Apple M1 Microarchitecture Research by Dougall Johnson

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

SMIN (vector, 2S)

Test 1: uops

Code:

  smin 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)03080b18191e1f3a3f4e51inst 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)a0a1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
10042037150000300611687251000100010002646800201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
10042037150000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
10042037150000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
10042037150000000611687251000100010002646800201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
10042037150000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
10042037150000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
10042037160000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
10042037150000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038
10042037150000000611687251000100010002646801201820372037157231895100010002000203720371110011000000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  smin 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)03181e1f3f4e51inst 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
102042003715003006119676251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102161119791100001002003820038200382003820038
10204200371490006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500008219687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715002106119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500306119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500606119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715004208419687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715001206119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150045010319687251012510010000100100005002847680020018200372003718422318745101002041000020020000200372003711102011009910010010000100007101161119791100001002008620038200382003820038
10204200371501906119687251010010010000100100005002848963020018200372003718422318745101002001000020020000200372003711102011009910010010000100037101161119791100001002003820038200382003820089

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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
1002420037150435611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
1002420037150246611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
1002420037150396611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
100242003715012611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
100242003714912611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  smin 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)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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715069611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007102251119791100001002003820038200382003820038
1020420037150276611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119823100001002003820038200382003820038
102042003715036611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006404163319785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006403163419785010000102003820038200862003820038
100242003714900000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006404164419785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768002002020037200371844431876710010201000020200002003720037111002110910101000010000006404164419785010000102003820038200382003820038
100242003714900000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006403164419785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402163419785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006404163419785010000102003820038200842003820038
100242003715000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006403163419785010000102003820038200382003820038
1002420037150000330611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006404164419785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006404163419785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  smin v0.2s, v8.2s, v9.2s
  smin v1.2s, v8.2s, v9.2s
  smin v2.2s, v8.2s, v9.2s
  smin v3.2s, v8.2s, v9.2s
  smin v4.2s, v8.2s, v9.2s
  smin v5.2s, v8.2s, v9.2s
  smin v6.2s, v8.2s, v9.2s
  smin 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)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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150138402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001001051102161120035800001002003920039200392003920039
80204200381500452580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815060402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000020019200882014899913999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150391472580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039

1000 unrolls and 10 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)9faccfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100502001216642003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100502009169102003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100502005165102003580000102003920039200392003920039
8002420038150393925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100502009165132003580000102003920039200392003920039
800242010015063925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100502005165132003580000102003920039200392003920039
800242003815021392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010050200416482003580000102003920039200392003920039
800242003815003925800101080000108000050640000020023200382003899963100188001020800002016000020038200381180021109101080000100502004161352003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100502008161352003580000102003920039200392003920039
8002420038150423925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100502004165132003580000102003920039200392003920039
8002420038150303925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100502001316752003580000102003920039200392003920039