diff options
author | Pirama Arumuga Nainar <pirama@google.com> | 2015-04-10 22:08:18 +0000 |
---|---|---|
committer | Android Git Automerger <android-git-automerger@android.com> | 2015-04-10 22:08:18 +0000 |
commit | 13a7db5b9c4f5e543d037be68ec3428216bfd550 (patch) | |
tree | 1b2c9792582e12f5af0b1512e3094425f0dc0df9 /test/CodeGen/R600/ds_write2.ll | |
parent | 0eb46f5d1e06a4284663d636a74b06adc3a161d7 (diff) | |
parent | 31195f0bdca6ee2a5e72d07edf13e1d81206d949 (diff) | |
download | external_llvm-13a7db5b9c4f5e543d037be68ec3428216bfd550.zip external_llvm-13a7db5b9c4f5e543d037be68ec3428216bfd550.tar.gz external_llvm-13a7db5b9c4f5e543d037be68ec3428216bfd550.tar.bz2 |
am 31195f0b: Merge "Update aosp/master llvm for rebase to r233350"
* commit '31195f0bdca6ee2a5e72d07edf13e1d81206d949':
Update aosp/master llvm for rebase to r233350
Diffstat (limited to 'test/CodeGen/R600/ds_write2.ll')
-rw-r--r-- | test/CodeGen/R600/ds_write2.ll | 206 |
1 files changed, 103 insertions, 103 deletions
diff --git a/test/CodeGen/R600/ds_write2.ll b/test/CodeGen/R600/ds_write2.ll index e2db81a..1d94c57 100644 --- a/test/CodeGen/R600/ds_write2.ll +++ b/test/CodeGen/R600/ds_write2.ll @@ -11,12 +11,12 @@ ; SI: s_endpgm define void @simple_write2_one_val_f32(float addrspace(1)* %C, float addrspace(1)* %in) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in.gep = getelementptr float addrspace(1)* %in, i32 %x.i - %val = load float addrspace(1)* %in.gep, align 4 - %arrayidx0 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i + %in.gep = getelementptr float, float addrspace(1)* %in, i32 %x.i + %val = load float, float addrspace(1)* %in.gep, align 4 + %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i store float %val, float addrspace(3)* %arrayidx0, align 4 %add.x = add nsw i32 %x.i, 8 - %arrayidx1 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x + %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x store float %val, float addrspace(3)* %arrayidx1, align 4 ret void } @@ -29,14 +29,14 @@ define void @simple_write2_one_val_f32(float addrspace(1)* %C, float addrspace(1 ; SI: s_endpgm define void @simple_write2_two_val_f32(float addrspace(1)* %C, float addrspace(1)* %in) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in.gep.0 = getelementptr float addrspace(1)* %in, i32 %x.i - %in.gep.1 = getelementptr float addrspace(1)* %in.gep.0, i32 1 - %val0 = load float addrspace(1)* %in.gep.0, align 4 - %val1 = load float addrspace(1)* %in.gep.1, align 4 - %arrayidx0 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i + %in.gep.0 = getelementptr float, float addrspace(1)* %in, i32 %x.i + %in.gep.1 = getelementptr float, float addrspace(1)* %in.gep.0, i32 1 + %val0 = load float, float addrspace(1)* %in.gep.0, align 4 + %val1 = load float, float addrspace(1)* %in.gep.1, align 4 + %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i store float %val0, float addrspace(3)* %arrayidx0, align 4 %add.x = add nsw i32 %x.i, 8 - %arrayidx1 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x + %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x store float %val1, float addrspace(3)* %arrayidx1, align 4 ret void } @@ -48,14 +48,14 @@ define void @simple_write2_two_val_f32(float addrspace(1)* %C, float addrspace(1 ; SI: s_endpgm define void @simple_write2_two_val_f32_volatile_0(float addrspace(1)* %C, float addrspace(1)* %in0, float addrspace(1)* %in1) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in0.gep = getelementptr float addrspace(1)* %in0, i32 %x.i - %in1.gep = getelementptr float addrspace(1)* %in1, i32 %x.i - %val0 = load float addrspace(1)* %in0.gep, align 4 - %val1 = load float addrspace(1)* %in1.gep, align 4 - %arrayidx0 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i + %in0.gep = getelementptr float, float addrspace(1)* %in0, i32 %x.i + %in1.gep = getelementptr float, float addrspace(1)* %in1, i32 %x.i + %val0 = load float, float addrspace(1)* %in0.gep, align 4 + %val1 = load float, float addrspace(1)* %in1.gep, align 4 + %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i store volatile float %val0, float addrspace(3)* %arrayidx0, align 4 %add.x = add nsw i32 %x.i, 8 - %arrayidx1 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x + %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x store float %val1, float addrspace(3)* %arrayidx1, align 4 ret void } @@ -67,14 +67,14 @@ define void @simple_write2_two_val_f32_volatile_0(float addrspace(1)* %C, float ; SI: s_endpgm define void @simple_write2_two_val_f32_volatile_1(float addrspace(1)* %C, float addrspace(1)* %in0, float addrspace(1)* %in1) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in0.gep = getelementptr float addrspace(1)* %in0, i32 %x.i - %in1.gep = getelementptr float addrspace(1)* %in1, i32 %x.i - %val0 = load float addrspace(1)* %in0.gep, align 4 - %val1 = load float addrspace(1)* %in1.gep, align 4 - %arrayidx0 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i + %in0.gep = getelementptr float, float addrspace(1)* %in0, i32 %x.i + %in1.gep = getelementptr float, float addrspace(1)* %in1, i32 %x.i + %val0 = load float, float addrspace(1)* %in0.gep, align 4 + %val1 = load float, float addrspace(1)* %in1.gep, align 4 + %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i store float %val0, float addrspace(3)* %arrayidx0, align 4 %add.x = add nsw i32 %x.i, 8 - %arrayidx1 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x + %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x store volatile float %val1, float addrspace(3)* %arrayidx1, align 4 ret void } @@ -88,16 +88,16 @@ define void @simple_write2_two_val_f32_volatile_1(float addrspace(1)* %C, float ; SI: s_endpgm define void @simple_write2_two_val_subreg2_mixed_f32(float addrspace(1)* %C, <2 x float> addrspace(1)* %in) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in.gep.0 = getelementptr <2 x float> addrspace(1)* %in, i32 %x.i - %in.gep.1 = getelementptr <2 x float> addrspace(1)* %in.gep.0, i32 1 - %val0 = load <2 x float> addrspace(1)* %in.gep.0, align 8 - %val1 = load <2 x float> addrspace(1)* %in.gep.1, align 8 + %in.gep.0 = getelementptr <2 x float>, <2 x float> addrspace(1)* %in, i32 %x.i + %in.gep.1 = getelementptr <2 x float>, <2 x float> addrspace(1)* %in.gep.0, i32 1 + %val0 = load <2 x float>, <2 x float> addrspace(1)* %in.gep.0, align 8 + %val1 = load <2 x float>, <2 x float> addrspace(1)* %in.gep.1, align 8 %val0.0 = extractelement <2 x float> %val0, i32 0 %val1.1 = extractelement <2 x float> %val1, i32 1 - %arrayidx0 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i + %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i store float %val0.0, float addrspace(3)* %arrayidx0, align 4 %add.x = add nsw i32 %x.i, 8 - %arrayidx1 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x + %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x store float %val1.1, float addrspace(3)* %arrayidx1, align 4 ret void } @@ -109,14 +109,14 @@ define void @simple_write2_two_val_subreg2_mixed_f32(float addrspace(1)* %C, <2 ; SI: s_endpgm define void @simple_write2_two_val_subreg2_f32(float addrspace(1)* %C, <2 x float> addrspace(1)* %in) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in.gep = getelementptr <2 x float> addrspace(1)* %in, i32 %x.i - %val = load <2 x float> addrspace(1)* %in.gep, align 8 + %in.gep = getelementptr <2 x float>, <2 x float> addrspace(1)* %in, i32 %x.i + %val = load <2 x float>, <2 x float> addrspace(1)* %in.gep, align 8 %val0 = extractelement <2 x float> %val, i32 0 %val1 = extractelement <2 x float> %val, i32 1 - %arrayidx0 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i + %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i store float %val0, float addrspace(3)* %arrayidx0, align 4 %add.x = add nsw i32 %x.i, 8 - %arrayidx1 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x + %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x store float %val1, float addrspace(3)* %arrayidx1, align 4 ret void } @@ -128,14 +128,14 @@ define void @simple_write2_two_val_subreg2_f32(float addrspace(1)* %C, <2 x floa ; SI: s_endpgm define void @simple_write2_two_val_subreg4_f32(float addrspace(1)* %C, <4 x float> addrspace(1)* %in) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in.gep = getelementptr <4 x float> addrspace(1)* %in, i32 %x.i - %val = load <4 x float> addrspace(1)* %in.gep, align 16 + %in.gep = getelementptr <4 x float>, <4 x float> addrspace(1)* %in, i32 %x.i + %val = load <4 x float>, <4 x float> addrspace(1)* %in.gep, align 16 %val0 = extractelement <4 x float> %val, i32 0 %val1 = extractelement <4 x float> %val, i32 3 - %arrayidx0 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i + %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i store float %val0, float addrspace(3)* %arrayidx0, align 4 %add.x = add nsw i32 %x.i, 8 - %arrayidx1 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x + %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x store float %val1, float addrspace(3)* %arrayidx1, align 4 ret void } @@ -148,14 +148,14 @@ define void @simple_write2_two_val_subreg4_f32(float addrspace(1)* %C, <4 x floa ; SI: s_endpgm define void @simple_write2_two_val_max_offset_f32(float addrspace(1)* %C, float addrspace(1)* %in) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in.gep.0 = getelementptr float addrspace(1)* %in, i32 %x.i - %in.gep.1 = getelementptr float addrspace(1)* %in.gep.0, i32 1 - %val0 = load float addrspace(1)* %in.gep.0, align 4 - %val1 = load float addrspace(1)* %in.gep.1, align 4 - %arrayidx0 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i + %in.gep.0 = getelementptr float, float addrspace(1)* %in, i32 %x.i + %in.gep.1 = getelementptr float, float addrspace(1)* %in.gep.0, i32 1 + %val0 = load float, float addrspace(1)* %in.gep.0, align 4 + %val1 = load float, float addrspace(1)* %in.gep.1, align 4 + %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i store float %val0, float addrspace(3)* %arrayidx0, align 4 %add.x = add nsw i32 %x.i, 255 - %arrayidx1 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x + %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x store float %val1, float addrspace(3)* %arrayidx1, align 4 ret void } @@ -166,14 +166,14 @@ define void @simple_write2_two_val_max_offset_f32(float addrspace(1)* %C, float ; SI: s_endpgm define void @simple_write2_two_val_too_far_f32(float addrspace(1)* %C, float addrspace(1)* %in0, float addrspace(1)* %in1) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in0.gep = getelementptr float addrspace(1)* %in0, i32 %x.i - %in1.gep = getelementptr float addrspace(1)* %in1, i32 %x.i - %val0 = load float addrspace(1)* %in0.gep, align 4 - %val1 = load float addrspace(1)* %in1.gep, align 4 - %arrayidx0 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i + %in0.gep = getelementptr float, float addrspace(1)* %in0, i32 %x.i + %in1.gep = getelementptr float, float addrspace(1)* %in1, i32 %x.i + %val0 = load float, float addrspace(1)* %in0.gep, align 4 + %val1 = load float, float addrspace(1)* %in1.gep, align 4 + %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i store float %val0, float addrspace(3)* %arrayidx0, align 4 %add.x = add nsw i32 %x.i, 257 - %arrayidx1 