GPU: smaller thread groups for the merger track fit and the tracking data on Metal

A tuning of the Metal column of GPUParameters.csv only, which changes
nothing for the other backends. On an M1 Max with a 30-collision Pb-Pb
time frame, GPU time per event:

  GPUTPCGMMergerTrackFit       256: 158.5 ms  128 x 2: 141.6  64 x 4: 120.9  32 x 8: 120.3
  GPUTPCCreateTrackingData     256:  44.0 ms  128:      27.3  64:      17.9  32:      19.8

and the whole event 1.331 s before, 1.278 s with [64, 4] and 64 (--runs
10, 3 interleaved rounds, spread under 15 ms). Smaller groups did not
help GPUTPCTrackletConstructor (219 ms at 256, 218 at 128, 223 at 64,
slower at 192, 512 and 1024), GPUTPCGMMergerSectorRefit (131),
GPUTPCExtrapolationTracking (67 to 64) or GPUTPCGMMergerFollowLoopers
(34 to 36), which keep the defaults.

Author: ktf

GPU/GPUTracking/Definitions/Parameters/GPUParameters.csv

@@ -5,7 +5,7 @@ WARP_SIZE,0,,64,64,32,32,32,32,32,32,32,32,32,32,32,64,32,64,32
 THREAD_COUNT_DEFAULT,256,,256,256,,,,,,512,512,,512,256,512,512,512,,256
 ,,,,,,,,,,,,,,,,,,,
 LB:,,,,,,,,,,,,,,,,,,,
-GPUTPCCreateTrackingData,256,,"[256, 7]","[192, 2]",,,,,,"[224, 7]",256,"[128, 14]",416,,"[64, 21]",,384,"[320, 2]",
+GPUTPCCreateTrackingData,256,,"[256, 7]","[192, 2]",,,,,,"[224, 7]",256,"[128, 14]",416,,"[64, 21]",,384,"[320, 2]",64
 GPUTPCTrackletConstructor,256,,"[768, 8]","[512, 10]","[256, 2]","[256, 1]","[256, 2]","[1024, 2]","[512, 4]",1024,"[256, 2]",1024,"[1024, 1]",,"[768, 2]",,768,512,
 GPUTPCTrackletSelector,256,,"[384, 5]","[192, 10]","[256, 3]","[256, 1]","[256, 3]","[512, 4]","[256, 3]","[288, 3]","[192, 3]","[544, 1]","[32, 2]",,"[384, 3]",,992,"[256, 6]",
 GPUTPCNeighboursFinder,256,,"[192, 8]","[960, 8]",256,256,256,512,256,864,"[640, 1]","[512, 2]","[736, 1]",,"[480, 3]",,992,"[704, 1]",
@@ -27,7 +27,7 @@ GPUTPCCFDecodeZSLink,"""GPUCA_WARP_SIZE""",,"""GPUCA_WARP_SIZE""","""GPUCA_WARP_
 GPUTPCCFDecodeZSDenseLink,"""GPUCA_WARP_SIZE""",,"[""GPUCA_WARP_SIZE"", 4]","[""GPUCA_WARP_SIZE"", 14]",,,,,,"[""GPUCA_WARP_SIZE"", 14]","""GPUCA_WARP_SIZE""","[""GPUCA_WARP_SIZE"", 22]","[""GPUCA_WARP_SIZE"", 22]",,"[""GPUCA_WARP_SIZE"", 17]",,"[""GPUCA_WARP_SIZE"", 8]","[""GPUCA_WARP_SIZE"", 5]",
 GPUTPCCFGather,"[1024, 1]",,"[1024, 5]","[1024, 1]",,,,,,"[160, 11]","[1024, 1]",736,896,,"[928, 1]",,"[1024, 1]","[320, 2]",
 COMPRESSION_GATHER,1024,,1024,1024,,,,,,1024,1024,,1024,,,,,,
-GPUTPCGMMergerTrackFit,256,,"[192, 2]","[64, 7]",,,,,,"[32, 16]","[32, 8]","[32, 14]","[160, 2]",,"[32, 24]",,"[64, 8]","[64, 6]",
+GPUTPCGMMergerTrackFit,256,,"[192, 2]","[64, 7]",,,,,,"[32, 16]","[32, 8]","[32, 14]","[160, 2]",,"[32, 24]",,"[64, 8]","[64, 6]","[64, 4]"
 GPUTPCGMMergerFollowLoopers,256,,"[256, 5]","[256, 4]",,,,,,"[256, 4]","[128, 4]","[1024, 1]",640,,"[128, 16]",,"[224, 3]","[256, 7]",
 GPUTPCGMMergerSectorRefit,256,,"[64, 4]","[256, 2]",,,,,,"[32, 8]","[64, 5]","[32, 7]","[32, 7]",,"[32, 20]",,"[32, 10]","[64, 4]",
 GPUTPCGMMergerUnpackResetIds,256,,256,256,,,,,,256,256,256,256,,256,,256,256,