[opaque pointer type] Add textual IR support for explicit type parameter to load...

[oota-llvm.git] / test / CodeGen / R600 / ds_read2.ll

diff --git a/test/CodeGen/R600/ds_read2.ll b/test/CodeGen/R600/ds_read2.ll
index 5901e8595cbf146f3d1d3e8f97f030d9f5b301f5..f53b6c0c023db3fed61b072ce8b7bf96324e1916 100644 (file)
--- a/test/CodeGen/R600/ds_read2.ll
+++ b/test/CodeGen/R600/ds_read2.ll
@@ -15,10 +15,10 @@
 define void @simple_read2_f32(float addrspace(1)* %out) #0 {
   %x.i = tail call i32 @llvm.r600.read.tidig.x() #1
   %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i
-  %val0 = load float addrspace(3)* %arrayidx0, align 4
+  %val0 = load float, float addrspace(3)* %arrayidx0, align 4
   %add.x = add nsw i32 %x.i, 8
   %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x
-  %val1 = load float addrspace(3)* %arrayidx1, align 4
+  %val1 = load float, float addrspace(3)* %arrayidx1, align 4
   %sum = fadd float %val0, %val1
   %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i32 %x.i
   store float %sum, float addrspace(1)* %out.gep, align 4
@@ -34,10 +34,10 @@ define void @simple_read2_f32(float addrspace(1)* %out) #0 {
 define void @simple_read2_f32_max_offset(float addrspace(1)* %out) #0 {
   %x.i = tail call i32 @llvm.r600.read.tidig.x() #1
   %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i
-  %val0 = load float addrspace(3)* %arrayidx0, align 4
+  %val0 = load float, float addrspace(3)* %arrayidx0, align 4
   %add.x = add nsw i32 %x.i, 255
   %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x
-  %val1 = load float addrspace(3)* %arrayidx1, align 4
+  %val1 = load float, float addrspace(3)* %arrayidx1, align 4
   %sum = fadd float %val0, %val1
   %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i32 %x.i
   store float %sum, float addrspace(1)* %out.gep, align 4
@@ -52,10 +52,10 @@ define void @simple_read2_f32_max_offset(float addrspace(1)* %out) #0 {
 define void @simple_read2_f32_too_far(float addrspace(1)* %out) #0 {
   %x.i = tail call i32 @llvm.r600.read.tidig.x() #1
   %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i
-  %val0 = load float addrspace(3)* %arrayidx0, align 4
+  %val0 = load float, float addrspace(3)* %arrayidx0, align 4
   %add.x = add nsw i32 %x.i, 257
   %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x
-  %val1 = load float addrspace(3)* %arrayidx1, align 4
+  %val1 = load float, float addrspace(3)* %arrayidx1, align 4
   %sum = fadd float %val0, %val1
   %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i32 %x.i
   store float %sum, float addrspace(1)* %out.gep, align 4
@@ -70,20 +70,20 @@ define void @simple_read2_f32_x2(float addrspace(1)* %out) #0 {
   %tid.x = tail call i32 @llvm.r600.read.tidig.x() #1
   %idx.0 = add nsw i32 %tid.x, 0
   %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.0
-  %val0 = load float addrspace(3)* %arrayidx0, align 4
+  %val0 = load float, float addrspace(3)* %arrayidx0, align 4
 
   %idx.1 = add nsw i32 %tid.x, 8
   %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.1
-  %val1 = load float addrspace(3)* %arrayidx1, align 4
+  %val1 = load float, float addrspace(3)* %arrayidx1, align 4
   %sum.0 = fadd float %val0, %val1
 
   %idx.2 = add nsw i32 %tid.x, 11
   %arrayidx2 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.2
-  %val2 = load float addrspace(3)* %arrayidx2, align 4
+  %val2 = load float, float addrspace(3)* %arrayidx2, align 4
 
   %idx.3 = add nsw i32 %tid.x, 27
   %arrayidx3 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.3
-  %val3 = load float addrspace(3)* %arrayidx3, align 4
+  %val3 = load float, float addrspace(3)* %arrayidx3, align 4
   %sum.1 = fadd float %val2, %val3
 
