Apple M1 Microarchitecture Research by Dougall Johnson

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

FABD (scalar, H)

Test 1: uops

Code:

  fabd h0, h0, h1
  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
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415828951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722010525482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723023225482510001000100039831313018303730372415328951000100020003037303711100110001073116112630100030383038303830383038
1004303722013625482510001000100039831303018303730372415328951000100020003037303711100110003073116112630100030383038303830383038
1004303723366125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  fabd h0, h0, h1
  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)0308090b191e1f3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000061295482510100100100001001000058442773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037302291110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722400000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030084300841110201100991001001000010000007102162229634100001003003830038300383003830038
1020430037225000000252295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229635100001003003830038300383003830038

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)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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000008229548251001010100001010000504277313153001830037300372828732876710010201000020200003003730037111002110910101000010000200064042162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313133001830037300372828732876710010201000020200003003730037111002110910101000010000000064032162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313133001830037300372828732876710010201000020200003003730037111002110910101000010000000064032162229630010000103003830038300383003830038
100243003722500000025129548251001012100001010000504277313133001830037300372828732876710160201000020200003003730037111002110910101000010000200064032162229630010000103003830038300383003830038
100243003722500000072629548251001010100001010000504277313133001830037300372828732876710010201000020200003003730037111002110910101000010000000064032162229630010000103003830038300383003830038
100243003722500000072629548251001010100001010000504277313133001830037300372828732876710010201000020200003003730037111002110910101000010000100064032162229630010000103003830038300383003830038
100243003722500000072629548251001010100001010000504277313133001830037300372828732876710010201000020200003003730037111002110910101000010000000064032162229630010000103003830038300383003830038
100243003722500000072629548251001010100001010000504277313133001830037300372828732876710010201000020200003003730037111002110910101000010000000064032162229630010000103003830038300383003830038
100243003722500000025129548631001010100001010000504277313133001830037300372828732876710010201000020200003003730037111002110910101000010000100064032162229630010000103003830038300383003830038
100243003722500000072629548251001010100001010000504277313133001830037300372828732876710010201000020200003003730037111002110910101000010000000064032162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  fabd h0, h1, h0
  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)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)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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100006071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100100071003011296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830230
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038

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)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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006404162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100002706402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372240000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722400000007262954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830083
100243003722500000001032954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  fabd h0, h8, h9
  fabd h1, h8, h9
  fabd h2, h8, h9
  fabd h3, h8, h9
  fabd h4, h8, h9
  fabd h5, h8, h9
  fabd h6, h8, h9
  fabd h7, h8, h9
  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)030b3f51inst 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)9fa0a1a7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000100511051644200360800001002004020040200402004020040
80204200391550140258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000100511041645200360800001002004020040200402004020040
8020420039150041828010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511051655200860800001002004020040200402004020040
80204200391500212258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000500511041654200360800001002004020040200402004020040
8020420039150041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511041655200368800001002004020040200402004020040
8020420039150041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511051655200360800001002004020040200402004020040
8020420039150041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000130511051655200360800001002004020040200402004020040
8020420039150041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100040100511061654201990800001002004020040200402004020040
8020420039150041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000030511051645200360800001002004020040200402004020040
8020420039150141258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000000511041644200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)033f51inst 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)9fa8accfd5d6d9ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915011925800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000502061605320036080000102004020040200402004020040
800242003915040258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010015502051605320036080000102004020040200402004020040
80024200391504025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000502031603620036080000102004020040200402004020040
80024200391504025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000502031605520036080000102004020040200402004020040
80024200391504025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000502051605420036080000102004020040200402004020040
80024200391504025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000502051605520036080000102004020040200402004020040
80024200391504025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000502051605320036080000102004020040200402004020040
80024200391504625800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000502051605320036080000102004020040200402004020040
80024200391504625800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000502051605320036080000102004020040200402004020040
80024200391504625800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000502031603520036080000102004020040200402004020040