Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHL (immediate, vector, 8H)

Test 1: uops

Code:

  sqshl 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)031e3f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073416441786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073416441786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073416441786100020382038203820382038
10042037160611686251000100010002645210202220372037157131895100010001000203720371110011000073416441786100020382038203820382038
100420371539611686251000100010002645211201820372037157131895100010001000203720371110011000073416441786100020382038203820382038
1004203716126611686251000100010002645211201820372084157131895100010001000203720371110011000073416441786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073416441786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073416431786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000073416441786100020382038203820382038
10042037160611686251000100010002645211201820372037157131895100010001000203720371110011000073416441786100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl 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)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)9fa1a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150082196862510100100100001001000050028475211200180200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200180200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001802003720037184213187451010020010000200100002003720037111020110099100100100001000000127101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200180200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200180200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018020037200371842131874510100200100002001000020037200371110201100991001001000010000100547101161119791100001002003820038200382003820038
1020420037150961196862510100100100001001000050028475211200180200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200180200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001802003720037184213187451010020010000200100002003720037111020110099100100100001000000697101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200180200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

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)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)9fa6a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119686251001012100001010000602847521020018200372003718443111876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
100242003715027611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371500611968625100241010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371506611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
100242003715001051968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371506611968625100101210000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sqshl v0.8h, v8.8h, #3
  sqshl v1.8h, v8.8h, #3
  sqshl v2.8h, v8.8h, #3
  sqshl v3.8h, v8.8h, #3
  sqshl v4.8h, v8.8h, #3
  sqshl v5.8h, v8.8h, #3
  sqshl v6.8h, v8.8h, #3
  sqshl 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)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)9fa8acc5branch mispredict (cb)cdcfd6e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150081625801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816200350800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100024111511816200350800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816200350800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816200350800001002009020039200392003920039
802042003815002925801081008000810080020500640132020019200382003899772699898012020080032200800322003820038118020110099100100800001000159111511816200350800001002003920039200392003920039
802042003815002950801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100027111511816200350800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100015111511816200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500000000061258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000000502031644200350080000102003920039200392003920039
80024200381500000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000000502041644200350080000102003920039200392003920039
800242003815000000180039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000000502041633200350080000102003920039200392003920039
80024200381500000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000000502051633200350080000102003920039200392003920039
80024200381500000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000000502031654200350080000102003920039200392003920039
80024200381500000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000000502051655200350080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000018600502051625200350080000102003920039200392003920039
80024200381500000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000000502041624200350080000102003920039200392003920039
800242003815000000150060258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000000502041644200350080000102003920039200392003920039
800242003815000000000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100000002700502051643200350080000102003920039200392003920039