[llvm] r338569 - AMDGPU: Allow fp32-denormals feature for r600 targets

[Hans Wennborg via llvm-commits]

Merged to 7.0 in r339103.

On Wed, Aug 1, 2018 at 5:04 PM, Jan Vesely via llvm-commits
<llvm-commits at lists.llvm.org> wrote:
> Author: jvesely
> Date: Wed Aug  1 08:04:36 2018
> New Revision: 338569
>
> URL: http://llvm.org/viewvc/llvm-project?rev=338569&view=rev
> Log:
> AMDGPU: Allow fp32-denormals feature for r600 targets
>
> This was accidentally removed in r335942.
>
> Differential Revision: https://reviews.llvm.org/D49934
>
> Modified:
>     llvm/trunk/lib/Target/AMDGPU/AMDGPU.td
>     llvm/trunk/lib/Target/AMDGPU/AMDGPUFeatures.td
>
> Modified: llvm/trunk/lib/Target/AMDGPU/AMDGPU.td
> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/AMDGPU.td?rev=338569&r1=338568&r2=338569&view=diff
> ==============================================================================
> --- llvm/trunk/lib/Target/AMDGPU/AMDGPU.td (original)
> +++ llvm/trunk/lib/Target/AMDGPU/AMDGPU.td Wed Aug  1 08:04:36 2018
> @@ -267,15 +267,6 @@ def FeatureD16PreservesUnusedBits : Subt
>  // Subtarget Features (options and debugging)
>  //===------------------------------------------------------------===//
>
> -// Some instructions do not support denormals despite this flag. Using
> -// fp32 denormals also causes instructions to run at the double
> -// precision rate for the device.
> -def FeatureFP32Denormals : SubtargetFeature<"fp32-denormals",
> -  "FP32Denormals",
> -  "true",
> -  "Enable single precision denormal handling"
> ->;
> -
>  // Denormal handling for fp64 and fp16 is controlled by the same
>  // config register when fp16 supported.
>  // TODO: Do we need a separate f16 setting when not legal?
>
> Modified: llvm/trunk/lib/Target/AMDGPU/AMDGPUFeatures.td
> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/AMDGPUFeatures.td?rev=338569&r1=338568&r2=338569&view=diff
> ==============================================================================
> --- llvm/trunk/lib/Target/AMDGPU/AMDGPUFeatures.td (original)
> +++ llvm/trunk/lib/Target/AMDGPU/AMDGPUFeatures.td Wed Aug  1 08:04:36 2018
> @@ -19,6 +19,15 @@ def FeatureFMA : SubtargetFeature<"fmaf"
>    "Enable single precision FMA (not as fast as mul+add, but fused)"
>  >;
>
> +// Some instructions do not support denormals despite this flag. Using
> +// fp32 denormals also causes instructions to run at the double
> +// precision rate for the device.
> +def FeatureFP32Denormals : SubtargetFeature<"fp32-denormals",
> +  "FP32Denormals",
> +  "true",
> +  "Enable single precision denormal handling"
> +>;
> +
>  class SubtargetFeatureLocalMemorySize <int Value> : SubtargetFeature<
>    "localmemorysize"#Value,
>    "LocalMemorySize",
>
>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at lists.llvm.org
> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits