Apple M1 Microarchitecture Research by Dougall Johnson

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

FMINNM (vector, 4S)

Test 1: uops

Code:

  fminnm v0.4s, v0.4s, v1.4s
  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)0308090b193f4e51inst 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
100420371500006116872510001000100026468012018203720371572318951000100020002037203711100110000073216331787100020382038203820382038
100420371500006116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371501006116872510001000100026468002018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371500006116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371500006116872510001000100026468002018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371500006116872510001000100026468002018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371500006116872510001000100026468002018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371500006116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038
100420371500006116872510001000100026468012018203720371572318951000100020002037203711100110000073316331817100020382038203820382038
100420371610006116872510001000100026468012018203720371572318951000100020002037203711100110000073316331787100020382038203820382038

Test 2: Latency 1->2

Code:

  fminnm v0.4s, v0.4s, v1.4s
  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)03081e1f3f4e51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000061196872510100100100001001000050028489631200182017920037184253187451010020010000200200002003720037211020110099100100100001002232307101161119791100001002003820181200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150000103196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150000103196872510100100100001001000050028476801200182003720037184223187451058020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150000441196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000010007101161119791100001002003820038200382003820038
1020420037150000103196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000010007101161119791100001002003820038200382003820038
1020420037150000103196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715000821968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100036403163319785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100036403163319785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006403163319823010000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100006403163319785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100136403163319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fminnm v0.4s, v1.4s, v0.4s
  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)033a3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000067101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001004810010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715001711968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010002007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308191e3f4e51inst 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)9fa1a8c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715000010319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100122010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715000010319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200372110021109101010000100006402162219785010000102003820038200382003820038
100242003715000010819687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715000043319687251001010100001210000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001210000602847680020018200372003718444318767100122010000202000020037200371110021109101010000100006404164419787010000102003820038200382003820038
100242003715000010319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006602162219785110000102017020038200382003820038

Test 4: throughput

Count: 8

Code:

  fminnm v0.4s, v8.4s, v9.4s
  fminnm v1.4s, v8.4s, v9.4s
  fminnm v2.4s, v8.4s, v9.4s
  fminnm v3.4s, v8.4s, v9.4s
  fminnm v4.4s, v8.4s, v9.4s
  fminnm v5.4s, v8.4s, v9.4s
  fminnm v6.4s, v8.4s, v9.4s
  fminnm v7.4s, v8.4s, v9.4s
  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)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)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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420056150101000002925801081008000810080020500640132120019200382003899776998980120200800322001600642003820038118020110099100100800001000000000111511821611200350800001002003920039200392003920039
8020420038150101000002925801081008000810080020500640132020019200382003899776998980120200800322001600642003820038118020110099100100800001000000000111511811611200350800001002003920039200392003920039
80204200381501010000083725801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
8020420038150000000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
80204200381500000000058925801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
8020420038150000000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
8020420038150000000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
8020420038149000000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
80204200381500000000040258010010080000100800005006400000200192003820038997314999680100200800002001600002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039
8020420038150000000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000000511021622200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b1e1f3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150000060258001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000100050206166620035080000102003920039200392003920039
8002420038150000039508001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000100050204166620035080000102003920039200392003920039
8002420038150000039258001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000100050205165520035080000102003920039200392003920039
8002420038150000080258001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000100050205164420035080000102003920039200392003920039
8002420038150000039258001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000100050207165620035080000102003920039200392003920039
8002420038150000039258001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000100050205165620035080000102003920039200392003920039
8002420038150000039258001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000100050203166720035080000102003920039200392003920039
8002420038150000039258001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000100050204165520035080000102003920039200392003920039
8002420038150000039258001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000100050206165520035080000102003920039200392003920039
8002420038150000039258001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000100050203165420035080000102003920039200392003920039