Apple M1 Microarchitecture Research by Dougall Johnson

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

RADDHN (8H)

Test 1: uops

Code:

  raddhn v0.8b, 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)033a3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230105254825100010001000398313301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
1004303722061254825100010001000398313301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
1004303723061254825100010001000398313301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
1004303722061254825100010001000398313301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037220103254825100010001000398313301830373037241532895100010002000303730371110011000073125112630100030383038303830383038
1004303723061254825100010001000398313301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
1004303722061254825100010001000398313301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
1004303723061254825100010001000398313301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
1004303723061254825100010001000398313301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037220413254825100010001000398313301830373037241532895100010002000303730371110011000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  raddhn v0.8b, 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): 3.0037

retire (01)cycle (02)03091e1f3f4e51inst 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)9fa0a1a6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000031007102162229634100001003003830038300383003830038
1020430037224008861295482510100100100001001000050042786750300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000204200003003730037111020110099100100100001000000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007102162229634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007402162229634100001003003830038300383003830038
102043003722400061295482510116100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007102162229634100001003003830038300383003830038

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)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
100243003722500000025229548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372240000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
100243003722500000012429548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000606402162229630010000103003830038300383003830038
100243003722400001506129548251001010100001010149504277313300183003730037282873287671001020100002020000300373003711100211091010100001002000006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372240000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162529630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  raddhn v0.8b, 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): 3.0037

retire (01)cycle (02)03080918191e1f3a3f4e51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000090061295488410125129100001001000050042773131300183018230229282653287451010020010000200200003003730037111020110099100100100001000000007102163129634100001003003830038300383008630038
10204300372240000120061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000090061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000001007101161129769100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000001007101161129634100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161429634100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000002007101161129634100001003003830038300383003830038
1020430037225000090161295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000001007101161129634100001003003830038300383018330038
1020430037224000000082295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000003007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430178226111334082643993295392510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000100006403162229630010000103003830038300383003830038
100243003722400000026461295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038
10024300372250000012061295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000100006402162229630010000103003830038300383003830038
100243003722500000001032954825100101010000101000050427731303001803003730037282873287671001020100002020000300373003711100211091010100001000003909006402162329630210000103003830085301313003830038
100243003722500000306061295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000400006402162229630010000103003830038300383003830038
10024300372250000012061295482510010121000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038
10024300372250000012061295482510010101000010100005042773130300180300373003728300328767100102010000202000030037300371110021109101010000100000300006402162229630010000103003830038300383003830038
1002430037225000000082295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100000000006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  raddhn v0.8b, v8.8h, v9.8h
  raddhn v1.8b, v8.8h, v9.8h
  raddhn v2.8b, v8.8h, v9.8h
  raddhn v3.8b, v8.8h, v9.8h
  raddhn v4.8b, v8.8h, v9.8h
  raddhn v5.8b, v8.8h, v9.8h
  raddhn v6.8b, v8.8h, v9.8h
  raddhn v7.8b, 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)0308090b18191e1f3f51inst 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)9fa1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500000024041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000000511021611200360800001002004020040200402004020040
8020420039150000000041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000511011611200360800001002004020040200402004020040
80204200391500000027041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000511011611200360800001002004020040200402004020040
80204200391500000021041258010010080000100800005006400000200202003920039997339997801002008000020016000020039201103180201100991001008000010000000511011611200360800001002004020040200402004020040
8020420039150000000041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000511011611200360800001002004020040200402004020040
80204200391500000021041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000511011611200360800001002004020040200402004020040
802042003915000000180944258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000511011611200360800001002004020040200402004020040
8020420039150000000041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000511011621200360800001002004020040200402004020040
80204200391500000012041258010010080000100800005006400000200202003920039997339997801002008000020016020820039200391180201100991001008000010000000511011611200360800001002004020040200402004020040
80204200391500000015041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0309181e1f3f51inst 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)9fa0a1a7a8accfd0d2d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000204040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000502000916000882003600080000102004020040200402004020040
8002420039150000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000000502000716000652003600080000102004020040200402004020040
8002420039150000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000000502000616000572003600080000102004020356203002034620455
8002420143150003016781748099212807811280838606473580200202003920039999631001980010208000020160000200392003911800211091010800001000000502000516000882003600080000102004020040200402004020040
80024200391500000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020317160006520036020080000102004020090200402004020040
8002420039150000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000010502000516000562003600080000102004020040200402004020040
8002420039150000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000502000516000772003600080000102004020040200402004020040
8002420039150000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000000502000716000652003600080000102004020040200402004020040
8002420039150000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000000502000516000552003600080000102004020040200402008920040
8002420039150000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000000502000516000562003600080000102004020040200402004020040