Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGE (vector, zero, 4S)

Test 1: uops

Code:

  fcmge v0.4s, v0.4s, #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)0318191e3f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500061168625100010001000264521201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500061168625100010001000264521201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500061168625100010001000264521201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500061168625100010001000264521201820372037157131895100010001000203720371110011000073116111962100020382038203820382038
1004203715003661168625100010001000264521201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500082168625100010001000264521201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500361168625100010001000264521201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371600084168625100010001000264521201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
100420371500061168625100010001000264521201820372037157131895100010001000203720371110011000073116111786100020382038203820382038
1004203715002161168625100010001000264521201820372037157131895100010001000203720371110011000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmge v0.4s, v0.4s, #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)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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500006119686251010010010000100100005002847521200182003720037184286187411010020010008200100082003720037111020110099100100100001000011171701600198010100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500906119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001006000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03070a1e3a3f4e51inst 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)9fc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150110268196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001006441016101019786010000102003820038200382003820038
100242003715011026819686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100644516101019786010000102003820038200382003820038
1002420037150111826819686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100644101610519786010000102003820038200382003820038
1002420037150110268196662510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001006441016101019786010000102003820038200382003820038
10024200371501112268196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001006441016101019786010000102003820038200382003820038
10024200371501102258196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001006441016101019786010000102003820038200382003820038
1002420037150113268196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001006441016111019786010000102003820038200382003820038
100242003715011026819686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100644101651019786010000102003820038200382003820038
1002420037150110268196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001006441016101019786010000102003820038200382003820038
10024200371501121268196862510010101000010101525028475211200182003720037184433187671001020100002010000200372003711100211091010100001006441016101019786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmge v0.4s, v8.4s, #0
  fcmge v1.4s, v8.4s, #0
  fcmge v2.4s, v8.4s, #0
  fcmge v3.4s, v8.4s, #0
  fcmge v4.4s, v8.4s, #0
  fcmge v5.4s, v8.4s, #0
  fcmge v6.4s, v8.4s, #0
  fcmge v7.4s, v8.4s, #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)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)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)9facc5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151181620035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151181620035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003821802011009910010080000100011151181620035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100311151181620035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151361620035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151181620035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100011151181620035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151181620035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151181620035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151181620035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304191e3f51inst 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)9fa6a8acc2cfitlb miss (d4)d5d6dbddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005020019160171720035080000102003920039200392003920039
80024200381500003925800101080000108000050640768200192011220038100133100188001020800002080000200382003811800211091010800001000005021117160141720035080000102003920039200392003920039
80024200381501048392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005021116160171720035080000102003920039200392003920039
80024200381501063925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010001805021114160171420035080000102003920039200392003920039
8002420038150100392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005021117161121720035080000102003920039200392003920039
8002420038150100392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005021117160161820035080000102003920039200392003920039
8002420038150100392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005021114160171420035080000102003920039200392003920039
80024200381501018392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005021117160141720035080000102003920039200392003920039
800242003815010039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100000502111816081720035080000102003920039200392003920039
8002420038150100392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005021117160171720035080000102003920039200392003920039