Apple M1 Microarchitecture Research by Dougall Johnson

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

SSHL (vector, D)

Test 1: uops

Code:

  sshl d0, d0, d1
  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
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371502021687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150841687251000100010002646802018203720371572318951000100020002037203711100110000073116111855100020382038203820382038
10042037153611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  sshl d0, d0, d1
  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)030818191e1f3a3f4e51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500006006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000000034619687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000008806119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007351161119791100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080a0b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000030611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001020000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000120611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000120611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000004710611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  sshl d0, d1, d0
  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)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
1020420037150666119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003721102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000441196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200842003721100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150031561196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001044000006402567319945210000102027320273202262022720038

Test 4: throughput

Count: 8

Code:

  sshl d0, d8, d9
  sshl d1, d8, d9
  sshl d2, d8, d9
  sshl d3, d8, d9
  sshl d4, d8, d9
  sshl d5, d8, d9
  sshl d6, d8, d9
  sshl d7, d8, d9
  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)030818191e1f3f51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000130511041623200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000130511021632200350800001002003920039200392003920039
802042023915000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000330511031633200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511031633200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000130511031632200350800001002003920039200392003920039
8020420038150000001352580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000130511031632200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000130511021632200350800001002003920039200392003920039
802042019215000000402580100100800001008011250064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000200511031623200350800001002003920039200392003920039
8020420038150000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000203753700511021623200350800001002003920039200392003920039
802042003816100000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000030511021623200350800001002003920039200392003920039

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)9fa1a8a9accfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010010050207160662003580000102003920039200392003920039
80024200381500602580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050203160462003580000102003920039200392003920039
80024200381510392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050205160552003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100270050205160662003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050206160462003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000017150207160352003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050205160532003580000102003920039200392003920039
80025200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050203160532003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010020050204160552003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100240050205160542003580000102003920039200392003920039