Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

UMAXP (vector, 16B)

Test 1: uops

Code:

  umaxp v0.16b, v0.16b, v1.16b
  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: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073216111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000373116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000973116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110001573116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110002173116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000373116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002062000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150001911968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000607101161119859100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000821968725101001001000010010000500284768002001820037200371842231874510100200100002142000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500038371968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010030007101161119791100001002003820038200382003820038
1020420037150003131968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000156061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000019486402162219785010000102003820038200382003820038
1002420037150000021061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003714900000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000243061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003714900000061196872510010101000010100005028476800200182003720037184443187671016420100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000072061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000536196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371503168196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371503361196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715038161196872510100100100001001000050028476802001820037200371842231874510256200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715049261196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371502161196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715001206119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500606119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500606119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500396119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680200182003720037184443188021001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
10024200371500396119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  umaxp v0.16b, v8.16b, v9.16b
  umaxp v1.16b, v8.16b, v9.16b
  umaxp v2.16b, v8.16b, v9.16b
  umaxp v3.16b, v8.16b, v9.16b
  umaxp v4.16b, v8.16b, v9.16b
  umaxp v5.16b, v8.16b, v9.16b
  umaxp v6.16b, v8.16b, v9.16b
  umaxp v7.16b, v8.16b, v9.16b
  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): 0.2505

retire (01)cycle (02)031e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8c2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601503340258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
802042003815044740258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815001153258010010080000100800006146400001200192008820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815012402580100100800001008000050064000012001920038200389973025999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150340258010010080000100800005006400001200192003820038997303999680505200800002001600002003820038118020110099100100800001000051271161120035800001002003920039200392003920039
8020420038150640258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381501540258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381502140258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150640258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)031e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391502103925800101080000108000050640000120097200382003899960310018800102080000201600002003820038118002110910108000010005020216222003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899960310018800102080000201600002003820038118002110910108000010005020216222003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899960310018800102080000201600002003820038118002110910108000010005020216222003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999603100188001020800002016000020038200382180021109101080000100125020216232003580000102003920039200392003920039
8002420038150303925800101080000108000050640000120019200382003899960310018800102080000201600002003820038118002110910108000010105020216222003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899960310018800102080000201600002003820038118002110910108000010005020216232003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899960310018800102080000201600002003820038118002110910108000010005020216222003580000102003920039200392003920039
8002420038150303925800101080000108000050640000120019200382003899960310018800102080000201600002003820038118002110910108000010005020216222003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899960310018800102080000201600002003820038118002110910108000010005020216222003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899960310018800102080000201600002003820038118002110910108000010005020216222003580000102003920039200392003920039