Apple M1 Microarchitecture Research by Dougall Johnson

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

CMHS (register, 8B)

Test 1: uops

Code:

  cmhs 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371508416872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmhs 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)033f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100207101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200182003720037184220318765101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820132200382003820038
102042003715061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100207101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010001027101161119791100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000907101161119791100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000397101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007101171119825100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308191e1f3f4e51inst 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)9fa6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
100242003715010001031968725100101010000101000050284768012001820083200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
100242003715000004411968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010040000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844471876710010201000020200002003720037211002110910101000010000000640216221978510000102003820038200382003820038
10024200371500000611968744100221010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010002196800640216221982410000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmhs 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)030818191e1f3f4e51inst 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)9fa1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000000251196872510100100100001001000050028489630200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150000204061196872510100100100001001000050028476801200182003720037184223187451028020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150000291061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000371011611197910100001002003820038200382003820038
1020420037150000678061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150000249061196872510100100100001001000050028476800200182003720037184223187451010020010000200203322003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000030071011611197910100001002003820038200382003820038
10204200371500000061196652510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000371011611197910100001002003820038200382003820038

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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000039611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000015611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010030640216221978510000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010002640216221978510000102003820038200382003820038
100242003715000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820083
1002420037150000015611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000012611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000000861968725100101010000101000050284768002001820037200371844431878810010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037211002110910101000010000640216221978510000102007420038200382003820086
100242003715000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmhs v0.8b, v8.8b, v9.8b
  cmhs v1.8b, v8.8b, v9.8b
  cmhs v2.8b, v8.8b, v9.8b
  cmhs v3.8b, v8.8b, v9.8b
  cmhs v4.8b, v8.8b, v9.8b
  cmhs v5.8b, v8.8b, v9.8b
  cmhs v6.8b, v8.8b, v9.8b
  cmhs 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)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
80204200381500040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000051103163220044800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815001540258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
802042003815002140258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200190200882003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000051352162220035800001002003920039200392003920039
80204200381500040528010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500040528010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200190200382003899733999680100200800002001600002003820038118020110099100100800001000051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307181e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150000392580010108000010800005064000020019200382003899960310018800102080000201600002003820038118002110910108000010005020416242003580000102003920039200392003920039
80024200381500015392580010108000010800005064000020019200382003899960310018800102080000201600002003820038118002110910108000010005020216422003580000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899960310046800102080000201600002003820038118002110910108000010005020416442003580000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899960310018800102080000201600002003820038118002110910108000010005020216242003580000102003920039200392003920039
80024200381500004192580010108000010800005064000020019200382003899960310018800102080000201600002003820038118002110910108000010005020416422003580000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899960310018800102080000201600002003820038118002110910108000010005020416422003580000102003920039200392003920039
8002420038149000392580010108000010800005064000020019200382003899960310018800102080000201600002003820038118002110910108000010005020416422003580000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382009799960310018800102080000201600002003820038118002110910108000010005020416242003580000102003920039200392003920039
8002420038150000392580010108000010800005064000020019200382003899960310018800102080000201600002003820038118002110910108000010005020416422003580000102003920039200392003920039
80024200381500018442580010108000010800005064000020019200382003899960310018800102080000201600002003820038118002110910108000010005020216422003580000102003920039200392003920039