Re: [PATCH][AArch64] PR79262: Adjust vector cost

Hi Richard, > I acked this here: > https://gcc.gnu.org/ml/gcc-patches/2019-10/msg01229.html Thanks - I missed your email, but it's committed now. Yes we will need to look at the vector costs again and retune them based on recent vectorizer improvements and latest microarchitectures. Cheers,

Re: [PATCH][AArch64] PR79262: Adjust vector cost

Wilco Dijkstra writes: > ping I acked this here: https://gcc.gnu.org/ml/gcc-patches/2019-10/msg01229.html > > PR79262 has been fixed for almost all AArch64 cpus, however the example is > still > vectorized in a few cases, resulting in lower performance. Increase the cost > of >

Re: [PATCH][AArch64] PR79262: Adjust vector cost

ping PR79262 has been fixed for almost all AArch64 cpus, however the example is still vectorized in a few cases, resulting in lower performance. Increase the cost of vector-to-scalar moves so it is more similar to the other vector costs. As a result -mcpu=cortex-a53 no longer vectorizes the

Re: [PATCH][AArch64] PR79262: Adjust vector cost

Wilco Dijkstra writes: > ping > > PR79262 has been fixed for almost all AArch64 cpus, however the example is > still > vectorized in a few cases, resulting in lower performance. Increase the cost > of > vector-to-scalar moves so it is more similar to the other vector costs. As a > result >

Re: [PATCH][AArch64] PR79262: Adjust vector cost

ping PR79262 has been fixed for almost all AArch64 cpus, however the example is still vectorized in a few cases, resulting in lower performance. Increase the cost of vector-to-scalar moves so it is more similar to the other vector costs. As a result -mcpu=cortex-a53 no longer vectorizes the

Re: [PATCH][AArch64] PR79262: Adjust vector cost

Hi James, >On Mon, Jan 22, 2018 at 09:22:27AM -0600, Richard Biener wrote: >> It would be better to dissect this cost into vec_to_scalar and vec_extract >> where >> vec_to_scalar really means getting at the scalar value of a vector of >> uniform values >> which most targets can do without any

Re: [PATCH][AArch64] PR79262: Adjust vector cost

Hi James, > We have 7 unique target tuning structures in the AArch64 backend, of which > only one has a 2x ratio between scalar_int_cost and vec_to_scalar_cost. Other > ratios are 1, 3, 8, 3, 4, 6. I wouldn't read too much in the exact value here - the costs are simply relative to other values

Re: [PATCH][AArch64] PR79262: Adjust vector cost

On Mon, Jan 22, 2018 at 09:22:27AM -0600, Richard Biener wrote: > On Mon, Jan 22, 2018 at 4:01 PM, Wilco Dijkstra > wrote: > > PR79262 has been fixed for almost all AArch64 cpus, however the example is > > still > > vectorized in a few cases, resulting in lower performance. Increase the > >

Re: [PATCH][AArch64] PR79262: Adjust vector cost

On Fri, Nov 09, 2018 at 08:14:27AM -0600, Wilco Dijkstra wrote: > PR79262 has been fixed for almost all AArch64 cpus, however the example is > still > vectorized in a few cases, resulting in lower performance.  Increase the cost > of > vector-to-scalar moves so it is more similar to the other

[PATCH][AArch64] PR79262: Adjust vector cost

PR79262 has been fixed for almost all AArch64 cpus, however the example is still vectorized in a few cases, resulting in lower performance.  Increase the cost of vector-to-scalar moves so it is more similar to the other vector costs. As a result -mcpu=cortex-a53 no longer vectorizes the testcase

Re: [PATCH][AArch64] PR79262: Adjust vector cost

On Mon, Jan 22, 2018 at 4:01 PM, Wilco Dijkstra wrote: > PR79262 has been fixed for almost all AArch64 cpus, however the example is > still > vectorized in a few cases, resulting in lower performance. Increase the cost > of > vector-to-scalar moves so it is more similar

[PATCH][AArch64] PR79262: Adjust vector cost

PR79262 has been fixed for almost all AArch64 cpus, however the example is still vectorized in a few cases, resulting in lower performance. Increase the cost of vector-to-scalar moves so it is more similar to the other vector costs. As a result -mcpu=cortex-a53 no longer vectorizes the testcase