Apple M1 Microarchitecture Research by Dougall Johnson

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

CMEQ (zero, 8H)

Test 1: uops

Code:

  cmeq v0.8h, v0.8h, #0
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116211786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020852038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116121786100020382038203820382038
100420371515611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmeq v0.8h, v0.8h, #0
  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)030e1e3f4e51inst 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)9fa6cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715010611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
1020420037150018611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
10204200371500363611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521200182003720037184212318745101002001000020010000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
1020420134150003461968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
1020420037150024611968625101001001000010010000500284752120018200372003718421318745101002001000020010174200372003711102011009910010010000100071011611197910100001002003820038200382003820038
10204200371500243611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
1020420037150001061968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100071011611197910100001002003820038200382003820038
10204200371500468611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100071011611197910100001002008520086200852003820038
102042003715000611967545101381001001212610152500284752120018200372003718421818764102712001000020010000200372003711102011009910010010000100071011611197912100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)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)9fa7a8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000399006405163319786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
100242003715000000631196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475212001820037200371844331876710010201000020100002008420037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000061196862510010101000010101505028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmeq v0.8h, v8.8h, #0
  cmeq v1.8h, v8.8h, #0
  cmeq v2.8h, v8.8h, #0
  cmeq v3.8h, v8.8h, #0
  cmeq v4.8h, v8.8h, #0
  cmeq v5.8h, v8.8h, #0
  cmeq v6.8h, v8.8h, #0
  cmeq v7.8h, v8.8h, #0
  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)03070a1e3f51inst 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)9fa1a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151182161120035800001002003920039200392003920039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815011629258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815011067258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304080a0b18191e1f3a3f51inst 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)9fa0a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000005020221611620035080000102003920039200392003920039
8002420038150000000360039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000050201116111020035080000102003920039200392010020039
80024200381500000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000005020111671120035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000502010169920035080000102003920039200392003920039
800252003815000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000050208167520035080000102003920039200392003920039
800242003815000000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000050207168620035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000502061610720035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000502061610720035080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000030502051651120035080000102003920039200392003920039
800242003815000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000050208168820035080000102003920039200392003920039