================ @@ -46,6 +46,24 @@ define amdgpu_kernel void @floor_f16( ; VI-NEXT: buffer_store_short v0, off, s[4:7], 0 ; VI-NEXT: s_endpgm ; +; GFX11-TRUE16-LABEL: floor_f16: +; GFX11-TRUE16: ; %bb.0: ; %entry +; GFX11-TRUE16-NEXT: s_load_b128 s[0:3], s[4:5], 0x24 +; GFX11-TRUE16-NEXT: s_mov_b32 s6, -1 +; GFX11-TRUE16-NEXT: s_mov_b32 s7, 0x31016000 +; GFX11-TRUE16-NEXT: s_mov_b32 s10, s6 +; GFX11-TRUE16-NEXT: s_mov_b32 s11, s7 +; GFX11-TRUE16-NEXT: s_waitcnt lgkmcnt(0) +; GFX11-TRUE16-NEXT: s_mov_b32 s8, s2 +; GFX11-TRUE16-NEXT: s_mov_b32 s9, s3 +; GFX11-TRUE16-NEXT: s_mov_b32 s4, s0 +; GFX11-TRUE16-NEXT: buffer_load_d16_b16 v0, off, s[8:11], 0 +; GFX11-TRUE16-NEXT: s_mov_b32 s5, s1 +; GFX11-TRUE16-NEXT: s_waitcnt vmcnt(0) +; GFX11-TRUE16-NEXT: v_floor_f16_e32 v0.l, v0.l +; GFX11-TRUE16-NEXT: buffer_store_b16 v0, off, s[4:7], 0 +; GFX11-TRUE16-NEXT: s_endpgm +; ---------------- saxlungs wrote:
I believe I've fixed this, the issue arose from something I missed when splitting up the initial work into separate branches for this stack. Let me know if you still think there's some artifacting https://github.com/llvm/llvm-project/pull/209889 _______________________________________________ llvm-branch-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
