diff options
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/bf16.ll')
-rw-r--r-- | llvm/test/CodeGen/AMDGPU/bf16.ll | 22 |
1 files changed, 10 insertions, 12 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/bf16.ll b/llvm/test/CodeGen/AMDGPU/bf16.ll index bf4302c..4c9c34d 100644 --- a/llvm/test/CodeGen/AMDGPU/bf16.ll +++ b/llvm/test/CodeGen/AMDGPU/bf16.ll @@ -38342,12 +38342,11 @@ define <32 x bfloat> @v_vselect_v32bf16(<32 x i1> %cond, <32 x bfloat> %a, <32 x ; GFX10-NEXT: v_and_b32_e32 v2, 1, v2 ; GFX10-NEXT: v_and_b32_e32 v4, 1, v4 ; GFX10-NEXT: v_and_b32_e32 v6, 1, v6 -; GFX10-NEXT: v_writelane_b32 v40, s31, 1 ; GFX10-NEXT: v_and_b32_e32 v8, 1, v8 ; GFX10-NEXT: v_and_b32_e32 v10, 1, v10 +; GFX10-NEXT: v_writelane_b32 v40, s31, 1 ; GFX10-NEXT: v_and_b32_e32 v1, 1, v1 ; GFX10-NEXT: v_and_b32_e32 v3, 1, v3 -; GFX10-NEXT: v_writelane_b32 v40, s34, 2 ; GFX10-NEXT: v_and_b32_e32 v5, 1, v5 ; GFX10-NEXT: v_and_b32_e32 v7, 1, v7 ; GFX10-NEXT: v_and_b32_e32 v9, 1, v9 @@ -38366,7 +38365,7 @@ define <32 x bfloat> @v_vselect_v32bf16(<32 x i1> %cond, <32 x bfloat> %a, <32 x ; GFX10-NEXT: v_cmp_eq_u32_e64 s17, 1, v4 ; GFX10-NEXT: v_cmp_eq_u32_e64 s18, 1, v2 ; GFX10-NEXT: v_cmp_eq_u32_e64 s19, 1, v0 -; GFX10-NEXT: v_writelane_b32 v40, s35, 3 +; GFX10-NEXT: v_writelane_b32 v40, s34, 2 ; GFX10-NEXT: v_cmp_eq_u32_e64 s20, 1, v27 ; GFX10-NEXT: v_cmp_eq_u32_e64 s21, 1, v25 ; GFX10-NEXT: v_cmp_eq_u32_e64 s22, 1, v23 @@ -38377,10 +38376,10 @@ define <32 x bfloat> @v_vselect_v32bf16(<32 x i1> %cond, <32 x bfloat> %a, <32 x ; GFX10-NEXT: v_cmp_eq_u32_e64 s27, 1, v13 ; GFX10-NEXT: v_cmp_eq_u32_e64 s28, 1, v11 ; GFX10-NEXT: v_cmp_eq_u32_e64 s29, 1, v7 -; GFX10-NEXT: v_cmp_eq_u32_e64 s30, 1, v3 -; GFX10-NEXT: v_cmp_eq_u32_e64 s31, 1, v1 -; GFX10-NEXT: v_cmp_eq_u32_e64 s34, 1, v5 -; GFX10-NEXT: v_cmp_eq_u32_e64 s35, 1, v9 +; GFX10-NEXT: v_cmp_eq_u32_e64 vcc_hi, 1, v3 +; GFX10-NEXT: v_cmp_eq_u32_e64 s30, 1, v1 +; GFX10-NEXT: v_cmp_eq_u32_e64 s31, 1, v5 +; GFX10-NEXT: v_cmp_eq_u32_e64 s34, 1, v9 ; GFX10-NEXT: s_waitcnt vmcnt(32) ; GFX10-NEXT: v_lshrrev_b32_e32 v0, 16, v31 ; GFX10-NEXT: s_waitcnt vmcnt(31) @@ -38460,10 +38459,10 @@ define <32 x bfloat> @v_vselect_v32bf16(<32 x i1> %cond, <32 x bfloat> %a, <32 x ; GFX10-NEXT: v_cndmask_b32_e64 v6, v29, v39, s27 ; GFX10-NEXT: v_cndmask_b32_e64 v5, v28, v26, s28 ; GFX10-NEXT: v_cndmask_b32_e64 v20, v51, v20, s29 -; GFX10-NEXT: v_cndmask_b32_e64 v0, v14, v12, s31 -; GFX10-NEXT: v_cndmask_b32_e64 v1, v55, v16, s30 -; GFX10-NEXT: v_cndmask_b32_e64 v2, v53, v18, s34 -; GFX10-NEXT: v_cndmask_b32_e64 v12, v24, v22, s35 +; GFX10-NEXT: v_cndmask_b32_e64 v0, v14, v12, s30 +; GFX10-NEXT: v_cndmask_b32_e64 v1, v55, v16, vcc_hi +; GFX10-NEXT: v_cndmask_b32_e64 v2, v53, v18, s31 +; GFX10-NEXT: v_cndmask_b32_e64 v12, v24, v22, s34 ; GFX10-NEXT: v_cndmask_b32_e64 v16, v4, v3, s4 ; GFX10-NEXT: v_perm_b32 v0, v0, v64, 0x5040100 ; GFX10-NEXT: v_perm_b32 v1, v1, v54, 0x5040100 @@ -38481,7 +38480,6 @@ define <32 x bfloat> @v_vselect_v32bf16(<32 x i1> %cond, <32 x bfloat> %a, <32 x ; GFX10-NEXT: v_perm_b32 v13, v66, v13, 0x5040100 ; GFX10-NEXT: v_perm_b32 v14, v65, v17, 0x5040100 ; GFX10-NEXT: v_perm_b32 v15, v16, v15, 0x5040100 -; GFX10-NEXT: v_readlane_b32 s35, v40, 3 ; GFX10-NEXT: v_readlane_b32 s34, v40, 2 ; GFX10-NEXT: v_readlane_b32 s31, v40, 1 ; GFX10-NEXT: v_readlane_b32 s30, v40, 0 |