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, 4H)

Test 1: uops

Code:

  umin 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)03081e3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371600156164625100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371500103168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715012061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715015156168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371500129168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  umin 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)0308090b18191e1f3f4e51inst 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
1020420037150000000028219687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003714900000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161219827100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000000037119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
102042003715000000002511968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010031787101161119791100001002003820038200382003820038
102042003714900000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000000012419687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010025847101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030a0b1e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000012419687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006404165619785010000102003820038200382003820038
1002420037150000070319687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006405166519785010000102003820038200382003820038
1002420037150000079019687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006626165619785010000102003820038200382003820038
1002420037150000074819687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006404165619785010000102003820038200382003820038
1002420037150000067019687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006405166519785010000102003820038200382003820038
1002420037150000066919687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006405164619785010000102003820038200382003820038
1002420037150000014719687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006406165619785010000102003820038200382003820038
1002420037150000061196872510010101000010100005528476801200180200372003718444318767100102010000202000020037200371110021109101010000100064061645197854810000102003820038200382003820038
1002420037150000097919687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010006406166519785010000102003820038200382003820038
10024200371500000103196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000102106405166619785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  umin 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)031e3a3f4e51inst 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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500010801968725101001001000010010000500284768020018200372003718422318744101252001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000611968725101251001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150001451968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100009071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100200071011611197910100001002003820038200382003820038
1020420037150011451968725101001001000010010000500284768020018200372003718422318744101252001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150001471968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150001451968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371501801261968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150001031968725101001001000010010000500284768020018200372003718422318744101252001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318744101252001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037149000027300611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000306402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000004061968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000050006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000010800611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  umin v0.4h, v8.4h, v9.4h
  umin v1.4h, v8.4h, v9.4h
  umin v2.4h, v8.4h, v9.4h
  umin v3.4h, v8.4h, v9.4h
  umin v4.4h, v8.4h, v9.4h
  umin v5.4h, v8.4h, v9.4h
  umin v6.4h, v8.4h, v9.4h
  umin 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)03081e1f3f51inst 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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511021611200350800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001001000511011611200350800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500308225801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500006325801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
80204200381500004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 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)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)9fa8accfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020005516532003580000102003920039200392003920039
8002420038150050925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020005416432003580000102003920039200392003920039
800242003815003925800101080000108000050640000112001920038200389996310018800102080000201600002003820038118002110910108000010005020004516362003580000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050200041016442003580000102003920039200392003920039
800242003815003925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020004716972003580000102003920039200392003920039
800242003815003925800101080000108000050640000012001920038200389996310018800102080000201600002003820038218002110910108000010005020004816342003580000102003920039200392003920039
8002420038150012325800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020004416442003580000102003920039200392003920039
800242003815003925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020004416432003580000102003920039200392003920039
800242003815003925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020004516452003580000102003920039200392003920039
800242003815003925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020004416582003580000102003920039200392003920039