   %sum = fadd float %sum.0, %sum.1
@@ -102,22 +102,22 @@ define void @simple_read2_f32_x2_barrier(float addrspace(1)* %out) #0 {
   %tid.x = tail call i32 @llvm.r600.read.tidig.x() #1
   %idx.0 = add nsw i32 %tid.x, 0
   %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.0
-  %val0 = load float addrspace(3)* %arrayidx0, align 4
+  %val0 = load float, float addrspace(3)* %arrayidx0, align 4
 
   %idx.1 = add nsw i32 %tid.x, 8
   %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.1
-  %val1 = load float addrspace(3)* %arrayidx1, align 4
+  %val1 = load float, float addrspace(3)* %arrayidx1, align 4
   %sum.0 = fadd float %val0, %val1
 
   call void @llvm.AMDGPU.barrier.local() #2
 
   %idx.2 = add nsw i32 %tid.x, 11
   %arrayidx2 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.2
-  %val2 = load float addrspace(3)* %arrayidx2, align 4
+  %val2 = load float, float addrspace(3)* %arrayidx2, align 4
 
   %idx.3 = add nsw i32 %tid.x, 27
   %arrayidx3 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.3
-  %val3 = load float addrspace(3)* %arrayidx3, align 4
+  %val3 = load float, float addrspace(3)* %arrayidx3, align 4
   %sum.1 = fadd float %val2, %val3
 
   %sum = fadd float %sum.0, %sum.1
@@ -137,20 +137,20 @@ define void @simple_read2_f32_x2_nonzero_base(float addrspace(1)* %out) #0 {
   %tid.x = tail call i32 @llvm.r600.read.tidig.x() #1
   %idx.0 = add nsw i32 %tid.x, 2
   %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.0
-  %val0 = load float addrspace(3)* %arrayidx0, align 4
+  %val0 = load float, float addrspace(3)* %arrayidx0, align 4
 
   %idx.1 = add nsw i32 %tid.x, 8
   %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.1
-  %val1 = load float addrspace(3)* %arrayidx1, align 4
+  %val1 = load float, float addrspace(3)* %arrayidx1, align 4
   %sum.0 = fadd float %val0, %val1
 
   %idx.2 = add nsw i32 %tid.x, 11
   %arrayidx2 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.2
-  %val2 = load float addrspace(3)* %arrayidx2, align 4
+  %val2 = load float, float addrspace(3)* %arrayidx2, align 4
 
   %idx.3 = add nsw i32 %tid.x, 27
   %arrayidx3 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %idx.3
-  %val3 = load float addrspace(3)* %arrayidx3, align 4
+  %val3 = load float, float addrspace(3)* %arrayidx3, align 4
   %sum.1 = fadd float %val2, %val3
 
   %sum = fadd float %sum.0, %sum.1
@@ -177,8 +177,8 @@ define void @read2_ptr_is_subreg_arg_f32(float addrspace(1)* %out, <2 x float ad
   %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
-  %val0 = load float addrspace(3)* %gep.0, align 4
-  %val1 = load float addrspace(3)* %gep.1, align 4
+  %val0 = load float, float addrspace(3)* %gep.0, align 4
+  %val1 = load float, float addrspace(3)* %gep.1, align 4
   %add.x = add nsw i32 %x.i, 8
   %sum = fadd float %val0, %val1
   %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i32 %x.i
@@ -207,8 +207,8 @@ define void @read2_ptr_is_subreg_arg_offset_f32(float addrspace(1)* %out, <2 x f
   ; Apply an additional offset after the vector that will be more obviously folded.
   %gep.1.offset = getelementptr float, float addrspace(3)* %gep.1, i32 8
 
