[PATCH] D14327: IR: Add llvm.ldexp and llvm.experimental.constrained.ldexp intrinsics

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/test/MC/AMDGPU/gfx10_asm_vop2.s:12937
 
 v_ldexp_f16_e64 v5, v1, -4.0
+// GFX10: encoding: [0x05,0x00,0x3b,0xd5,0x01,0xff,0x01,0x00,0x00,0xc4,0x00,0x00]
----------------
foad wrote:
> > The assembler now rejects these as invalid literals.
> Looks like it is still accepting -4.0 here?
It's being accepted as a 32-bit literal, which is valid on gfx10


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D14327/new/

https://reviews.llvm.org/D14327