Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAX (scalar, H)

Test 1: uops

Code:

  fmax h0, h0, h1
  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)696d6edispatch 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
10042037160821687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100002773216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmax h0, h0, h1
  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)030809181e3f4e51inst 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)9fa1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000010719687251010010010000100100005002847680200182003720037184296187411010020010008200200162003720037111020110099100100100001000001117170160219791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100021560007101161119791100001002003820038200382003820038
102042003715010006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000200007101161119791100001002003820038200382003820038
10204200371500000147196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010004200007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161219791100001002003820038200382003820038
102042003715000008219687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000180007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216241978510000102003820038200382003820038
1002420037150611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216231978510000102003820038200382003820038
1002420037150611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216231978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000105200640216221978510000102003820086200852003820038
1002420037150611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216231978510000102003820038200382003820038
1002420037150611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720084111002110910101000010000640216221978510000102003820038200382003820038
10024200371501031968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216231978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000101830640216231978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmax h0, h1, h0
  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)03181e3f4e51inst 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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000233196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820086200862003820038
102042003715000810196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000252196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000097101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000145196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030e1e1f3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715020082196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000672196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000147196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000082196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037211002110910101000010000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000504196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010410640216221978510000102003820038200382003820038
1002420037150000126196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmax h0, h8, h9
  fmax h1, h8, h9
  fmax h2, h8, h9
  fmax h3, h8, h9
  fmax h4, h8, h9
  fmax h5, h8, h9
  fmax h6, h8, h9
  fmax h7, h8, h9
  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)03181e1f3f51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591510002672580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511061611200350800001002003920039200392003920039
8020420038151000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150115132402580100100800001008000050064000012001920038200389982399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500007812580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100100511011611200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100030511011611200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150000822580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
80204200381500002302580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039

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)5f60696d6edispatch 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)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010050200916161420035080000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100502001716141720035080000102003920039200392003920039
8002420038150039258001010800001080000506400001120019200382003899963100188001020800002016000020038200381180021109101080000100502001516181720035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100502001716171720035080000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100502001716171720035080000102003920039200392011420039
800242003815020439258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100502001716171720035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100502001816171020035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100502001716141720035080000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010050200131681720035080000102003920039200392003920039
8002420038150039258001010800001080000506400000120175200382003899963100188001020800002016000020038200381180021109101080000100502001716171420035080000102003920039200392003920039