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x + %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x store float %val1, float addrspace(3)* %arrayidx1, align 4 ret void } @@ -184,25 +184,25 @@ define void @simple_write2_two_val_too_far_f32(float addrspace(1)* %C, float add ; SI: s_endpgm define void @simple_write2_two_val_f32_x2(float addrspace(1)* %C, float addrspace(1)* %in0, float addrspace(1)* %in1) #0 { %tid.x = tail call i32 @llvm.r600.read.tidig.x() #1 - %in0.gep = getelementptr float addrspace(1)* %in0, i32 %tid.x - %in1.gep = getelementptr float addrspace(1)* %in1, i32 %tid.x - %val0 = load float addrspace(1)* %in0.gep, align 4 - %val1 = load float addrspace(1)* %in1.gep, align 4 + %in0.gep = getelementptr float, float addrspace(1)* %in0, i32 %tid.x + %in1.gep = getelementptr float, float addrspace(1)* %in1, i32 %tid.x + %val0 = load float, float addrspace(1)* %in0.gep, align 4 + %val1 = load float, float addrspace(1)* %in1.gep, align 4 %idx.0 = add nsw i32 %tid.x, 0 - %arrayidx0 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.0 + %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.0 store float %val0, float addrspace(3)* %arrayidx0, align 4 %idx.1 = add nsw i32 %tid.x, 8 - %arrayidx1 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.1 + %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.1 store float %val1, float addrspace(3)* %arrayidx1, align 4 %idx.2 = add nsw i32 %tid.x, 11 - %arrayidx2 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.2 + %arrayidx2 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.2 store float %val0, float addrspace(3)* %arrayidx2, align 4 %idx.3 = add nsw i32 %tid.x, 27 - %arrayidx3 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.3 + %arrayidx3 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.3 store float %val1, float addrspace(3)* %arrayidx3, align 4 ret void @@ -214,25 +214,25 @@ define void @simple_write2_two_val_f32_x2(float addrspace(1)* %C, float addrspac ; SI: s_endpgm define void @simple_write2_two_val_f32_x2_nonzero_base(float addrspace(1)* %C, float addrspace(1)* %in0, float addrspace(1)* %in1) #0 { %tid.x = tail call i32 @llvm.r600.read.tidig.x() #1 - %in0.gep = getelementptr float addrspace(1)* %in0, i32 %tid.x - %in1.gep = getelementptr float addrspace(1)* %in1, i32 %tid.x - %val0 = load float addrspace(1)* %in0.gep, align 4 - %val1 = load float addrspace(1)* %in1.gep, align 4 + %in0.gep = getelementptr float, float addrspace(1)* %in0, i32 %tid.x + %in1.gep = getelementptr float, float addrspace(1)* %in1, i32 %tid.x + %val0 = load float, float addrspace(1)* %in0.gep, align 4 + %val1 = load float, float addrspace(1)* %in1.gep, align 4 %idx.0 = add nsw i32 %tid.x, 3 - %arrayidx0 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.0 + %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.0 store float %val0, float addrspace(3)* %arrayidx0, align 4 %idx.1 = add nsw i32 %tid.x, 8 - %arrayidx1 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.1 + %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.1 store float %val1, float addrspace(3)* %arrayidx1, align 4 %idx.2 = add nsw i32 %tid.x, 11 - %arrayidx2 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.2 + %arrayidx2 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.2 store float %val0, float addrspace(3)* %arrayidx2, align 4 %idx.3 = add nsw i32 %tid.x, 27 - %arrayidx3 = getelementptr inbounds [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.3 + %arrayidx3 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.3 store float %val1, float addrspace(3)* %arrayidx3, align 4 ret void @@ -245,19 +245,19 @@ define void @simple_write2_two_val_f32_x2_nonzero_base(float addrspace(1)* %C, f ; SI: s_endpgm define void @write2_ptr_subreg_arg_two_val_f32(float addrspace(1)* %C, float addrspace(1)* %in0, float addrspace(1)* %in1, <2 x float addrspace(3)*> %lds.ptr) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in0.gep = getelementptr float addrspace(1)* %in0, i32 %x.i - %in1.gep = getelementptr float addrspace(1)* %in1, i32 %x.i - %val0 = load float addrspace(1)* %in0.gep, align 4 - %val1 = load float addrspace(1)* %in1.gep, align 4 + %in0.gep = getelementptr float, float addrspace(1)* %in0, i32 %x.i + %in1.gep = getelementptr float, float addrspace(1)* %in1, i32 %x.i + %val0 = load float, float addrspace(1)* %in0.gep, align 4 + %val1 = load float, float addrspace(1)* %in1.gep, align 4 %index.0 = insertelement <2 x i32> undef, i32 %x.i, i32 0 %index.1 = insertelement <2 x i32> %index.0, i32 8, i32 0 - %gep = getelementptr inbounds <2 x float addrspace(3)*> %lds.ptr, <2 x i32> %index.1 + %gep = getelementptr inbounds float, <2 x float addrspace(3)*> %lds.ptr, <2 x i32> %index.1 %gep.0 = extractelement <2 x float addrspace(3)*> %gep, i32 0 %gep.1 = extractelement <2 x float addrspace(3)*> %gep, i32 1 ; Apply an additional offset after the vector that will be more obviously folded. - %gep.1.offset = getelementptr float addrspace(3)* %gep.1, i32 8 + %gep.1.offset = getelementptr float, float addrspace(3)* %gep.1, i32 8 store float %val0, float addrspace(3)* %gep.0, align 4 %add.x = add nsw i32 %x.i, 8 @@ -272,12 +272,12 @@ define void @write2_ptr_subreg_arg_two_val_f32(float addrspace(1)* %C, float add ; SI: s_endpgm define void @simple_write2_one_val_f64(double addrspace(1)* %C, double addrspace(1)* %in) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in.gep = getelementptr double addrspace(1)* %in, i32 %x.i - %val = load double addrspace(1)* %in.gep, align 8 - %arrayidx0 = getelementptr inbounds [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %x.i + %in.gep = getelementptr double, double addrspace(1)* %in, i32 %x.i + %val = load double, double addrspace(1)* %in.gep, align 8 + %arrayidx0 = getelementptr inbounds [512 x double], [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %x.i store double %val, double addrspace(3)* %arrayidx0, align 8 %add.x = add nsw i32 %x.i, 8 - %arrayidx1 = getelementptr inbounds [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %add.x + %arrayidx1 = getelementptr inbounds [512 x double], [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %add.x store double %val, double addrspace(3)* %arrayidx1, align 8 ret void } @@ -290,12 +290,12 @@ define void @simple_write2_one_val_f64(double addrspace(1)* %C, double addrspace ; SI: s_endpgm define void @misaligned_simple_write2_one_val_f64(double addrspace(1)* %C, double addrspace(1)* %in, double addrspace(3)* %lds) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in.gep = getelementptr double addrspace(1)* %in, i32 %x.i - %val = load double addrspace(1)* %in.gep, align 8 - %arrayidx0 = getelementptr inbounds double addrspace(3)* %lds, i32 %x.i + %in.gep = getelementptr double, double addrspace(1)* %in, i32 %x.i + %val = load double, double addrspace(1)* %in.gep, align 8 + %arrayidx0 = getelementptr inbounds double, double addrspace(3)* %lds, i32 %x.i store double %val, double addrspace(3)* %arrayidx0, align 4 %add.x = add nsw i32 %x.i, 7 - %arrayidx1 = getelementptr inbounds double addrspace(3)* %lds, i32 %add.x + %arrayidx1 = getelementptr inbounds double, double addrspace(3)* %lds, i32 %add.x store double %val, double addrspace(3)* %arrayidx1, align 4 ret void } @@ -308,14 +308,14 @@ define void @misaligned_simple_write2_one_val_f64(double addrspace(1)* %C, doubl ; SI: s_endpgm define void @simple_write2_two_val_f64(double addrspace(1)* %C, double addrspace(1)* %in) #0 { %x.i = tail