search for: d35471

...rectness issue: Currently, Polly assumes that 64 bits is large enough for all new loop-induction variables and index expressions. In rare cases, transformations could be performed where more bits are required. Preconditions need to be generated preventing this (e.g., D35471). * A performance issue: Polly currently models temporal locality (i.e., it tries to get better reuse in time), but does not model spatial locality (i.e., it does not model cache-line reuse). As a result, it can sometimes introduce performance regress...

...t 64 bits is large > > enough for all new loop-induction variables and index expressions. > > In rare cases, transformations could be performed where more bits > > are required. Preconditions need to be generated preventing this > > (e.g., D35471). > > > > * > > > > A performance issue: Polly currently models temporal locality (i.e., > > it tries to get better reuse in time), but does not model spatial > > locality (i.e., it does not model cache-line reuse). A...

...ently, Polly assumes that 64 bits is >> large enough for all new loop-induction variables and index >> expressions. In rare cases, transformations could be performed >> where more bits are required. Preconditions need to be generated >> preventing this (e.g., D35471). >> * >> A performance issue: Polly currently models temporal locality >> (i.e., it tries to get better reuse in time), but does not model >> spatial locality (i.e., it does not model cache-line reuse). As a >> result, it can sometimes introduce perfo...

...* A correctness issue: Currently, Polly assumes that 64 bits is large enough for all new loop-induction variables and index expressions. In rare cases, transformations could be performed where more bits are required. Preconditions need to be generated preventing this (e.g., D35471). * A performance issue: Polly currently models temporal locality (i.e., it tries to get better reuse in time), but does not model spatial locality (i.e., it does not model cache-line reuse). As a result, it can sometimes introduce performance regressions. Polly Labs is curr...

...ult: - A correctness issue: > Currently, Polly assumes that 64 bits is large enough for all new > loop-induction variables and index expressions. In rare cases, > transformations could be performed where more bits are required. > Preconditions need to be generated preventing this (e.g., D35471). - A > performance issue: Polly currently models temporal locality (i.e., it tries > to get better reuse in time), but does not model spatial locality (i.e., it > does not model cache-line reuse). As a result, it can sometimes introduce > performance regressions. Polly Labs is currentl...

...d by default: >>> A correctness issue: Currently, Polly assumes that 64 bits is large enough for all new loop-induction variables and index expressions. In rare cases, transformations could be performed where more bits are required. Preconditions need to be generated preventing this (e.g., D35471). >>> A performance issue: Polly currently models temporal locality (i.e., it tries to get better reuse in time), but does not model spatial locality (i.e., it does not model cache-line reuse). As a result, it can sometimes introduce performance regressions. Polly Labs is currently working...

...ently, Polly assumes that 64 bits is large > > enough for all new loop-induction variables and index expressions. > > In rare cases, transformations could be performed where more bits > > are required. Preconditions need to be generated preventing this > > (e.g., D35471). > > > > * > > > > A performance issue: Polly currently models temporal locality (i.e., > > it tries to get better reuse in time), but does not model spatial > > locality (i.e., it does not model cache-line reuse). As a result, it > > can some...

...rectness issue: Currently, Polly assumes that 64 bits is large > enough for all new loop-induction variables and index expressions. > In rare cases, transformations could be performed where more bits > are required. Preconditions need to be generated preventing this > (e.g., D35471). > > * > > A performance issue: Polly currently models temporal locality (i.e., > it tries to get better reuse in time), but does not model spatial > locality (i.e., it does not model cache-line reuse). As a result, it > can sometimes introduce performance regre...