[llvm] [AMDGPU][True16][MC] 16bit vsrc and vdst support in MC (PR #104510)

Ivan Kosarev via llvm-commits llvm-commits at lists.llvm.org
Wed Sep 4 07:55:33 PDT 2024


================
@@ -403,50 +403,50 @@ v_ctz_i32_b32 v5, src_scc
 v_ctz_i32_b32 v255, 0xaf123456
 // GFX11: encoding: [0xff,0x74,0xfe,0x7f,0x56,0x34,0x12,0xaf]
 
-v_cvt_f16_f32 v5, v1
+v_cvt_f16_f32 v5.l, v1
----------------
kosarev wrote:

Just to make sure we are on the same page with this: these patches make no changes to the MC tests, such as reordering of instructions, that would complicate merging them in downstream, right?

https://github.com/llvm/llvm-project/pull/104510


More information about the llvm-commits mailing list