Apple M1 Microarchitecture Research by Dougall Johnson

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

UMINP (vector, 8H)

Test 1: uops

Code:

  uminp v0.8h, v0.8h, v1.8h
  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
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037160611687251000100010002646801201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
100420371521611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  uminp v0.8h, v0.8h, v1.8h
  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)03090b1e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550018061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500000673196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500000145196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037155000108124196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

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)696d6edispatch 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000000006406163419785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000000006403164319785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000000006403164419785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444031876710010201000020200002013120037111002110910101000010000010606404164419785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000000006404164419785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000000006404164419785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000000006403164419785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000000006404164419785010000102003820038200382003820038
1002420037150000060611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000000006404164419785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000000306404164419785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uminp v0.8h, v1.8h, v0.8h
  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)0318191e1f3a3f4e51inst 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)60696b6d6edispatch 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150006006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500018006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500048006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010007341161119791100001002003820038200382003820086
1020420037150111328806119687251010010010000100100005002847680020018020037200371842231876210433200100002002000020037200371110201100991001001000010007101162119791100001002003820038200382003820038
1020420037150100016119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150000006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037149009006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000279006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500036006119687251010010010000100100005002847680120018020037200371842231874510589200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715002161196872510010101000010100005028476801200182003720037184441218786100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150096119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150066119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500363119687251001010100001010000502847680020018200372003718444318767100102010000202100020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715002166119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037149036419687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uminp v0.8h, v8.8h, v9.8h
  uminp v1.8h, v8.8h, v9.8h
  uminp v2.8h, v8.8h, v9.8h
  uminp v3.8h, v8.8h, v9.8h
  uminp v4.8h, v8.8h, v9.8h
  uminp v5.8h, v8.8h, v9.8h
  uminp v6.8h, v8.8h, v9.8h
  uminp v7.8h, v8.8h, v9.8h
  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)03091e3f51inst 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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815007240258010010080000100800005006400001200192003820038997339996801002008000020016027220038200381180201100991001008000010051102161120035800001002003920039200392003920039
802042003815000281258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820144998239996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039

1000 unrolls and 10 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)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)9fa6a8a9acc5cfd5d6dadbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000502012160014152003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502015160013182003580000102003920039200392003920039
80024200381500392580010108000010801085064000012001920038200381001431001880010208000020160000200382003811800211091010800001000000502013160016122003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502016160014112003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502013160012122003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000502012160012122003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502011160011142003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502015162017142003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000502014160015142003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000502015160016132003580000102003920039200392003920039