Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGE (scalar, zero, S)

Test 1: uops

Code:

  fcmge s0, s0, #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)03191e3f4e51inst 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)a0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500611686251000100010002645210201820372037157131895100010001000203720371110011000000073216111786100020382038203820382038
100420371600711686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371500611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371500611686251000100010002645210201820372037157131895100010001000203720371110011000000673116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715012611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371500821686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371500611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371500821686251000100010002645211201820372037157131895100010001000203720371110011000001073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmge s0, s0, #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)031e1f3f4e51inst 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
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037149006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)60696b6d6edispatch 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)9fa0a1a6a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000251196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000006406163319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000006403163319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000006403163319786010000102008520038200382003820038
100242003715000000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000006403163319786010000102003820038200382003820038
1002420037150000000233196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000006404163319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000006404163319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000006403163319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200841110021109101010000100000006404163319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000006404163319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200180200372003718443318767100102010000201000020037200371110021109101010000100000006403163319786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmge s0, s8, #0
  fcmge s1, s8, #0
  fcmge s2, s8, #0
  fcmge s3, s8, #0
  fcmge s4, s8, #0
  fcmge s5, s8, #0
  fcmge s6, s8, #0
  fcmge s7, s8, #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)031e3f5051inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715091240258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118416020035800001002003920039200392003920039
802042003815002850258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118416020035800001002003920039200392003920039
80204200381500290258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118116020035800001002003920039200392003920039
80204200381500290258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118316020035800001002003920039200392003920039
80204200381500290258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118316020035800001002003920039200392003920039
80204200381500290258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118316020035800001002003920039200392003920039
80204200381500290258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118316020035800001002003920039200392003920039
802042003815007102580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000121115118116020035800001002003920039200392003920039
80204200381500296258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118316020035800001002003920039200392003920039
80204200381500290258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118216020035800001002003920039200892003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)033a3f51inst 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)9fa8acc2cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115003925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020150416442003580000102003920039200392003920039
800242003815003925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020150216242003580000102003920039200392003920039
800242003815003925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020150316422003580000102003920039200392003920039
800242003815008325800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005040150216252003580000102003920039200392003920039
800242003815003925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020120416242003580000102003920039200392003920039
800242003815003925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020120216342003580000102003920039200392003920039
800242003815016025800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020120416542003580000102003920039200392003920039
800242003815003925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020120216242003580000102003920039200392003920039
800242003815003925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180022109101080000100005020120416432003580000102003920039200392003920039
8002420038150038525800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020120416242003580000102003920039200392003920039