Apple M1 Microarchitecture Research by Dougall Johnson

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

ZIP1 (vector, 2S)

Test 1: uops

Code:

  zip1 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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037166103168725100010001000264680020182037203715723189510001000200020372037111001100000073316221787100020382038203820382038
1004203716061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203716961168725100010001000264680120182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
10042037161261168725100010001000264680120182037203715723189510001000200020832037111001100000073216221787100020382038203820382038
1004203716061168725100010001000264680120182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203716061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038
1004203716061168725100010001000264680020182037203715723189510001000200020372037211001100000073216221787100020382038203820382038
1004203716061168725100010001000264680020182037203715723189510001000200020372037111001100000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  zip1 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)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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371560000000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000000071021611197910100001002003820038200382003820038
10204200371560000000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001002201120071011611197910100001002003820038200382003820038
102042003715500000006119632159101981281007213910912699285409502019820321202751844402618846110502221097021921996203232008461102011009910010010000100020012118684849365212000625100001002037320327202782032620228
1020420415158117810656160403619599178102251441002413811064757285812502030620418203721843504118889112042231126922622664202762037181102011009910010010000100620120138630871181411989526100001002037320419204202042220410
1020420406158008310566160121819610175102081451008414811064737285666102030620180204221844603618782111962301133421522982203742042181102011009910010010000100020010158354869180222004437100001002041720422204182027720419
1020420227157018810807040403019610176102271441003613611216748285794402030620418204171844804118872113612251132322422362202272041181102011009910010010000100422112158532895372112003627100001002003820038200382003820077
102042003715600000001261968725101001001000010010000692285891502023420037200371842203187451010020010000200200002003720037111020110099100100100001000000003071011611197910100001002003820038200382003820038
10204200371550000000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371550000000891968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371550000000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150024441196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001003640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001040640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182022520037184446187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  zip1 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)030b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715500000027919687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037155000120021119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371550000006119687251010010010000100100005002847680020018200372003718422318745102762001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000054019687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000023119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000043819687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715600000012419687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715600000016619687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002008520038200382003820038
102042003715500000025019687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715500000014719687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e1f3f4e51inst 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)6061696d6edispatch 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)9fa0a1a6a8a9acc2cfd0itlb miss (d4)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371550006119687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000000064000416431978510000102003820038200382003820038
10024200371560006119687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000000064000416441978510000102003820038200382003820038
100242003715500025119687251001010100001010000502847680102001820037200371844431876710010201000020200002003720037111002110910101000010000000064000316321978510000102003820038200382003820038
10024200371650006119687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000000064000316341978510000102003820038200382003820038
100242003715501208919687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000000064000316341978510000102003820038200382003820038
10024200371550008919687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000000064000416441978510000102003820038200382003820038
1002420037155100122719687251001010100001010000502847680002001820037200371844431876710010201000020200002003720037111002110910101000010000000064000416451978510000102003820038200382003820038
10024200371550006119687251001010100001010000502847680002001820037200371844431877810010201000020200002003720037111002110910101000010000000064000416441978510000102003820038200382003820038
10024200371550006119687251001010100001010000502847680102001820037200371844431876710010201000020200002003720037111002110910101000010000003064000416341978510000102003820038200382003820038
10024200371560006119687251001010100001010000502847680102001820037200371844431876710010201000020200002003720037111002110910101000010000000064000316441978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  zip1 v0.2s, v8.2s, v9.2s
  zip1 v1.2s, v8.2s, v9.2s
  zip1 v2.2s, v8.2s, v9.2s
  zip1 v3.2s, v8.2s, v9.2s
  zip1 v4.2s, v8.2s, v9.2s
  zip1 v5.2s, v8.2s, v9.2s
  zip1 v6.2s, v8.2s, v9.2s
  zip1 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)0309181e3a3f51inst 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)9fa0a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715500004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000130511021611200350800001002003920039200392003920039
8020420038156000010525801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815700004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815600004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381550000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100035850511011611200350800001002003920039200392003920039
8020420038155000012825801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
8020420038155000015125801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
8020420038156000047025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815500006825801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000100511011611200350800001002003920039200392003920039
802042003815500008625801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa0a1a6a8acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715506392580010108000010800005064000020099201362014710003710044801102080096201601982010020090218002110910108000010447002503707269520121280000102015920144201462014820097
800242003815501144258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000502006166520035080000102003920039200392003920039
800242003815501150258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000502006166620035080000102003920039200392003920039
8002420038155122731258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000502007165720035080000102003920039200392003920039
800242003815501124258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000502006166620035080000102003920039200392003920039
800242003815501186258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000502005165620035080000102003920039200392003920039
80024200381550181258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000502006166520035080000102003920039200392003920039
800242003815501234258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000502007168720035080000102003920039200392003920039
800242003815601328258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000502008166720035080000102003920039200392003920039
800242003815501150258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000502006166520035080000102003920039200392003920039