-  %val0 = load float addrspace(3)* %gep.0, align 4
-  %val1 = load float addrspace(3)* %gep.1.offset, align 4
+  %val0 = load float, float addrspace(3)* %gep.0, align 4
+  %val1 = load float, float addrspace(3)* %gep.1.offset, align 4
   %add.x = add nsw i32 %x.i, 8
   %sum = fadd float %val0, %val1
   %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i32 %x.i
@@ -231,8 +231,8 @@ define void @read2_ptr_is_subreg_f32(float addrspace(1)* %out) #0 {
   %gep = getelementptr inbounds [512 x float], <2 x [512 x float] addrspace(3)*> %ptr.1, <2 x i32> <i32 0, i32 0>, <2 x i32> %idx
   %gep.0 = extractelement <2 x float addrspace(3)*> %gep, i32 0
   %gep.1 = extractelement <2 x float addrspace(3)*> %gep, i32 1
-  %val0 = load float addrspace(3)* %gep.0, align 4
-  %val1 = load float addrspace(3)* %gep.1, align 4
+  %val0 = load float, float addrspace(3)* %gep.0, align 4
+  %val1 = load float, float addrspace(3)* %gep.1, align 4
   %add.x = add nsw i32 %x.i, 8
   %sum = fadd float %val0, %val1
   %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i32 %x.i
@@ -248,10 +248,10 @@ define void @read2_ptr_is_subreg_f32(float addrspace(1)* %out) #0 {
 define void @simple_read2_f32_volatile_0(float addrspace(1)* %out) #0 {
   %x.i = tail call i32 @llvm.r600.read.tidig.x() #1
   %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i
-  %val0 = load volatile float addrspace(3)* %arrayidx0, align 4
+  %val0 = load volatile float, float addrspace(3)* %arrayidx0, align 4
   %add.x = add nsw i32 %x.i, 8
   %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x
-  %val1 = load float addrspace(3)* %arrayidx1, align 4
+  %val1 = load float, float addrspace(3)* %arrayidx1, align 4
   %sum = fadd float %val0, %val1
   %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i32 %x.i
   store float %sum, float addrspace(1)* %out.gep, align 4
@@ -266,10 +266,10 @@ define void @simple_read2_f32_volatile_0(float addrspace(1)* %out) #0 {
 define void @simple_read2_f32_volatile_1(float addrspace(1)* %out) #0 {
   %x.i = tail call i32 @llvm.r600.read.tidig.x() #1
   %arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %x.i
-  %val0 = load float addrspace(3)* %arrayidx0, align 4
+  %val0 = load float, float addrspace(3)* %arrayidx0, align 4
   %add.x = add nsw i32 %x.i, 8
   %arrayidx1 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %add.x
-  %val1 = load volatile float addrspace(3)* %arrayidx1, align 4
+  %val1 = load volatile float, float addrspace(3)* %arrayidx1, align 4
   %sum = fadd float %val0, %val1
   %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i32 %x.i
   store float %sum, float addrspace(1)* %out.gep, align 4
@@ -285,10 +285,10 @@ define void @simple_read2_f32_volatile_1(float addrspace(1)* %out) #0 {
 define void @unaligned_read2_f32(float addrspace(1)* %out, float addrspace(3)* %lds) #0 {
   %x.i = tail call i32 @llvm.r600.read.tidig.x() #1
   %arrayidx0 = getelementptr inbounds float, float addrspace(3)* %lds, i32 %x.i
-  %val0 = load float addrspace(3)* %arrayidx0, align 1
+  %val0 = load float, float addrspace(3)* %arrayidx0, align 1
   %add.x = add nsw i32 %x.i, 8
   %arrayidx1 = getelementptr inbounds float, float addrspace(3)* %lds, i32 %add.x
-  %val1 = load float addrspace(3)* %arrayidx1, align 1
+  %val1 = load float, float addrspace(3)* %arrayidx1, align 1
   %sum = fadd float %val0, %val1
   %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i32 %x.i
   store float %sum, float addrspace(1)* %out.gep, align 4
@@ -301,10 +301,10 @@ define void @unaligned_read2_f32(float addrspace(1)* %out, float addrspace(3)* %
 define void @misaligned_2_simple_read2_f32(float addrspace(1)* %out, float addrspace(3)* %lds) #0 {
   %x.i = tail call i32 @llvm.r600.read.tidig.x() #1
