Compiling a compute shader for GFX1010 shows incorrect 'wave_size'

Open AdamJMiles opened this issue 5 years ago • 1 comments

If you compile a compute shader with [numthreads(64,1,1)] the top of the ISA output says "wave_size(64)". However it's apparent from the generated asm that the code generated was designed for wave32.

Evidence for this is manipulation of only exec_lo (exec_hi is never touched) and the fact that DX12 Wave Intrinsics such as "WaveActiveSum" generate code that only sums across 32 lanes.

If GFX1010 uses Wave32 now as its native wave size for Compute then the "wave_size(64)" at the top of the ISA output should read "wave_size(32)" instead.

Mar 10 '20 16:03 AdamJMiles

Hi AdamJMiles,

Thanks for reporting this issue. A fix will be delivered in one of AMD's future driver releases. You do not need to update RGA to consume this fix.

Mar 25 '20 15:03 AmitBM