Apple M1 Microarchitecture Research by Dougall Johnson

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

SSHR (vector, 4H)

Test 1: uops

Code:

  sshr v0.4h, v0.4h, #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)0304080b18191e1f3a3f4e51inst 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)a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037160000000282168625100010001000264521201820372037157131895100010001000203720371110011000000077416441786100020382038203820382038
10042037151000000282168625100010001000264521201820372037157131895100010001000203720371110011000000077416441786100020382038203820382038
10042037151000000282168625100010001000264521201820372037157131895100010001000203720371110011000000077416451786100020382038203820382038
10042037151000000282168625100010001000264521201820372037157131895100010001000203720371110011000000077416441786100020382038203820382038
10042037151000000282168625100010001000264521201820372037157131895100010001000203720371110011000009077416441786100020382038203820382038
10042037151000000282168625100010001000264521201820372037157131895100010001000203720371110011000006077416441786100020382038203820382038
10042037151000000282168625100010001000264521201820372037157131895100010001000203720371110011000009077416441786100020382038203820382038
10042037151000000282168625100010001000264521201820372037157131895100010001000203720371110011000000077416441786100020382038203820382038
100420371510000002299168625100010001000264521201820372037157131895100010001000203720371110011000006077416441786100020382038203820382038
1004203715100000028216862510001000100026452120182037203715713189510001000100020372037111001100000135077416441786100020382038203820382038

Test 2: Latency 1->2

Code:

  sshr v0.4h, v0.4h, #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)03080b191e3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000002101968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010002207101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000841968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161019791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000001031968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3a3f4e51inst 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
100242003715000128196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216281978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216241978610000102003820038200382003820038
10024200371500084196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216271978610000102003820038200382003820038
100242003715000191196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216261978610000102003820038200382003820038
100242003715000166196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216251978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216261978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216231978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001029640216261978610000102003820038200382003820038
10024200371500084196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000661433261978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216261978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sshr v0.4h, v8.4h, #3
  sshr v1.4h, v8.4h, #3
  sshr v2.4h, v8.4h, #3
  sshr v3.4h, v8.4h, #3
  sshr v4.4h, v8.4h, #3
  sshr v5.4h, v8.4h, #3
  sshr v6.4h, v8.4h, #3
  sshr v7.4h, v8.4h, #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)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)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)9fa0a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015011279425801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151182161120035800001002003920039200392003920039
80204200381501102925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181161120035800001002003920039200392003920039
802042003815011025325801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181161120035800001002003920039200392003920039
80204200381501103325801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181161120035800001002003920039200392003920039
80204200381501102925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181161120035800001002003920039200392003920039
80204200381501102925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181161120035800001002003920039200392003920039
80204200381501165025801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181161120035800001002003920039200392003920039
802042003815011013425801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181161120035800001002003920039200392003920039
80204200381501102925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181161120035800001002003920039200392003920039
80204200381501102925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181161120035800001002003920039200392003920039

1000 unrolls and 10 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)9fa0acc5cfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201161112003580000102003920039200392003920039
8002420038150006542580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201161112003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201162112003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201162112003580000102003920039200392003920039
8002420038150001232580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201162112003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201160112003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201162222003580000102003920039200392003920039
800242003815000602580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201163112003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201163112003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000050201162112003580000102003920039200392003920039