Apple M1 Microarchitecture Research by Dougall Johnson

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

UQADD (scalar, H)

Test 1: uops

Code:

  uqadd 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)031e1f3f4e51inst 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)a0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372200612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372200612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300822548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
1004303722002412548251000100010003983130301830373037241532895100010002000303730371110011000001073116112630100030383038303830383038
100430372300612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372330612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300822548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqadd 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)031e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000204200003003730037111020110099100100100001000071021611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000206200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250076295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006404166529630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006406166629630010000103003830038300383003830038
100243003722500000103295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000001036404165529630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000001006404165529630010000103008530038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006404165629630010000103003830038300383003830038
10024300372240000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006405164529630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006405165529630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006405166629630010000103003830038300383003830038
10024300372240000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006404165429630010000103003830038300383003830038
100243003722400000251295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006406167529630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqadd 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)9fa6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722507262954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000140007101161129634100001003003830038300383003830038
10204300372250156295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
102043003722502850295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037224061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225082295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200208503003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e3c3f4e51inst 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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
1002430037225000286629548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010647202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722400072629548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
10024300372240006129548251001010100001010000504277313030018300373003728287328767100102010488202000030037300371110021109101010000100000640316342963010000103003830038300383003830038
100243003722500078029548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640316332963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqadd h0, h8, h9
  uqadd h1, h8, h9
  uqadd h2, h8, h9
  uqadd h3, h8, h9
  uqadd h4, h8, h9
  uqadd h5, h8, h9
  uqadd h6, h8, h9
  uqadd 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)03181e3f51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500276412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100051103161120087800001002004020040200402004020040
8020420039150033412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
80204200391500300412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
8020420039150036412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
8020420039150021412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
8020420039150012412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
80204200391500237412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040

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)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)9fa6a8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020516532003680000102004020040200402004020040
800242003915024402580010108000012801055064000012002020039200399996310046800102080107201600002003920039118002110910108000010400005020516532003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020816532003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020516552003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000201600002009020141118002110910108000010000005020516552003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010003005020716532003680000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020516572003680000102004020040200402004020040
80024200391500822580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010010005020316532003680000102004020040200402004020040
80024200391500402580010108000010800006064000012002020039200399996310019800102080000201600002003920039118002110910108000010013205020516532003680000102004020040200402004020040
800242003915039402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020316532003680000102004020040200402004020100