call i32 @llvm.r600.read.tidig.x() #1 - %in.gep.0 = getelementptr double addrspace(1)* %in, i32 %x.i - %in.gep.1 = getelementptr double addrspace(1)* %in.gep.0, i32 1 - %val0 = load double addrspace(1)* %in.gep.0, align 8 - %val1 = load double addrspace(1)* %in.gep.1, align 8 - %arrayidx0 = getelementptr inbounds [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %x.i + %in.gep.0 = getelementptr double, double addrspace(1)* %in, i32 %x.i + %in.gep.1 = getelementptr double, double addrspace(1)* %in.gep.0, i32 1 + %val0 = load double, double addrspace(1)* %in.gep.0, align 8 + %val1 = load double, double addrspace(1)* %in.gep.1, align 8 + %arrayidx0 = getelementptr inbounds [512 x double], [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %x.i store double %val0, double addrspace(3)* %arrayidx0, align 8 %add.x = add nsw i32 %x.i, 8 - %arrayidx1 = getelementptr inbounds [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %add.x + %arrayidx1 = getelementptr inbounds [512 x double], [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %add.x store double %val1, double addrspace(3)* %arrayidx1, align 8 ret void } @@ -326,8 +326,8 @@ define void @simple_write2_two_val_f64(double addrspace(1)* %C, double addrspace ; SI: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}} ; SI: ds_write2_b32 [[ZERO]], v{{[0-9]+}}, v{{[0-9]+}} offset0:0 offset1:1 define void @store_constant_adjacent_offsets() { - store i32 123, i32 addrspace(3)* getelementptr inbounds ([4 x i32] addrspace(3)* @foo, i32 0, i32 0), align 4 - store i32 123, i32 addrspace(3)* getelementptr inbounds ([4 x i32] addrspace(3)* @foo, i32 0, i32 1), align 4 + store i32 123, i32 addrspace(3)* getelementptr inbounds ([4 x i32], [4 x i32] addrspace(3)* @foo, i32 0, i32 0), align 4 + store i32 123, i32 addrspace(3)* getelementptr inbounds ([4 x i32], [4 x i32] addrspace(3)* @foo, i32 0, i32 1), align 4 ret void } @@ -336,8 +336,8 @@ define void @store_constant_adjacent_offsets() { ; SI-DAG: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}} ; SI: ds_write2_b32 [[ZERO]], [[VAL]], [[VAL]] offset0:0 offset1:2 define void @store_constant_disjoint_offsets() { - store i32 123, i32 addrspace(3)* getelementptr inbounds ([4 x i32] addrspace(3)* @foo, i32 0, i32 0), align 4 - store i32 123, i32 addrspace(3)* getelementptr inbounds ([4 x i32] addrspace(3)* @foo, i32 0, i32 2), align 4 + store i32 123, i32 addrspace(3)* getelementptr inbounds ([4 x i32], [4 x i32] addrspace(3)* @foo, i32 0, i32 0), align 4 + store i32 123, i32 addrspace(3)* getelementptr inbounds ([4 x i32], [4 x i32] addrspace(3)* @foo, i32 0, i32 2), align 4 ret void } @@ -348,8 +348,8 @@ define void @store_constant_disjoint_offsets() { ; SI: ds_write2_b32 [[ZERO]], v{{[0-9]+}}, v{{[0-9]+}} offset0:0 offset1:1 ; SI: ds_write2_b32 [[ZERO]], v{{[0-9]+}}, v{{[0-9]+}} offset0:2 offset1:3 define void @store_misaligned64_constant_offsets() { - store i64 123, i64 addrspace(3)* getelementptr inbounds ([4 x i64] addrspace(3)* @bar, i32 0, i32 0), align 4 - store i64 123, i64 addrspace(3)* getelementptr inbounds ([4 x i64] addrspace(3)* @bar, i32 0, i32 1), align 4 + store i64 123, i64 addrspace(3)* getelementptr inbounds ([4 x i64], [4 x i64] addrspace(3)* @bar, i32 0, i32 0), align 4 + store i64 123, i64 addrspace(3)* getelementptr inbounds ([4 x i64], [4 x i64] addrspace(3)* @bar, i32 0, i32 1), align 4 ret void } @@ -362,8 +362,8 @@ define void @store_misaligned64_constant_offsets() { ; SI-DAG: ds_write2_b32 [[BASE1]], v{{[0-9]+}}, v{{[0-9]+}} offset0:0 offset1:1 ; SI: s_endpgm define void @store_misaligned64_constant_large_offsets() { - store i64 123, i64 addrspace(3)* getelementptr inbounds ([4096 x i64] addrspace(3)* @bar.large, i32 0, i32 2048), align 