Apple M1 Microarchitecture Research by Dougall Johnson

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

UMINV (vector, 16B)

Test 1: uops

Code:

  uminv b0, v0.16b
  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)0318191e1f3f4e51inst 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722000061254725100010001000398160030183037303724143289510001000200030373037111001100000073216112629100030383038303830383038
10043037220000612547251000100010003981601301830373037241432895100010002000303730371110011000036073116112629100030383038303830383038
10043037230000612547251000100010003981601301830373037241432895100010002000303730371110011000003073116112629100030383038303830383038
1004303723000061254725100010001000398160030183037303724143289510001000200030373037111001100000073116112629100030383038303830383038
1004303723000061254725100010001000398160130183037303724143289510001000200030373037111001100000073116112629100030383038303830383038
10043037230012061254725100010001000398160030183037303724143289510001000200030373037111001100000073116112629100030383038303830383038
10043037220012061254725100010001000398160130183037303724143289510001000200030373037111001100000073116112629100030383038303830383038
1004303723000061254725100010001000398160130183037303724143289510001000200030373037111001100001073116112629100030383038303830383038
1004303723000061254725100010001000398160130183037303724143289510001000200030373037111001100000073116112629100030383038303830383038
1004303723000061254725100010001000398160030183037303724143289510001000200030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uminv b0, v0.16b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b1e3f4e51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500726129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
102043003722500034629547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372240006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100171011611296330100001003003830038300383003830038
102043003722500186129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372240006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100071011611296330100001003003830038300383003830038
102043003722500336129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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
10024300372250000180103295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000010006404162329629010000103003830038300383003830038
1002430037225000060061295472510043101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000006404164329629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000006404164429629010000103003830038300383003830038
1002430037224000042061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000006403164329629010000103003830038300383003830038
1002430037225002030103295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000006404164429629010000103003830038300383003830038
1002430037225000018061295472510010101000010100005042771601300183003730037282863288061001020100002020000300373003711100211091010100001000000006403164429629010000103003830038300383003830038
1002430037225000036061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000006404164629629010000103003830038300383023030038
100243003722500002702778295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000006404164329629010000103003830038300383003830038
1002430037225000039061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000006403164329629010000103003830038300383003830038
1002430037225000045061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000006404163429728010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uminv b0, v8.16b
  uminv b1, v8.16b
  uminv b2, v8.16b
  uminv b3, v8.16b
  uminv b4, v8.16b
  uminv b5, v8.16b
  uminv b6, v8.16b
  uminv b7, v8.16b
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03181e1f3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150010803025801081008000810080020500640132020020200392003999770699908012020080032200160064200392003911802011009910010080000100031115118016020036800001002004020040200402004020040
80204200391500007225801081008000810080020500640132120020200392003999770699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040201022004020040
802042003915010883025801081008000810080020500640132120020200392003999770699908012020080032200160276200392003911802011009910010080000100201115118016020036800001002004020040200402004020040
802042003915002407225801081008000810080020500640132120020200392003999770699908012020080032200160064200392003911802011009910010080000100701115118016020036800001002004020040200402004020040
802042003915007203025801081008000810080020500640132120020200392003999770699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
802042003915003903025801081008000810080020500640132120020200392003999770699908012020080032200160064200392003911802011009910010080000100531115118016020036800001002004020040200402004020040
802042003915000013625801081008000810080020500640132120020200392003999770699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132120020200392003999770699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132120020200392003999770699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132020020200392003999770699908012020080032200160064200392003911802011009910010080000100001115118016020036800001002004020040200402004020040

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)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)9fa8a9accfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500402580010108000010800005064000012002002003920039999631001980010208000020160000200392003911800211091010800001000050203160222003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002002003920039999631001980010208000020160000200392003911800211091010800001000350202160222003680000102004020040200402004020040
80024200391500402580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000050202160432003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002002003920039999631001980010208000020160000200392003911800211091010800001000050203160442003680000102004020040200402004020040
800242003915004025800101080000108000050640000120020020039200399996310019800102080000201600002003920039118002110910108000010100050203160222003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002002003920039999631001980010208000020160000200392003911800211091010800001000050203160442003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002002003920039999631001980010208000020160000200392003911800211091010800001012050202160332003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002002003920039999631001980010208000020160000200392003911800211091010800001000050203160222003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002002003920039999631001980010208000020160000200392003911800211091010800001000050202160222003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000100011750202160222003680000102004020040200402004020040