Apple M1 Microarchitecture Research by Dougall Johnson

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

DUP (element, scalar, B)

Test 1: uops

Code:

  dup b0, v0.b[1]
  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)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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715010516862510001000100026452120182037203715713189510001000100020372037111001100001073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382086203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  dup b0, v0.b[1]
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150082419686251010010010000100100005002847521120018200372003718421031874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382008420038
102042003715036119686251010010010000100100005002847521020018200372003718421031874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421031874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421031874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421031874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421031874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150012419686251010010010000100100005002847521120018200372003718421031874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150010319686251010010010000100100005002847521120018200372003718421031874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421031874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421031874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03091e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150206119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640616221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521200652003720037184433187671001020100002010000200372003711100211091010100001000640216241978610000102003820038200382003820038
100242003715003366119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500966119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500996119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500666119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500053619686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150096119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  dup b0, v8.b[1]
  dup b1, v8.b[1]
  dup b2, v8.b[1]
  dup b3, v8.b[1]
  dup b4, v8.b[1]
  dup b5, v8.b[1]
  dup b6, v8.b[1]
  dup b7, v8.b[1]
  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)031e3a3f51inst 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)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005015000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815090292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
8020420038150150292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080128200382003811802011009910010080000100001115118016120035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039

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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001007305020216222003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000005020416442003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001902003820038999631001880010208000020800002003820038118002210910108000010048005020216322003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000005020416242003580000102003920039200392003920039
8002420038151039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000005020316232003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000305020216222003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000605020416442003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001902003820038999631001880010208000020800002003820038118002110910108000010007205020416232003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000005020216222003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000005020416222003580000102003920039200392003920039