4 - store i64 123, i64 addrspace(3)* getelementptr inbounds ([4096 x i64] addrspace(3)* @bar.large, i32 0, i32 4095), align 4 + store i64 123, i64 addrspace(3)* getelementptr inbounds ([4096 x i64], [4096 x i64] addrspace(3)* @bar.large, i32 0, i32 2048), align 4 + store i64 123, i64 addrspace(3)* getelementptr inbounds ([4096 x i64], [4096 x i64] addrspace(3)* @bar.large, i32 0, i32 4095), align 4 ret void } @@ -373,34 +373,34 @@ define void @store_misaligned64_constant_large_offsets() { define void @write2_sgemm_sequence(float addrspace(1)* %C, i32 %lda, i32 %ldb, float addrspace(1)* %in) #0 { %x.i = tail call i32 @llvm.r600.read.tgid.x() #1 %y.i = tail call i32 @llvm.r600.read.tidig.y() #1 - %val = load float addrspace(1)* %in - %arrayidx44 = getelementptr inbounds [264 x float] addrspace(3)* @sgemm.lA, i32 0, i32 %x.i + %val = load float, float addrspace(1)* %in + %arrayidx44 = getelementptr inbounds [264 x float], [264 x float] addrspace(3)* @sgemm.lA, i32 0, i32 %x.i store float %val, float addrspace(3)* %arrayidx44, align 4 %add47 = add nsw i32 %x.i, 1 - %arrayidx48 = getelementptr inbounds [264 x float] addrspace(3)* @sgemm.lA, i32 0, i32 %add47 + %arrayidx48 = getelementptr inbounds [264 x float], [264 x float] addrspace(3)* @sgemm.lA, i32 0, i32 %add47 store float %val, float addrspace(3)* %arrayidx48, align 4 %add51 = add nsw i32 %x.i, 16 - %arrayidx52 = getelementptr inbounds [264 x float] addrspace(3)* @sgemm.lA, i32 0, i32 %add51 + %arrayidx52 = getelementptr inbounds [264 x float], [264 x float] addrspace(3)* @sgemm.lA, i32 0, i32 %add51 store float %val, float addrspace(3)* %arrayidx52, align 4 %add55 = add nsw i32 %x.i, 17 - %arrayidx56 = getelementptr inbounds [264 x float] addrspace(3)* @sgemm.lA, i32 0, i32 %add55 + %arrayidx56 = getelementptr inbounds [264 x float], [264 x float] addrspace(3)* @sgemm.lA, i32 0, i32 %add55 store float %val, float addrspace(3)* %arrayidx56, align 4 - %arrayidx60 = getelementptr inbounds [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %y.i + %arrayidx60 = getelementptr inbounds [776 x float], [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %y.i store float %val, float addrspace(3)* %arrayidx60, align 4 %add63 = add nsw i32 %y.i, 1 - %arrayidx64 = getelementptr inbounds [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add63 + %arrayidx64 = getelementptr inbounds [776 x float], [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add63 store float %val, float addrspace(3)* %arrayidx64, align 4 %add67 = add nsw i32 %y.i, 32 - %arrayidx68 = getelementptr inbounds [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add67 + %arrayidx68 = getelementptr inbounds [776 x float], [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add67 store float %val, float addrspace(3)* %arrayidx68, align 4 %add71 = add nsw i32 %y.i, 33 - %arrayidx72 = getelementptr inbounds [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add71 + %arrayidx72 = getelementptr inbounds [776 x float], [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add71 store float %val, float addrspace(3)* %arrayidx72, align 4 %add75 = add nsw i32 %y.i, 64 - %arrayidx76 = getelementptr inbounds [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add75 + %arrayidx76 = getelementptr inbounds [776 x float], [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add75 store float %val, float addrspace(3)* %arrayidx76, align 4 %add79 = add nsw i32 %y.i, 65 - %arrayidx80 = getelementptr inbounds [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add79 + %arrayidx80 = getelementptr inbounds [776 x float], [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add79 store float %val, float addrspace(3)* %arrayidx80, align 4 ret void } |