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, 2S)

Test 1: uops

Code:

  fminnm 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371536116872510001000100026468012018203720371572318951000100020002037203711100110000073216111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037151296116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037151566116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720841572318951000100020002037203711100110000195073116111787100020382038203820382038
100420371636116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fminnm 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)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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371503361196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371504261196872510100100100001001000050028476801200180200372003718422318745101002041000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150661196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371501561196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500536196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715021961196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371503361196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100207101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150082196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007341161119791100001002003820038200382003820038

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)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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000001502511968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000450611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785110000102003820038200382003820038
100242003715000003780611968725100101010000101000050284768012001820037200371844481878610010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000001202511968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768012001820037200371844431876710160201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000240611968725100101010000101000050284768012001820037200371845331876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fminnm 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)0308181e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000570611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000210611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000150611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187511010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187451010020010000200203342003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012002220037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)9fa6accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715051611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820085200382008620038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200852003820038
100242003715005361968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715021611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010036402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fminnm v0.2s, v8.2s, v9.2s
  fminnm v1.2s, v8.2s, v9.2s
  fminnm v2.2s, v8.2s, v9.2s
  fminnm v3.2s, v8.2s, v9.2s
  fminnm v4.2s, v8.2s, v9.2s
  fminnm v5.2s, v8.2s, v9.2s
  fminnm v6.2s, v8.2s, v9.2s
  fminnm 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)030b191e1f3f51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500018040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051102161120035800001002003920039200392003920039
80204200381500033040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500036040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100300185151101161120035800001002003920039200392009220039
8020420038150000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000082258010010080000100800005006400002001920038200389973399968040220080000200160000200382003811802011009910010080000100000051291161120035800001002003920039200392003920039
80204200381500124040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e1f3f51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471510000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050205165520035080000102003920039200392003920039
80024200381500000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050204163420035080000102003920039200392003920039
80024200381500000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050204164420035080000102003920039200392003920039
8002420038150000435039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050204163420035080000102003920039200392003920039
80024200381500000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050203163420035080000102003920039200392003920039
8002420038150000399039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050204163220035080000102003920039200392003920039
80024200381500000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050204164420035080000102003920039200392003920039
80024200381500000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050204164320035080000102003920039200392003920039
80024200381500000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050203163420035080000102003920039200392003920039
80024200381500000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050204164320035080000102003920039200392003920039