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, 2S)

Test 1: uops

Code:

  umaxp v0.2s, v0.2s, v1.2s
  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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037160611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  umaxp v0.2s, v0.2s, v1.2s
  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)030b1e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003716300611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000371021611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500011951968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000071012511197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001001071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842273187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150001451968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500010541968725101001001000010010000593284896312001820181201341842603187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3a3f4e51inst 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)9fa6a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150016219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000644111611111978510000102003820038200382003820038
10024200371500250619687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000644111612111978510000102003820038200382003820038
1002420037150021271968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000064411161161978510000102003820038200382003820038
1002420037150026219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100001644111611111978510000102003820038200382003820038
1002420037150622261968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000064491611111978510000102003820038200382003820038
1002420037150026219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000644111611111978510000102003820038200382003820038
1002420037150028519687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000644111611111978510000102003820038200382003820038
10024200371500250919687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100030644111611121978510000102003820038200382003820038
10024200371500276519687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100001644111612121978510000102003820038200382003820038
1002420037150021041968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000064461612121978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  umaxp v0.2s, v1.2s, v0.2s
  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)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)9fa8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003714901451968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715004411968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715501101968725101001001000010010000612284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080918191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006403162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200852003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000161196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006403162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  umaxp v0.2s, v8.2s, v9.2s
  umaxp v1.2s, v8.2s, v9.2s
  umaxp v2.2s, v8.2s, v9.2s
  umaxp v3.2s, v8.2s, v9.2s
  umaxp v4.2s, v8.2s, v9.2s
  umaxp v5.2s, v8.2s, v9.2s
  umaxp v6.2s, v8.2s, v9.2s
  umaxp v7.2s, v8.2s, v9.2s
  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)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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051103163220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051102162220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100651102162220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051102162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064076020019200382003899738100228021720080000200160000200382003811802011009910010080000100051102162220035800001002003920039200392003920039
8020420038150040258010010080000123800955006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051102162220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051102162220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051102162220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051102162220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b1e3f51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000039258001010800001080000506400001200192003820038999603100188001020800002016000020038200381180021109101080000100005031616882003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100005035516772003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100005034516752003580000102003920039200392003920039
8002420038165000939258001010800001080000506400001200192003820038999603100188001020800002016000020038200381180021109101080000100005033516552003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100005033816772003580000102003920039200392003920039
8002420038150000062258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100005033516652003580000102003920039200392003920039
80024200381500000138258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100005033516672003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100005031716752003580000102003920039200392003920039
8002420038150000039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100005033716852003580000102003920039200392003920039
8002420038150000083258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100005033616672003580000102003920039200392003920039