[llvm] [AMDGPU][True16][MC] support more VOP3 inst in true16/fake16 format (PR #113603)

Ivan Kosarev via llvm-commits llvm-commits at lists.llvm.org
Wed Nov 13 09:05:54 PST 2024


================
@@ -596,58 +596,58 @@ v_and_or_b32 v255, 0xaf123456, vcc_hi, null
 // GFX11: encoding: [0xff,0x00,0x57,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
 
 v_ashrrev_i16 v5.l, v1.l, v2.l
-// GFX11: [0x05,0x00,0x3a,0xd7,0x01,0x05,0x02,0x00]
+// GFX11: encoding: [0x05,0x00,0x3a,0xd7,0x01,0x05,0x02,0x00]
----------------
kosarev wrote:

In the future please move such changes to separate patches.

https://github.com/llvm/llvm-project/pull/113603


More information about the llvm-commits mailing list