   %arrayidx0 = getelementptr inbounds float, float addrspace(3)* %lds, i32 %x.i
-  %val0 = load float addrspace(3)* %arrayidx0, align 2
+  %val0 = load float, float addrspace(3)* %arrayidx0, align 2
   %add.x = add nsw i32 %x.i, 8
   %arrayidx1 = getelementptr inbounds float, float addrspace(3)* %lds, i32 %add.x
-  %val1 = load float addrspace(3)* %arrayidx1, align 2
+  %val1 = load float, float addrspace(3)* %arrayidx1, align 2
   %sum = fadd float %val0, %val1
   %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i32 %x.i
   store float %sum, float addrspace(1)* %out.gep, align 4
@@ -320,10 +320,10 @@ define void @misaligned_2_simple_read2_f32(float addrspace(1)* %out, float addrs
 define void @simple_read2_f64(double addrspace(1)* %out) #0 {
   %x.i = tail call i32 @llvm.r600.read.tidig.x() #1
   %arrayidx0 = getelementptr inbounds [512 x double], [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %x.i
-  %val0 = load double addrspace(3)* %arrayidx0, align 8
+  %val0 = load double, double addrspace(3)* %arrayidx0, align 8
   %add.x = add nsw i32 %x.i, 8
   %arrayidx1 = getelementptr inbounds [512 x double], [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %add.x
-  %val1 = load double addrspace(3)* %arrayidx1, align 8
+  %val1 = load double, double addrspace(3)* %arrayidx1, align 8
   %sum = fadd double %val0, %val1
   %out.gep = getelementptr inbounds double, double addrspace(1)* %out, i32 %x.i
   store double %sum, double addrspace(1)* %out.gep, align 8
@@ -336,10 +336,10 @@ define void @simple_read2_f64(double addrspace(1)* %out) #0 {
 define void @simple_read2_f64_max_offset(double addrspace(1)* %out) #0 {
   %x.i = tail call i32 @llvm.r600.read.tidig.x() #1
   %arrayidx0 = getelementptr inbounds [512 x double], [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %x.i
-  %val0 = load double addrspace(3)* %arrayidx0, align 8
+  %val0 = load double, double addrspace(3)* %arrayidx0, align 8
   %add.x = add nsw i32 %x.i, 255
   %arrayidx1 = getelementptr inbounds [512 x double], [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %add.x
-  %val1 = load double addrspace(3)* %arrayidx1, align 8
+  %val1 = load double, double addrspace(3)* %arrayidx1, align 8
   %sum = fadd double %val0, %val1
   %out.gep = getelementptr inbounds double, double addrspace(1)* %out, i32 %x.i
   store double %sum, double addrspace(1)* %out.gep, align 8
@@ -354,10 +354,10 @@ define void @simple_read2_f64_max_offset(double addrspace(1)* %out) #0 {
 define void @simple_read2_f64_too_far(double addrspace(1)* %out) #0 {
   %x.i = tail call i32 @llvm.r600.read.tidig.x() #1
   %arrayidx0 = getelementptr inbounds [512 x double], [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %x.i
-  %val0 = load double addrspace(3)* %arrayidx0, align 8
+  %val0 = load double, double addrspace(3)* %arrayidx0, align 8
   %add.x = add nsw i32 %x.i, 257
   %arrayidx1 = getelementptr inbounds [512 x double], [512 x double] addrspace(3)* @lds.f64, i32 0, i32 %add.x
-  %val1 = load double addrspace(3)* %arrayidx1, align 8
+  %val1 = load double, double addrspace(3)* %arrayidx1, align 8
   %sum = fadd double %val0, %val1
   %out.gep = getelementptr inbounds double, double addrspace(1)* %out, i32 %x.i
   store double %sum, double addrspace(1)* %out.gep, align 8
@@ -372,10 +372,10 @@ define void @simple_read2_f64_too_far(double addrspace(1)* %out) #0 {
 define void @misaligned_read2_f64(double addrspace(1)* %out, double addrspace(3)* %lds) #0 {
   %x.i = tail call i32 @llvm.r600.read.tidig.x() #1
   %arrayidx0 = getelementptr inbounds double, double addrspace(3)* %lds, i32 %x.i
-  %val0 = load double addrspace(3)* %arrayidx0, align 4
+  %val0 = load double, double addrspace(3)* %arrayidx0, align 4
   %add.x = add nsw i32 %x.i, 7
