Apple M1 Microarchitecture Research by Dougall Johnson

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

ORR (vector, 16B)

Test 1: uops

Code:

  orr v0.16b, v0.16b, v1.16b
  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)03080b18191e1f3f4e51inst 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)a0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500000061168725100010001000264680120182037203715723189510001000200020372037111001100000000073216111787100020382038203820382038
100420371500000061168725100010001000264680120182037203715723189510001000200020372037111001100000010373116111787100020382038203820382038
100420371500000061168725100010001000264680120182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
1004203716000024061168725100010001000264680120182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680120182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
1004203715000000263168725100010001000264680120182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680120182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680120182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680120182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
1004203715000012061168725100010001000264680120182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  orr v0.16b, v0.16b, v1.16b
  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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371503036119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820086
1020420086150018919687251010010010000100100005002847680200182003720037184223187451010020010000204200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371503486119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715036119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150246119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150996119687251010010010000100100005002847680200182003720037184223188131010020010000200200002003720037111020110099100100100001000007101161119825100001002003820038200382003820038
10204200371503816119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371503636119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000067101161119791100001002003820038200382003820038
10204200371503366119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

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)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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715023366119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
100242003715006066119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
100242003715002616119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500126119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
1002420037150008919687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038
10024200371500126119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  orr v0.16b, v1.16b, v0.16b
  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)03081e1f3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715003606119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100010007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372013218422318745101002001000020020000200372003721102011009910010010000100000027101161119791100001002003820038200382003820038
102042003715002706119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119856100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500006119687441013112210000100100005002847680020018200862008518424318745101002001000020020000200372003711102011009910010010000100000204007101161119791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715002406119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715002706119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715061561968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000640416221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001802003720037184443187671001020103352020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820085
100242003715018611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  orr v0.16b, v8.16b, v9.16b
  orr v1.16b, v8.16b, v9.16b
  orr v2.16b, v8.16b, v9.16b
  orr v3.16b, v8.16b, v9.16b
  orr v4.16b, v8.16b, v9.16b
  orr v5.16b, v8.16b, v9.16b
  orr v6.16b, v8.16b, v9.16b
  orr v7.16b, v8.16b, v9.16b
  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)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)9fcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150195402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100511031611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064072402001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
8020420038150180402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920103200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100511011611200350800001002003920039200392003920098

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)9fa6accfd0d5d6daddinst fetch restart (de)dfe0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000005142580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005024031601142003580000102011420101200392003920039
80024200381500060392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005024311601142003580000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005024011601142004480000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005024011601142003580000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005024011601142003580000102003920039200392003920039
800242003815000005142580010108000010800005064000012001920038201419996310018800102080000201600002003820038118002110910108000010005024311601142003580000102003920039200392003920039
80024200381500060392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005024021601142003580000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005024011602242003580000102003920039200392003920039
8002420038150002250392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005024611601142003580000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010005024311601142003580000102003920039200392003920039