forked from OSchip/llvm-project
129 lines
4.5 KiB
LLVM
129 lines
4.5 KiB
LLVM
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
; This test just checks that the compiler doesn't crash.
|
|
|
|
; FUNC-LABEL: {{^}}v32i8_to_v8i32:
|
|
define amdgpu_ps float @v32i8_to_v8i32(<32 x i8> addrspace(2)* inreg) #0 {
|
|
entry:
|
|
%1 = load <32 x i8>, <32 x i8> addrspace(2)* %0
|
|
%2 = bitcast <32 x i8> %1 to <8 x i32>
|
|
%3 = extractelement <8 x i32> %2, i32 1
|
|
%4 = icmp ne i32 %3, 0
|
|
%5 = select i1 %4, float 0.0, float 1.0
|
|
ret float %5
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}i8ptr_v16i8ptr:
|
|
; SI: s_endpgm
|
|
define amdgpu_kernel void @i8ptr_v16i8ptr(<16 x i8> addrspace(1)* %out, i8 addrspace(1)* %in) {
|
|
entry:
|
|
%0 = bitcast i8 addrspace(1)* %in to <16 x i8> addrspace(1)*
|
|
%1 = load <16 x i8>, <16 x i8> addrspace(1)* %0
|
|
store <16 x i8> %1, <16 x i8> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @f32_to_v2i16(<2 x i16> addrspace(1)* %out, float addrspace(1)* %in) nounwind {
|
|
%load = load float, float addrspace(1)* %in, align 4
|
|
%fadd32 = fadd float %load, 1.0
|
|
%bc = bitcast float %fadd32 to <2 x i16>
|
|
%add.bitcast = add <2 x i16> %bc, <i16 2, i16 2>
|
|
store <2 x i16> %add.bitcast, <2 x i16> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v2i16_to_f32(float addrspace(1)* %out, <2 x i16> addrspace(1)* %in) nounwind {
|
|
%load = load <2 x i16>, <2 x i16> addrspace(1)* %in, align 4
|
|
%add.v2i16 = add <2 x i16> %load, <i16 2, i16 2>
|
|
%bc = bitcast <2 x i16> %add.v2i16 to float
|
|
%fadd.bitcast = fadd float %bc, 1.0
|
|
store float %fadd.bitcast, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @f32_to_v2f16(<2 x half> addrspace(1)* %out, float addrspace(1)* %in) nounwind {
|
|
%load = load float, float addrspace(1)* %in, align 4
|
|
%fadd32 = fadd float %load, 1.0
|
|
%bc = bitcast float %fadd32 to <2 x half>
|
|
%add.bitcast = fadd <2 x half> %bc, <half 2.0, half 2.0>
|
|
store <2 x half> %add.bitcast, <2 x half> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v2f16_to_f32(float addrspace(1)* %out, <2 x half> addrspace(1)* %in) nounwind {
|
|
%load = load <2 x half>, <2 x half> addrspace(1)* %in, align 4
|
|
%add.v2f16 = fadd <2 x half> %load, <half 2.0, half 2.0>
|
|
%bc = bitcast <2 x half> %add.v2f16 to float
|
|
%fadd.bitcast = fadd float %bc, 1.0
|
|
store float %fadd.bitcast, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v4i8_to_i32(i32 addrspace(1)* %out, <4 x i8> addrspace(1)* %in) nounwind {
|
|
%load = load <4 x i8>, <4 x i8> addrspace(1)* %in, align 4
|
|
%bc = bitcast <4 x i8> %load to i32
|
|
store i32 %bc, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @i32_to_v4i8(<4 x i8> addrspace(1)* %out, i32 addrspace(1)* %in) nounwind {
|
|
%load = load i32, i32 addrspace(1)* %in, align 4
|
|
%bc = bitcast i32 %load to <4 x i8>
|
|
store <4 x i8> %bc, <4 x i8> addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}bitcast_v2i32_to_f64:
|
|
; SI: s_endpgm
|
|
define amdgpu_kernel void @bitcast_v2i32_to_f64(double addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
|
|
%val = load <2 x i32>, <2 x i32> addrspace(1)* %in, align 8
|
|
%add = add <2 x i32> %val, <i32 4, i32 9>
|
|
%bc = bitcast <2 x i32> %add to double
|
|
%fadd.bc = fadd double %bc, 1.0
|
|
store double %fadd.bc, double addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}bitcast_f64_to_v2i32:
|
|
; SI: s_endpgm
|
|
define amdgpu_kernel void @bitcast_f64_to_v2i32(<2 x i32> addrspace(1)* %out, double addrspace(1)* %in) {
|
|
%val = load double, double addrspace(1)* %in, align 8
|
|
%add = fadd double %val, 4.0
|
|
%bc = bitcast double %add to <2 x i32>
|
|
store <2 x i32> %bc, <2 x i32> addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}bitcast_v2i64_to_v2f64:
|
|
define amdgpu_kernel void @bitcast_v2i64_to_v2f64(i32 %cond, <2 x double> addrspace(1)* %out, <2 x i64> %value) {
|
|
entry:
|
|
%cmp0 = icmp eq i32 %cond, 0
|
|
br i1 %cmp0, label %if, label %end
|
|
|
|
if:
|
|
%cast = bitcast <2 x i64> %value to <2 x double>
|
|
br label %end
|
|
|
|
end:
|
|
%phi = phi <2 x double> [zeroinitializer, %entry], [%cast, %if]
|
|
store <2 x double> %phi, <2 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}bitcast_v2f64_to_v2i64:
|
|
define amdgpu_kernel void @bitcast_v2f64_to_v2i64(i32 %cond, <2 x i64> addrspace(1)* %out, <2 x double> %value) {
|
|
entry:
|
|
%cmp0 = icmp eq i32 %cond, 0
|
|
br i1 %cmp0, label %if, label %end
|
|
|
|
if:
|
|
%cast = bitcast <2 x double> %value to <2 x i64>
|
|
br label %end
|
|
|
|
end:
|
|
%phi = phi <2 x i64> [zeroinitializer, %entry], [%cast, %if]
|
|
store <2 x i64> %phi, <2 x i64> addrspace(1)* %out
|
|
ret void
|
|
}
|