Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGT (zero, 8H)

Test 1: uops

Code:

  cmgt v0.8h, v0.8h, #0
  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)a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037160611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037153611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371502511686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037150821686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmgt v0.8h, v0.8h, #0
  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)9fa1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010002010071011611197910100001002003820038200382003820038
1020420037150010351968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000010071011611197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000010071011611197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000010371011611197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000371011611197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000371011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421718764102772001000020010166200372003711102011009910010010000100000123732433111979128100001002003820038200382003820038
10204200371500611968625101001001000011510152538284878502001820037200371842181876310100200100002001000020037200371110201100991001001000010043004071021611197910100001002003820038200382003820038
10204200371506611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000010371011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000440071021611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308191e3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000006405162219786010000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000066402162219786010000102003820038200382003820038
100242003715000361196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001002006402162219786010000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmgt v0.8h, v8.8h, #0
  cmgt v1.8h, v8.8h, #0
  cmgt v2.8h, v8.8h, #0
  cmgt v3.8h, v8.8h, #0
  cmgt v4.8h, v8.8h, #0
  cmgt v5.8h, v8.8h, #0
  cmgt v6.8h, v8.8h, #0
  cmgt v7.8h, v8.8h, #0
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03080b183f51inst 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)9fa0a6a8a9acc5branch mispredict (cb)cdcfd6inst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100001041321115118160200353800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118160200350800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003821802011009910010080000100000001115118160200350800001002003920039200392003920039
8020420038150100292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100002001115118160200350800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118160200350800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118160200350800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100003001115118160200350800001002003920039200392003920039
80204200381500005992580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118160200350800001002003920039200392003920102
8020420038150000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118160200350800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100000001115118160200350800001002003920039200392003920039

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)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
800242005015102562258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005024191617182003580000102003920039200392003920039
800242003815002290258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005024171615172003580000102003920039200392003920039
800242003815002274258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005024141610162008480000102003920039200392003920039
800242003815002125258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005024171616142003580000102003920039200392003920039
800242003815002106258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005024131617142003580000102003920039200392003920039
800242003815002490258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005024151615162003580000102003920039200392003920039
8002420038150021376258001010800001080000506400001200192003820087999631001880010208000020800002003820038118002110910108000010005024171617152003580000102003920039200392003920039
80024200381500211825800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000502417168172003580000102003920039200392003920039
80024200381500211925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000502481613162003580000102003920039200392003920039
80024200381500210025800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000502481616172003580000102003920039200392003920039