Apple M1 Microarchitecture Research by Dougall Johnson

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

SHL (vector, 8H)

Test 1: uops

Code:

  shl v0.8h, v0.8h, #3
  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)03080b181e1f3a3f4e51inst 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)a0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000000611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371500019200611686251000100010002645210201820372037157131895100010001000203720371110011000040073116111786100020382038203820382038
1004203716000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
100420371500015300611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  shl v0.8h, v0.8h, #3
  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)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)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)9fa8branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150841968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100307101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000000015719686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000000012419686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000000012419686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006682162219786010000102003820038200382003820038
100242003715000000020819686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  shl v0.8h, v8.8h, #3
  shl v1.8h, v8.8h, #3
  shl v2.8h, v8.8h, #3
  shl v3.8h, v8.8h, #3
  shl v4.8h, v8.8h, #3
  shl v5.8h, v8.8h, #3
  shl v6.8h, v8.8h, #3
  shl v7.8h, v8.8h, #3
  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)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)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)9fa8acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815000922580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013220068200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
80204200381500013062580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815000712580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
802042003815000922580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150005042580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511504239258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020916462003580000102003920039200392003920039
80024200381509253258001010801891080000506400001200192003820038999631001880010208000020801942003820038118002110910108000010005020716462003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010105020616652003580000102003920039200392003920039
80024200381501539258001010800001080000506400001200192003820038999631001880010208000020800002011120038118002110910108000010135020616762003580000102003920039200392003920039
80024200381504839258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020416572003580000102003920039200392003920039
80024200381502139258001010800001080000506400001200192003820038999631001880010208000020800992003820089118002110910108000010335020516662003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020616642003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020616462003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020616752003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020416652003580000102003920039200392003920039