Apple M1 Microarchitecture Research by Dougall Johnson

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

UMIN (vector, 8H)

Test 1: uops

Code:

  umin v0.8h, v0.8h, v1.8h
  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)a0a8c2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203716061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715082168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382083
1004203716061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  umin v0.8h, v0.8h, v1.8h
  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)03181e3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071061622197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021621197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
1020420037150001451968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038

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
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006404165619785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006406165619785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006406165619785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006406166519785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006406166619785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006405165619785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006406165619785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006406166419785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006405165619785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006405165519785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  umin v0.8h, v1.8h, v0.8h
  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)0318191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420084150006661196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715000061196872510100100100121001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715000076196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715001061196872510100100100001001000050028476800200182003720037184220318745102622041000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150000251196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e1f3f4e51inst 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)9facc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500906119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150015906119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010076402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150024306119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150025806119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715005106119687251001010100001010000502847680020018020037200371846031876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  umin v0.8h, v8.8h, v9.8h
  umin v1.8h, v8.8h, v9.8h
  umin v2.8h, v8.8h, v9.8h
  umin v3.8h, v8.8h, v9.8h
  umin v4.8h, v8.8h, v9.8h
  umin v5.8h, v8.8h, v9.8h
  umin v6.8h, v8.8h, v9.8h
  umin v7.8h, v8.8h, v9.8h
  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)030b1e1f3f51inst 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
80204200491500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051103161120035800001002003920039200392003920039
802042003815004504025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815006070525801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815000030625801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001001051101161120035800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161020035800001002003920039200392003920039
802042003815001508225801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815000051525801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03090a0b1e1f3f51inst 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)5f60696d6edispatch 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
8002420047150000003925800101080000108000050640000112001920038200389996310018800102080000201600002003820038118002110910108000010005020316542003580000102003920039200392003920039
800242003815000048032425800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020416342003580000102003920039200392003920039
8002420038150000303925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020516452003580000102003920039200392003920039
8002420038150000003925800101080000108000050640000112001920038200389996310018800102080000201600002003820038118002110910108000010005020316442003580000102003920039200392003920039
80024200381500002103925800101080000108000050640000102001920038200389996310018800102080000201600002003820038118002110910108000010005020416432003580000102003920039200392003920039
800242003815000000186525800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020416442003580000102003920039200392003920039
8002420038150000003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020216552003580000102003920039200392003920039
8002420038150000003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020516532003580000102003920039200392003920039
80024200381500002103925800101080000108000050640000102001920038200389996310018800102080000201600002003820038118002110910108000010005020416442003580000102003920039200392003920039
8002420038150000003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020516432003580000102003920039200392003920039