	10020	30020	10011	10010

Test 5: throughput

Count: 8

Code:

  madd w0, w8, w9, w9
  madd w1, w8, w9, w9
  madd w2, w8, w9, w9
  madd w3, w8, w9, w9
  madd w4, w8, w9, w9
  madd w5, w8, w9, w9
  madd w6, w8, w9, w9
  madd w7, w8, w9, w9

Initialization

  mov x8, 9
  mov x9, 10
  mov x10, 11

(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)	dispatch int uop (56)	int uops in schedulers (59)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	map ldst uop inputs (80)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
80204	80054	80104	80104	80105	240315	80105	80212	240236	0	80004	0	0	80100
80204	80044	80104	80104	80105	240315	80105	80212	240236	0	80004	0	0	80100
80204	80034	80104	80104	80105	240315	80105	80212	240236	0	80004	0	0	80100
80204	80034	80104	80104	80105	240315	80105	80212	240236	0	80004	0	0	80100
80204	80034	80104	80104	80105	240315	80105	80212	240236	0	80004	0	0	80100
80204	80034	80104	80104	80105	240315	80105	80212	240236	0	80004	0	0	80100
80204	80034	80104	80104	80105	240315	80105	80212	240308	0	80020	0	0	80100
80204	80034	80104	80104	80105	240315	80105	80212	240236	0	80004	0	0	80100
80204	80034	80104	80104	80105	240315	80105	80212	240236	0	80004	0	0	80100
80204	80034	80104	80104	80105	240315	80105	80212	240236	0	80004	0	0	80100

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 ldst uop (55)	dispatch int uop (56)	int uops in schedulers (59)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	? int output thing (e9)	? int retires (ef)
80024	80046	80025	80025	0	80026	240060	80020	80020	240020	80011	80010
80024	80032	80021	80021	0	80020	240132	80045	80056	240020	80011	80010
80024	80032	80021	80021	0	80020	240060	80020	80020	240020	80011	80010
80025	80067	80041	80041	0	80045	240060	80020	80020	240020	80011	80010
80024	80032	80021	80021	0	80020	240132	80045	80060	240020	80011	80010
80024	80032	80021	80021	0	80020	240060	80020	80020	240020	80011	80010
80024	80032	80021	80021	0	80020	240060	80020	80020	240020	80011	80010
80024	80032	80021	80021	0	80020	240060	80020	80020	240020	80011	80010
80024	80032	80021	80021	0	80020	240060	80020	80020	240020	80011	80010
80024	80032	80021	80021	0	80020	240060	80020	80020	240020	80011	80010

MADD (32-bit)

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: Latency 1->4

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 5: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations