Apple M1 Microarchitecture Research by Dougall Johnson

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

CMHS (register, 8H)

Test 1: uops

Code:

  cmhs 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606616872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203716156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmhs 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)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)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071021611197910100001002003820038200382003820038
10204200371500000000971968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000006071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001003018640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100018640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100379640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010030640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010010640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010010640216221978510000102003820038200382003820038
1002420037150072619687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010310640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmhs 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)03191e3f4e51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100223127101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000107101161119791100001002003820038200382003820038
10204200371500061196542510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000107101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100003907101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000607101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080b18191e1f3f4e51inst 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)6061696b6d6edispatch 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)9fa0a1a6a8a9acc2cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000611968725100101010000101000050284768000200180200372003718444318767100102010000202000020037200371110021109101010000100000000640002162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768000200180200372003718444318767100102010000202000020037200371110021109101010000100000000640002162219785010000102003820038200382003820038
10024200371490000000611968725100101010000101000050284768000200180200372003718444318767100102010000202000020037200371110021109101010000100000000640002162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768015200180200372003718444318767100102010000202000020037200371110021109101010000100000000640552162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768015200180200372003718444318767100102010000202000020037200371110021109101010000100000000640552162219785010000102003820038200382003820038
10024200371490000000611968725100101010000101000050284768015200180200372003718444318767100102010000202000020037200371110021109101010000100001000640552162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768015200180200372003718444318767100102010000202000020037200371110021109101010000100000000640552162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768015200180200372003718444318767100102010000202000020037200371110021109101010000100000000640552162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768015200180200372003718444318767100102010000202000020037200371110021109101010000100000000640552162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768000200180200372003718444318767100102010000202000020037200371110021109101010000100000000640002162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmhs v0.8h, v8.8h, v9.8h
  cmhs v1.8h, v8.8h, v9.8h
  cmhs v2.8h, v8.8h, v9.8h
  cmhs v3.8h, v8.8h, v9.8h
  cmhs v4.8h, v8.8h, v9.8h
  cmhs v5.8h, v8.8h, v9.8h
  cmhs v6.8h, v8.8h, v9.8h
  cmhs 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)03080a0b191e1f3f51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000000040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000051102161120035800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997373999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
8020420038150000000666258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000051451161120035800001002003920039200392003920039
80204200381500000001210258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
80204200381500000001177258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
8020420038150000000126258010010080000100801125006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997303999680100200800002001600002008820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815000000040258010010080000100801955006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815000000040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039

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)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)9fa1accfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150039258001010800001080000506400001020019200382003899963100188001020800002016000020038200381180021109101080000100050200003161120035080000102003920039200392003920039
80024200381504539258001010800001080000506400001520019200382003899963100188001020800002016000020038200381180021109101080000100050200001161120035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002016000020075200381180021109101080000100350200001161120035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200001161120035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200001161120035080000102003920039200392003920039
80024200381500134258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200001161120035080000102003920039200392003920039
800242003815043239258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200001161120035080000102003920039200392003920039
80024200381502739258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200001161120035080000102003920039200392003920039
800242003815001957258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200002161120035080000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100050200001161120035080000102003920039200392003920039