Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGT (vector, 2S)

Test 1: uops

Code:

  fcmgt 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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371615611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037160611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371504901687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037159611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmgt 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)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)9fa8c5branch mispredict (cb)cdcfd6e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150018319687251010010010000100100005002847680120018200372003718429618740101002001000820020016200372003711102011009910010010000100011171816198020100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718429718740101002001000820020016200372003711102011009910010010000100011171716198010100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182008420133184291218757101002041017920020016200372003711102011009910010010000100011171716198010100001002003820038200862013320086
102042008515006119687251010010010000100100005002847680120018200372003718429718741101002001000820020016200372003711102011009910010010000100011171816198010100001002003820038200382003820038
1020420037150010319687251010010010000100100005002847680120018200372003718429718741101002001000820020016200372003711102011009910010010000100111171716198010100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718429618741101002001000820020016200372003711102011009910010010000100011171816198020100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718429718741101002001000820020016200372003711102011009910010010000100011171716198010100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718429618741101002001000820020016200372003711102011009910010010000100211171716198010100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718429618741101002001000820020016200372003711102011009910010010000100011171716198020100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718429618740101002001000820020016200372003711102011009910010010000100011171716198010100001002003820038200382003820038

1000 unrolls and 10 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)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)9facc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150016819687251001010100001010000502847680200182003720037184443187671016220100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820083
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640216231978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000640516221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fcmgt 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)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)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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
1020420037150000000010619687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
1020420037150000000018919687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
1020420037150000000010319687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000010000071011611197910100001002003820038200382003820038
10204200371500000132006119676251010010010000105101525262847680120054200372003718422318745102612001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
10204200371500000698806119687251012410010012100100005002847680020018200372003718426318745102762001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000010300071011611197910100001002003820038200382003820038
10204200371500000120061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001002030140040071011621197910100001002008520038200382003820087

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e3a3f4e51inst 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)9fa7a8a9acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
100242003715000010319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200852003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038
100242003715000010319687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006403163319785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fcmgt v0.2s, v8.2s, v9.2s
  fcmgt v1.2s, v8.2s, v9.2s
  fcmgt v2.2s, v8.2s, v9.2s
  fcmgt v3.2s, v8.2s, v9.2s
  fcmgt v4.2s, v8.2s, v9.2s
  fcmgt v5.2s, v8.2s, v9.2s
  fcmgt v6.2s, v8.2s, v9.2s
  fcmgt 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)03080b193f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382024011802011009910010080000100000511031611200350800001002003920039200392003920039
80204200381500001870258010010080000100800005006400002001920038200389973399968010020080000200160000201892003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920196
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000012511011611200350800001002003920039200392003920039
802042003815000040518010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920192
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)9fa8a9acc2cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150011239258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000502000416242003580000102003920039200392003920039
800242003815000039258001010800001080000506400001020019200382003899963100188001020800002016000020038200381180021109101080000100000502000216242003580000102003920039200392003920039
800242003815000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000502000416422003580000102003920039200392003920039
800242003815000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000502000416422003580000102003920039200392003920039
800242003815000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000502000216442003580000102003920039200392003920039
800242003815000081258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000502000216242003580000102003920039200392003920039
800242003815000039258001010800001080000506400001020019200382003899963100188001020800002016000020038200381180021109101080000100000502000216342003580000102003920039200392003920039
800242003815000062258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000502000416442003580000102003920039200392003920039
800242003815000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000502000416422003580000102003920039200392003920039
800242003815000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000502000416442003580000102003920039200392003920039