Apple M1 Microarchitecture Research by Dougall Johnson

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

UABDL (vector, 2D)

Test 1: uops

Code:

  uabdl v0.2d, v0.2s, v1.2s
  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)03091e3f4e51inst 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)a0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000005773116112630100030383038303830383038
100430372200612548251000100010003983131301830373037241532895100010002000303730371110011000200073116112630100030383038303830383038
100430372303612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383085
100430372300612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372200612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uabdl v0.2d, v0.2s, v1.2s
  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)030b18191e1f3f4e51inst 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
1020430037225000306129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100028637102162229634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030809181e3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500096129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500006129548251001910100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100028856402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100066402162229630010000103003830038300383003830038
100243003722400006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uabdl v0.2d, v1.2s, v0.2s
  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)033f4e51inst 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)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)9fa0a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722516829548251010010010000100100005004277313300183003730037282650328745101002001000020020000300373003711102011009910010010000100207102161129634100001003003830038300383003830038
10204300372258429548251010010010000100100005004277313300183003730037282650328745101002001000020020000300373003711102011009910010010000100017101161129634100001003003830038300383003830038
102043003722453429548251010010010000100100005004277313300183003730037282650328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722512629548251010010010000100100005004277313300183003730037282650328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372256129548251010010010000100100005004277313300183003730037282650328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722516829548251010010010000100100005004277313300183003730037282650328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722512429548251010010010000100100005004277313300183003730037282650328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722549829548251010010010000100100005004277313300183003730037282650328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722518729548251010010010000100100005004277313300183003730037282657328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722519129548251010010010000100100005004277313300183003730037282650328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

1000 unrolls and 10 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225252612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010200640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300822828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612953025100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uabdl v0.2d, v8.2s, v9.2s
  uabdl v1.2d, v8.2s, v9.2s
  uabdl v2.2d, v8.2s, v9.2s
  uabdl v3.2d, v8.2s, v9.2s
  uabdl v4.2d, v8.2s, v9.2s
  uabdl v5.2d, v8.2s, v9.2s
  uabdl v6.2d, v8.2s, v9.2s
  uabdl v7.2d, v8.2s, v9.2s
  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)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)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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500612580100100800001008000050064000012002020039200399973739997801002008000020016000020039200391180201100991001008000010000000051103162220036800001002004020040200402004020040
80204200391500412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000000051102162220036800001002004020040200402004020040
80204200391500412580100100800001008000050064000002002020039200399973039997801002008000020216000020039200391180201100991001008000010000000051102162220036800001002004020040200402004020040
802042003915007062580100100800001008000050064000012002020039200399973039997801002008000020016000020039200391180201100991001008000010000000051102162220036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973039997801002008000020016000020039200391180201100991001008000010000000051102162220036800001002004020040200402004020040
802042003915001042580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000000051102162320036800001002004020040200402004020040
802042003915001042580100100800001008000050064000012002020039200399973039997801002008000020016000020039200391180201100991001008000010000000051102162220036800001002004020040200402004020040
80204200391500412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000000051102162220036800001002004020040200402004020040
80204200391500412580100100800001008000050064000002002020039200399973039997801002008000020016000020039200391180201100991001008000010000000051102162220036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973039997801002008000020016000020039200391180201100991001008000010000003051102162220036800001002004020040200402004020040

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)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)9fa8acbranch mispredict (cb)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420049150402580010108000010800005064081602002020039200399996310019800102080000201600002003920039118002110910108000010100502000041600043200360080000102004020040200402004020040
8002420039150402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502000041600044200360080000102004020040200402004020040
8002420039150402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502000041600044200360080000102004020040200402004020040
8002420039150402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502000041600044200360080000102004020040200402004020040
8002420039150402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502000041600043200360080000102004020040200402004020040
8002420039150402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502000031600044200360080000102004020040200402004020040
8002420039150402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000502000041600044200360080000102004020040200402004020040
800242003915019822580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502000031600043200360080000102004020040200402004020040
8002420039150402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502000031600044200360080000102004020040200402004020040
8002420039150402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502000041600034200360080000102004020040200402004020040