   %arrayidx1 = getelementptr inbounds double, double addrspace(3)* %lds, i32 %add.x
-  %val1 = load double addrspace(3)* %arrayidx1, align 4
+  %val1 = load double, double addrspace(3)* %arrayidx1, align 4
   %sum = fadd double %val0, %val1
   %out.gep = getelementptr inbounds double, double addrspace(1)* %out, i32 %x.i
   store double %sum, double addrspace(1)* %out.gep, align 4
@@ -388,8 +388,8 @@ define void @misaligned_read2_f64(double addrspace(1)* %out, double addrspace(3)
 ; SI: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}}
 ; SI: ds_read2_b32 v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]] offset0:0 offset1:1
 define void @load_constant_adjacent_offsets(i32 addrspace(1)* %out) {
-  %val0 = load i32 addrspace(3)* getelementptr inbounds ([4 x i32] addrspace(3)* @foo, i32 0, i32 0), align 4
-  %val1 = load i32 addrspace(3)* getelementptr inbounds ([4 x i32] addrspace(3)* @foo, i32 0, i32 1), align 4
+  %val0 = load i32, i32 addrspace(3)* getelementptr inbounds ([4 x i32] addrspace(3)* @foo, i32 0, i32 0), align 4
+  %val1 = load i32, i32 addrspace(3)* getelementptr inbounds ([4 x i32] addrspace(3)* @foo, i32 0, i32 1), align 4
   %sum = add i32 %val0, %val1
   store i32 %sum, i32 addrspace(1)* %out, align 4
   ret void
@@ -399,8 +399,8 @@ define void @load_constant_adjacent_offsets(i32 addrspace(1)* %out) {
 ; SI: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}}
 ; SI: ds_read2_b32 v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]] offset0:0 offset1:2
 define void @load_constant_disjoint_offsets(i32 addrspace(1)* %out) {
-  %val0 = load i32 addrspace(3)* getelementptr inbounds ([4 x i32] addrspace(3)* @foo, i32 0, i32 0), align 4
-  %val1 = load i32 addrspace(3)* getelementptr inbounds ([4 x i32] addrspace(3)* @foo, i32 0, i32 2), align 4
+  %val0 = load i32, i32 addrspace(3)* getelementptr inbounds ([4 x i32] addrspace(3)* @foo, i32 0, i32 0), align 4
+  %val1 = load i32, i32 addrspace(3)* getelementptr inbounds ([4 x i32] addrspace(3)* @foo, i32 0, i32 2), align 4
   %sum = add i32 %val0, %val1
   store i32 %sum, i32 addrspace(1)* %out, align 4
   ret void
@@ -413,8 +413,8 @@ define void @load_constant_disjoint_offsets(i32 addrspace(1)* %out) {
 ; SI: ds_read2_b32 v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]] offset0:0 offset1:1
 ; SI: ds_read2_b32 v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]] offset0:2 offset1:3
 define void @load_misaligned64_constant_offsets(i64 addrspace(1)* %out) {
-  %val0 = load i64 addrspace(3)* getelementptr inbounds ([4 x i64] addrspace(3)* @bar, i32 0, i32 0), align 4
-  %val1 = load i64 addrspace(3)* getelementptr inbounds ([4 x i64] addrspace(3)* @bar, i32 0, i32 1), align 4
+  %val0 = load i64, i64 addrspace(3)* getelementptr inbounds ([4 x i64] addrspace(3)* @bar, i32 0, i32 0), align 4
+  %val1 = load i64, i64 addrspace(3)* getelementptr inbounds ([4 x i64] addrspace(3)* @bar, i32 0, i32 1), align 4
   %sum = add i64 %val0, %val1
   store i64 %sum, i64 addrspace(1)* %out, align 8
   ret void
@@ -429,8 +429,8 @@ define void @load_misaligned64_constant_offsets(i64 addrspace(1)* %out) {
 ; SI-DAG: ds_read2_b32 v{{\[[0-9]+:[0-9]+\]}}, [[BASE1]] offset0:0 offset1:1
 ; SI: s_endpgm
 define void @load_misaligned64_constant_large_offsets(i64 addrspace(1)* %out) {
-  %val0 = load i64 addrspace(3)* getelementptr inbounds ([4096 x i64] addrspace(3)* @bar.large, i32 0, i32 2048), align 4
-  %val1 = load i64 addrspace(3)* getelementptr inbounds ([4096 x i64] addrspace(3)* @bar.large, i32 0, i32 4095), align 4
+  %val0 = load i64, i64 addrspace(3)* getelementptr inbounds ([4096 x i64] addrspace(3)* @bar.large, i32 0, i32 2048), align 4
+  %val1 = load i64, i64 addrspace(3)* getelementptr inbounds ([4096 x i64] addrspace(3)* @bar.large, i32 0, i32 4095), align 4
