Apple M1 Microarchitecture Research by Dougall Johnson

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

FMINP (vector, 4H)

Test 1: uops

Code:

  fminp v0.4h, v0.4h, v1.4h
  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)031e3a3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)6061696d6edispatch 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)a8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150010316872510001000100026468010201820372037157231895100010002000203720371110011000007300116111787100020382038203820382038
1004203716006116872510001000100026468010201820372037157231895100010002000203720371110011000007300116111787100020382038203820382038
1004203715006116872510001000100026468010201820372037157231895100010002000203720371110011000007300116111787100020382038203820382038
1004203715006116872510001000100026468010201820372037157231895100010002000203720371110011000007300116111787100020382038203820382038
1004203716006116872510001000100026468010201820372037157231895100010002000203720371110011000007300116111787100020382038203820382038
1004203715006116872510001000100026468010201820372037157231895100010002000203720371110011000007300116121787100020382038203820382038
1004203715006116872510001000100026468010201820372037157231895100010002000203720371110011000007300116111787100020382038203820382038
1004203715008216872510001000100026468010201820372037157231895100010002000203720371110011000007300116111787100020382038203820382038
1004203715006116872510001000100026468010201820372037157231895100010002000203720371110011000007300116111787100020382038203820382038
1004203715006116872510001000100026468010201820372037157231895100010002000203720371110011000007300116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fminp v0.4h, v0.4h, v1.4h
  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)03080b181e3f4e51inst 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)9fa8a9acc5branch mispredict (cb)cdcfd6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500001261196872510100100100001001000050028476801200180200372003718429718740101002001000820020016200372003711102011009910010010000100170931117171600198010100001002003820038200382003820038
102042003715000006119687251010010710012100100005002847680020018020037200371842971874010100200100082002001620037200371110201100991001001000010000511117171600198020100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680020018020037200371842961874110100200100082002001620037200371110201100991001001000010000571117171600198010100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001802003720037184297187411010020010008200200162003720037111020110099100100100001000001117171600198010100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001802003720037184296187411010020010008200200162003720037111020110099100100100001001001117171600198020100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001802003720037184296187401010020010008200200162003720037111020110099100100100001000001117171600198020100001002003820038200382003820038
10204200371500000611968725101001001000010010000511284768012001802003720037184297187401010020010008200200162003720037111020110099100100100001000001117181600198010100001002003820038200382003820038
102042003715000006211968725101001001000010010000500284768002001802003720037184297187401010020010008200200162003720037111020110099100100100001003031117171600198020100001002008520038200382003820038
10204200371500000611968725101001001000010010000500284768002001802003720037184297187411010020010008200200162003720037111020110099100100100001001061117171600198010100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001802003720037184297187401010020010008200200162003720037111020110099100100100001001061117171600198010100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150127841968725100101010000101000050284768012002020037200371844481876710010201000020200002003720037111002110910101000010718000640416551978510000102003820038200382003820038
10024200371500019119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000101900640616461978510000102003820038200382003820038
10024200371500150124196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001016000640616651978510000102003820038200382003820038
1002420037150096419687251001010100001010000562847680120018200372003718444318767100102010000202000020037200371110021109101010000100340640616551978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000101000640616651978510000102003820038200382003820038
100242003714900536196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001056300640516551978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001011800640616461978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001029000640516651978510000102003820038200382003820038
10024200371500246119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100300640516641978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000101300640516441978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fminp v0.4h, v1.4h, v0.4h
  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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119687251010010010000125100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100207101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150426119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687631010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100167101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100307101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001001807101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119663251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100167101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080b18191e1f3a3f4e51inst 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
10024200371500000000061196872510010101001210100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000010006403163319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000306403163319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000010306403163319785010000102003820038200382008620038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000606403193319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000326403163319785010000102003820038200382003820038
10024200371500000000061196762510063101000010101525028476800200182003720037184443187671001020100002020000200372003711100211091010100001000020306403163319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000906403163319785010000102003820038200382003820038
1002420037150000001200272196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000010306403163319785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000906403163319785010000102003820038200382003820038
100242003715020000000103196872510061101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006403163319785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fminp v0.4h, v8.4h, v9.4h
  fminp v1.4h, v8.4h, v9.4h
  fminp v2.4h, v8.4h, v9.4h
  fminp v3.4h, v8.4h, v9.4h
  fminp v4.4h, v8.4h, v9.4h
  fminp v5.4h, v8.4h, v9.4h
  fminp v6.4h, v8.4h, v9.4h
  fminp v7.4h, v8.4h, v9.4h
  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)030f1e3f51inst 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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000661258010010080000100800005006400002001920038200389973039996801002008000020016000020038200381180201100991001008000010000051104161120035800001002003920039200392003920039
802042003815000822258010010080000100800005006400002001920038200389973039996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000765258010010080000100800005006400002001920038200389973039996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000485258010010080000100800005006400002001920038200389973039996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150001472580100100800001008000050064000020019200382003899730399968010020080000200160000200382003811802011009910010080000100033351101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973039996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000020019200382003899730399968010020080000200160000200382003811802011009910010080000100041051101161120035800001002003920039200392003920039
80204200381500040258010010080095100800005006400002001920038200389973039996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150009362580100100800001008000050064000020019200382003899730399968010020080000200160000200382003811802011009910010080000100039051101161120035800001002003920039200392003920039
802042003815000515258010010080000100800005006400002001920038200389973039996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03090b1e3f51inst 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)9fa6a8a9acc5cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200491500006525800101080000108000050640000120019200382003899893100118001020800002016000020038200381180021109101080000100000050200116112003580000102003920039200392003920039
800242003815000010225800101080000108000050640000120019200382003899893100118001020800002016000020038200381180021109101080000100000050200116112003580000102003920039200392003920039
800242003815000091325800101080000108000050640000120019200382003899893100118001020800002016000020038200381180021109101080000100000050200116112003580000102003920039200392003920039
800242003815000010225800101080000108000050640000020019200382003899893100118001020800002016000020038200381180021109101080000100000050200116112003580000102003920039200392003920039
800242003815000051425800101080000108000050640000020019200382003899893100118001020800002016000020038200381180021109101080000100000050200116112003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899893100118001020800002016000020038200381180021109101080000100000050200116112003580000102003920039200392003920039
80024200381500005125800101080000108000050640000120019200382003899893100118001020800002016000020038200381180021109101080000100100150200116112003580000102003920039200392009220039
80024200381511008125800101080000108000050640000120019200382003899893100118001020800002016000020038200381180021109101080000100000050200134112003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899893100118001020800002016000020038200381180021109101080000100006050200116112003580000102003920039200392003920039
8002420038150000346258001010800001080000506400000200192003820038998931001180010208000020160000200382003811800211091010800001004000050200116112003580000102003920039200392003920039