Apple M1 Microarchitecture Research by Dougall Johnson

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

NOT (vector, 16B)

Test 1: uops

Code:

  not v0.16b, v0.16b
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110001073216221786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110001073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000176873216221786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100010002037203711100110001073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  not v0.16b, 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)03191e1f3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500007119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000010819686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715007506119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000002106119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006403162219786010000102003820038200382003820038
1002420037150000009063119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502850049020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820085
1002420037150000002406119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000000023219686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  not v0.16b, v8.16b
  not v1.16b, v8.16b
  not v2.16b, v8.16b
  not v3.16b, v8.16b
  not v4.16b, v8.16b
  not v5.16b, v8.16b
  not v6.16b, v8.16b
  not v7.16b, v8.16b
  movi v8.16b, 9

(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)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)9fc2c5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010001115118116020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010001115118016020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010001115118016020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010001115118016020035800001002003920039200392003920039
80204200381503425725801081008000810080020500640132120022200382003899776998980120200800322008003220038200381180201100991001008000010001115118016020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010001115118016020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010001115118016020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010001115118016020035800001002009120039200392003920039
802042003815002925802041008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010001115118016020035800001002003920039200392003920039
80204200381503002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa6accficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015002402580010108000010800005064000020019200382003899960310018800102080000208000020038200381180021109101080000100050240171614142003580000102003920039200392003920039
8002420038150270240258001010800001080000506400002001920038200389996031001880010208000020800002003820038118002110910108000010005024091619162003580000102003920039200392003920039
80024200381500240258001010800001080000506400002001920038200389996031001880010208000020800002003820038118002110910108000010005024015161582003580000102003920039200392003920039
80024200381502912402580010108000010800005064000020019200382003899960310018800102080000208000020038200381180021109101080000100050240161616122003580000102003920039200392003920039
800242003815002402580010108000010800005064000020019200382003899960310018800102080000208000020038200381180021109101080000100050240161616132003580000102003920039200392003920039
80024200381500240258001010800001080000506400002001920038200389996031001880010208000020800002003820038118002110910108000010005024091613162003580000102003920039200392003920039
800242003815002402580010108000010800005064000020019200382003899960310018800102080000208000020038200381180021109101080000100050242151613172003580000102003920039200392003920039
800242003815002402580010108000010800005064000020019200382003899960310018800102080000208000020038200381180021109101080000100050240161615152003580000102003920039200392003920039
80024200381503962402580010108000010800005064000020019200382003899960310018800102080000208000020038200381180021109101080000100050240141614142003580000102003920039200392003920039
800242003815002402580010108000010800005064000020019200382003899960310018800102080000208000020038200381180021109101080000100050240161613162003580000102003920039200392003920039