define void @fmuladd_f32(float addrspace(1)* %out, float addrspace(1)* %in1,
float addrspace(1)* %in2, float addrspace(1)* %in3) {
- %r0 = load float addrspace(1)* %in1
- %r1 = load float addrspace(1)* %in2
- %r2 = load float addrspace(1)* %in3
+ %r0 = load float, float addrspace(1)* %in1
+ %r1 = load float, float addrspace(1)* %in2
+ %r2 = load float, float addrspace(1)* %in3
%r3 = tail call float @llvm.fmuladd.f32(float %r0, float %r1, float %r2)
store float %r3, float addrspace(1)* %out
ret void
define void @fmuladd_f64(double addrspace(1)* %out, double addrspace(1)* %in1,
double addrspace(1)* %in2, double addrspace(1)* %in3) {
- %r0 = load double addrspace(1)* %in1
- %r1 = load double addrspace(1)* %in2
- %r2 = load double addrspace(1)* %in3
+ %r0 = load double, double addrspace(1)* %in1
+ %r1 = load double, double addrspace(1)* %in2
+ %r2 = load double, double addrspace(1)* %in3
%r3 = tail call double @llvm.fmuladd.f64(double %r0, double %r1, double %r2)
store double %r3, double addrspace(1)* %out
ret void
%gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
%gep.out = getelementptr float, float addrspace(1)* %out, i32 %tid
- %r1 = load float addrspace(1)* %gep.0
- %r2 = load float addrspace(1)* %gep.1
+ %r1 = load float, float addrspace(1)* %gep.0
+ %r2 = load float, float addrspace(1)* %gep.1
%r3 = tail call float @llvm.fmuladd.f32(float 2.0, float %r1, float %r2)
store float %r3, float addrspace(1)* %gep.out
%gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
%gep.out = getelementptr float, float addrspace(1)* %out, i32 %tid
- %r1 = load float addrspace(1)* %gep.0
- %r2 = load float addrspace(1)* %gep.1
+ %r1 = load float, float addrspace(1)* %gep.0
+ %r2 = load float, float addrspace(1)* %gep.1
%r3 = tail call float @llvm.fmuladd.f32(float %r1, float 2.0, float %r2)
store float %r3, float addrspace(1)* %gep.out
%gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
%gep.out = getelementptr float, float addrspace(1)* %out, i32 %tid
- %r0 = load float addrspace(1)* %gep.0
- %r1 = load float addrspace(1)* %gep.1
+ %r0 = load float, float addrspace(1)* %gep.0
+ %r1 = load float, float addrspace(1)* %gep.1
%add.0 = fadd float %r0, %r0
%add.1 = fadd float %add.0, %r1
%gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
%gep.out = getelementptr float, float addrspace(1)* %out, i32 %tid
- %r0 = load float addrspace(1)* %gep.0
- %r1 = load float addrspace(1)* %gep.1
+ %r0 = load float, float addrspace(1)* %gep.0
+ %r1 = load float, float addrspace(1)* %gep.1
%add.0 = fadd float %r0, %r0
%add.1 = fadd float %r1, %add.0
%gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
%gep.out = getelementptr float, float addrspace(1)* %out, i32 %tid
- %r1 = load float addrspace(1)* %gep.0
- %r2 = load float addrspace(1)* %gep.1
+ %r1 = load float, float addrspace(1)* %gep.0
+ %r2 = load float, float addrspace(1)* %gep.1
%r3 = tail call float @llvm.fmuladd.f32(float -2.0, float %r1, float %r2)
store float %r3, float addrspace(1)* %gep.out
%gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
%gep.out = getelementptr float, float addrspace(1)* %out, i32 %tid
- %r1 = load float addrspace(1)* %gep.0
- %r2 = load float addrspace(1)* %gep.1
+ %r1 = load float, float addrspace(1)* %gep.0
+ %r2 = load float, float addrspace(1)* %gep.1
%r1.fneg = fsub float -0.000000e+00, %r1
%gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
%gep.out = getelementptr float, float addrspace(1)* %out, i32 %tid
- %r1 = load float addrspace(1)* %gep.0
- %r2 = load float addrspace(1)* %gep.1
+ %r1 = load float, float addrspace(1)* %gep.0
+ %r2 = load float, float addrspace(1)* %gep.1
%r1.fneg = fsub float -0.000000e+00, %r1
%gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
%gep.out = getelementptr float, float addrspace(1)* %out, i32 %tid
- %r1 = load float addrspace(1)* %gep.0
- %r2 = load float addrspace(1)* %gep.1
+ %r1 = load float, float addrspace(1)* %gep.0
+ %r2 = load float, float addrspace(1)* %gep.1
%r2.fneg = fsub float -0.000000e+00, %r2