Apple M1 Microarchitecture Research by Dougall Johnson

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

SMAX (vector, 4H)

Test 1: uops

Code:

  smax v0.4h, v0.4h, v1.4h
  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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
10042037153661168725100010001000264680020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
10042037150164168725100010001000264680020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
10042037153961168725100010001000264680020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
10042037153061168725100010001000264680020182037203715723189510001000200020372037111001100073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100073116111787100020382038203820382038
1004203715061168725100010001000264680120192037203715723192110001000200020372037111001100073116111787100020382038203820382038
1004203716061168725100010001000264680120182037203715723189510001000200020372037111001100073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  smax v0.4h, v0.4h, v1.4h
  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)030b18191e3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420084150000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071012511197910100001002003820038200382003820038
1020420037165000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100001671011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680120018200372003718422031874510100200100002002000020083200371110201100991001001000010000012971011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000371011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000018971011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000371011611197910100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000371011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000080306402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000010006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000010006402162219785010000102003820038200382003820038
1002420037149000000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000012006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000010006402162219785010000102003820038200382003820038
10024200371500000000251196872510010101000010100005028476802001820037200371844403187671001020100002020000200372008411100211091010100001000040306402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000020006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000906402162219785010000102008620038200862008420038
1002420037150000000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000796506402162219785010000102003820038200382003820038
100242003715000000001471968725100101010000101000050284768020018200372003718448071876710010201000020200002003720037111002110910101000010000440306402162219785010000102003820038200852003820038

Test 3: Latency 1->3

Code:

  smax v0.4h, v1.4h, v0.4h
  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)03191e3f4e51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500010319687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500012619687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500010319687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100010007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100400007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500014919687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100020007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500014719687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100002007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e3f4e51inst 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
1002420037150000135196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715011061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  smax v0.4h, v8.4h, v9.4h
  smax v1.4h, v8.4h, v9.4h
  smax v2.4h, v8.4h, v9.4h
  smax v3.4h, v8.4h, v9.4h
  smax v4.4h, v8.4h, v9.4h
  smax v5.4h, v8.4h, v9.4h
  smax v6.4h, v8.4h, v9.4h
  smax v7.4h, v8.4h, v9.4h
  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)03080b1e1f3a3b3f51inst 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)9fa0a7a8cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150000000822580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511021611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500000001662580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100001511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500000001052580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b181e1f3f51inst 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)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000005020000211600011112003500080000102003920039200392003920039
800242003815000000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000000502000011160001362003500080000102003920039200392003920039
80024200381500000003925800101080000108000050640000020019200382003899963100188001020800002016078020038200381180021109101080000100000000050200008160001252003500080000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000005020000101600010102003500080000102003920039200392003920039
800242003815000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502000013160001142003500080000102003920039200392003920039
8002420038150000000438258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000000502000061600010102003500080000102003920039200392003920039
80024200381500000903925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000000050200007160005102003500080000102003920039200392003920039
800242003815000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502000012160001272003500080000102003920039200392003920039
8002420038150000000165258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000000502000061600010102003500080000102003920039200392003920039
800242003815000000060258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502000011160007122003500080000102003920039200392003920039