Re: [PATCH, ivopts] Fix fast-math-pr55281.c ICE

2020-01-31 Thread Andrew Stubbs
On 31/01/2020 08:09, Richard Biener wrote: On Thu, Jan 30, 2020 at 3:09 PM Andrew Stubbs wrote: How about this? I've only tested it on the one testcase, so far, but it works for that. OK to commit (following a full test)? OK. X86_64 bootstrap and test showed no issues. Nor amdgcn build an

Re: [PATCH, ivopts] Fix fast-math-pr55281.c ICE

2020-01-31 Thread Richard Biener
On Thu, Jan 30, 2020 at 3:09 PM Andrew Stubbs wrote: > > On 30/01/2020 13:49, Richard Biener wrote: > > On Thu, Jan 30, 2020 at 2:04 PM Bin.Cheng wrote: > >> > >> On Thu, Jan 30, 2020 at 8:53 PM Andrew Stubbs > >> wrote: > >>> > >>> On 29/01/2020 08:24, Richard Biener wrote: > On Tue, Jan

Re: [PATCH, ivopts] Fix fast-math-pr55281.c ICE

2020-01-30 Thread Andrew Stubbs
On 30/01/2020 13:49, Richard Biener wrote: On Thu, Jan 30, 2020 at 2:04 PM Bin.Cheng wrote: On Thu, Jan 30, 2020 at 8:53 PM Andrew Stubbs wrote: On 29/01/2020 08:24, Richard Biener wrote: On Tue, Jan 28, 2020 at 5:53 PM Andrew Stubbs wrote: This patch fixes an ICE compiling fast-math-pr

Re: [PATCH, ivopts] Fix fast-math-pr55281.c ICE

2020-01-30 Thread Richard Biener
On Thu, Jan 30, 2020 at 2:04 PM Bin.Cheng wrote: > > On Thu, Jan 30, 2020 at 8:53 PM Andrew Stubbs wrote: > > > > On 29/01/2020 08:24, Richard Biener wrote: > > > On Tue, Jan 28, 2020 at 5:53 PM Andrew Stubbs > > > wrote: > > >> > > >> This patch fixes an ICE compiling fast-math-pr55281.c for a

Re: [PATCH, ivopts] Fix fast-math-pr55281.c ICE

2020-01-30 Thread Bin.Cheng
On Thu, Jan 30, 2020 at 8:53 PM Andrew Stubbs wrote: > > On 29/01/2020 08:24, Richard Biener wrote: > > On Tue, Jan 28, 2020 at 5:53 PM Andrew Stubbs wrote: > >> > >> This patch fixes an ICE compiling fast-math-pr55281.c for amdgcn. > >> > >> The problem is that an "iv" is created in which both b

Re: [PATCH, ivopts] Fix fast-math-pr55281.c ICE

2020-01-30 Thread Andrew Stubbs
On 29/01/2020 08:24, Richard Biener wrote: On Tue, Jan 28, 2020 at 5:53 PM Andrew Stubbs wrote: This patch fixes an ICE compiling fast-math-pr55281.c for amdgcn. The problem is that an "iv" is created in which both base and step are pointer types, How did you get a POINTER_TYPE step? That'

Re: [PATCH, ivopts] Fix fast-math-pr55281.c ICE

2020-01-29 Thread Richard Biener
On Tue, Jan 28, 2020 at 5:53 PM Andrew Stubbs wrote: > > This patch fixes an ICE compiling fast-math-pr55281.c for amdgcn. > > The problem is that an "iv" is created in which both base and step are > pointer types, How did you get a POINTER_TYPE step? That's where the issue lies I think. > but

[PATCH, ivopts] Fix fast-math-pr55281.c ICE

2020-01-28 Thread Andrew Stubbs
This patch fixes an ICE compiling fast-math-pr55281.c for amdgcn. The problem is that an "iv" is created in which both base and step are pointer types, but the base is converted to sizetype without also converting the step to a non-pointer type. Later in the compilation this results in a PLUS_