   %sum = add i64 %val0, %val1
   store i64 %sum, i64 addrspace(1)* %out, align 8
   ret void
@@ -443,33 +443,33 @@ define void @sgemm_inner_loop_read2_sequence(float addrspace(1)* %C, i32 %lda, i
   %x.i = tail call i32 @llvm.r600.read.tgid.x() #1
   %y.i = tail call i32 @llvm.r600.read.tidig.y() #1
   %arrayidx44 = getelementptr inbounds [264 x float], [264 x float] addrspace(3)* @sgemm.lA, i32 0, i32 %x.i
-  %tmp16 = load float addrspace(3)* %arrayidx44, align 4
+  %tmp16 = load float, float addrspace(3)* %arrayidx44, align 4
   %add47 = add nsw i32 %x.i, 1
   %arrayidx48 = getelementptr inbounds [264 x float], [264 x float] addrspace(3)* @sgemm.lA, i32 0, i32 %add47
-  %tmp17 = load float addrspace(3)* %arrayidx48, align 4
+  %tmp17 = load float, float addrspace(3)* %arrayidx48, align 4
   %add51 = add nsw i32 %x.i, 16
   %arrayidx52 = getelementptr inbounds [264 x float], [264 x float] addrspace(3)* @sgemm.lA, i32 0, i32 %add51
-  %tmp18 = load float addrspace(3)* %arrayidx52, align 4
+  %tmp18 = load float, float addrspace(3)* %arrayidx52, align 4
   %add55 = add nsw i32 %x.i, 17
   %arrayidx56 = getelementptr inbounds [264 x float], [264 x float] addrspace(3)* @sgemm.lA, i32 0, i32 %add55
-  %tmp19 = load float addrspace(3)* %arrayidx56, align 4
+  %tmp19 = load float, float addrspace(3)* %arrayidx56, align 4
   %arrayidx60 = getelementptr inbounds [776 x float], [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %y.i
-  %tmp20 = load float addrspace(3)* %arrayidx60, align 4
+  %tmp20 = load float, float addrspace(3)* %arrayidx60, align 4
   %add63 = add nsw i32 %y.i, 1
   %arrayidx64 = getelementptr inbounds [776 x float], [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add63
-  %tmp21 = load float addrspace(3)* %arrayidx64, align 4
+  %tmp21 = load float, float addrspace(3)* %arrayidx64, align 4
   %add67 = add nsw i32 %y.i, 32
   %arrayidx68 = getelementptr inbounds [776 x float], [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add67
-  %tmp22 = load float addrspace(3)* %arrayidx68, align 4
+  %tmp22 = load float, float addrspace(3)* %arrayidx68, align 4
   %add71 = add nsw i32 %y.i, 33
   %arrayidx72 = getelementptr inbounds [776 x float], [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add71
-  %tmp23 = load float addrspace(3)* %arrayidx72, align 4
+  %tmp23 = load float, float addrspace(3)* %arrayidx72, align 4
   %add75 = add nsw i32 %y.i, 64
   %arrayidx76 = getelementptr inbounds [776 x float], [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add75
-  %tmp24 = load float addrspace(3)* %arrayidx76, align 4
+  %tmp24 = load float, float addrspace(3)* %arrayidx76, align 4
   %add79 = add nsw i32 %y.i, 65
   %arrayidx80 = getelementptr inbounds [776 x float], [776 x float] addrspace(3)* @sgemm.lB, i32 0, i32 %add79
-  %tmp25 = load float addrspace(3)* %arrayidx80, align 4
+  %tmp25 = load float, float addrspace(3)* %arrayidx80, align 4
   %sum.0 = fadd float %tmp16, %tmp17
   %sum.1 = fadd float %sum.0, %tmp18
   %sum.2 = fadd float %sum.1, %tmp19
@@ -484,13 +484,13 @@ define void @sgemm_inner_loop_read2_sequence(float addrspace(1)* %C, i32 %lda, i
 }
 
 define void @misaligned_read2_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(3)* %in) #0 {
-  %load = load <2 x i32> addrspace(3)* %in, align 4
+  %load = load <2 x i32>, <2 x i32> addrspace(3)* %in, align 4
   store <2 x i32> %load, <2 x i32> addrspace(1)* %out, align 8
   ret void
 }
 
 define void @misaligned_read2_i64(i64 addrspace(1)* %out, i64 addrspace(3)* %in) #0 {
-  %load = load i64 addrspace(3)* %in, align 4
+  %load = load i64, i64 addrspace(3)* %in, align 4
   store i64 %load, i64 addrspace(1)* %out, align 8
   ret void
 }