Apple M1 Microarchitecture Research by Dougall Johnson

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

SMINP (vector, 8B)

Test 1: uops

Code:

  sminp v0.8b, v0.8b, v1.8b
  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
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073316221787100020382038203820382038
10042037160611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037160611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  sminp v0.8b, v0.8b, v1.8b
  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)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)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)9fa1cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007102161119791100001002003820038200382003820038
1020420037150018611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715003611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030a0b18191e1f3a3f4e51inst 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)9fa0a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006403162219785010000102003820038200382022920038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200842003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010002803006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476802001820084200841844431876710165201000020200002003720037111002110910101000010005803006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  sminp v0.8b, v1.8b, v0.8b
  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)696b6d6edispatch 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)9fa6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715005361968725101001001000010010000500284768020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007102161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018020037200371842231874510100200100002002000020037200371110201100991001001000010001007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018020037200371842531874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018020037200371842231874510100200100002002000020037200371110201100991001001000010000907101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018320037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e3f4e51inst 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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000066196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000006404162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000000441196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820085200862003820038
10024200371500000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000306402162219785010000102003820038200382003820038
10024200371500000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000000858196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
1002420037150000001225196872510010101000011100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010010006402162219785010000102003820038200382003820038
1002420037150000001647196872510010101000010100005028476802001820037200371844431876710010201000020200002007320037111002110910101000010000026822162219785010000102003820086200382003820038
10024201331510000061196762510010101000010101525028476802001820037200371844431882210010201000020209782003720037111002110910101000010200007052242319823010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  sminp v0.8b, v8.8b, v9.8b
  sminp v1.8b, v8.8b, v9.8b
  sminp v2.8b, v8.8b, v9.8b
  sminp v3.8b, v8.8b, v9.8b
  sminp v4.8b, v8.8b, v9.8b
  sminp v5.8b, v8.8b, v9.8b
  sminp v6.8b, v8.8b, v9.8b
  sminp v7.8b, v8.8b, v9.8b
  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)03191e3f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000105258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010010051107161120035800001002003920039200392003920039
8020420038150012124258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120157800001002003920039200392003920039
80204200381501040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000293258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000128258010010080000100800005006400001200192003820038997389996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001201392003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101160120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3f51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471500000000060258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100000009050201616111120035080000102003920039200392003920039
800242003815000000000345258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100000000050201216101520035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100000000050201216111120035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100000000050201316101220035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100000000050201216121120035080000102003920039200392003920039
800242003815000000000106258001010800001080000506400000200192003820038999603100458001020800002016000020038200381180021109101080000100000000050201316121220035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100000000050201216121220035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100000000050201316121220035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100000000050201216101120035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100000000050201316121320035080000102003920039200392003920039