[PATCH] D101591: [AMDGPU] Improve global SADDR selection

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

This looks like it's regressing the case where the offset is known constant, but just doesn't fit.

Can you also make the corresponding globalisel change?



================
Comment at: llvm/test/CodeGen/AMDGPU/global-saddr-load.ll:88-91
+; GFX10-NEXT:    v_mov_b32_e32 v0, 0
+; GFX10-NEXT:    s_add_u32 s0, s2, 0xfffff000
+; GFX10-NEXT:    s_addc_u32 s1, s3, -1
+; GFX10-NEXT:    global_load_ubyte v0, v0, s[0:1]
----------------
This is more instructions


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D101591/new/

https://reviews.llvm.org/D101591