summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--llvm/include/llvm/IR/IntrinsicsAMDGPU.td95
-rw-r--r--llvm/lib/Target/AMDGPU/SIInstructions.td136
-rw-r--r--llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.gather4.ll364
-rw-r--r--llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.getlod.ll37
-rw-r--r--llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.ll208
-rw-r--r--llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.o.ll208
6 files changed, 1045 insertions, 3 deletions
diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
index 7163d0e70fa..a0a031230f3 100644
--- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -257,6 +257,101 @@ class AMDGPUImageStore : Intrinsic <
def int_amdgcn_image_store : AMDGPUImageStore;
def int_amdgcn_image_store_mip : AMDGPUImageStore;
+class AMDGPUImageSample : Intrinsic <
+ [llvm_anyfloat_ty], // vdata(VGPR)
+ [llvm_anyfloat_ty, // vaddr(VGPR)
+ llvm_anyint_ty, // rsrc(SGPR)
+ llvm_v4i32_ty, // sampler(SGPR)
+ llvm_i32_ty, // dmask(imm)
+ llvm_i1_ty, // unorm(imm)
+ llvm_i1_ty, // glc(imm)
+ llvm_i1_ty, // slc(imm)
+ llvm_i1_ty, // lwe(imm)
+ llvm_i1_ty], // da(imm)
+ [IntrReadMem]>;
+
+// Basic sample
+def int_amdgcn_image_sample : AMDGPUImageSample;
+def int_amdgcn_image_sample_cl : AMDGPUImageSample;
+def int_amdgcn_image_sample_d : AMDGPUImageSample;
+def int_amdgcn_image_sample_d_cl : AMDGPUImageSample;
+def int_amdgcn_image_sample_l : AMDGPUImageSample;
+def int_amdgcn_image_sample_b : AMDGPUImageSample;
+def int_amdgcn_image_sample_b_cl : AMDGPUImageSample;
+def int_amdgcn_image_sample_lz : AMDGPUImageSample;
+def int_amdgcn_image_sample_cd : AMDGPUImageSample;
+def int_amdgcn_image_sample_cd_cl : AMDGPUImageSample;
+
+// Sample with comparison
+def int_amdgcn_image_sample_c : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_cl : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_d : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_d_cl : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_l : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_b : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_b_cl : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_lz : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_cd : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_cd_cl : AMDGPUImageSample;
+
+// Sample with offsets
+def int_amdgcn_image_sample_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_cl_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_d_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_d_cl_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_l_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_b_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_b_cl_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_lz_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_cd_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_cd_cl_o : AMDGPUImageSample;
+
+// Sample with comparison and offsets
+def int_amdgcn_image_sample_c_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_cl_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_d_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_d_cl_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_l_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_b_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_b_cl_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_lz_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_cd_o : AMDGPUImageSample;
+def int_amdgcn_image_sample_c_cd_cl_o : AMDGPUImageSample;
+
+// Basic gather4
+def int_amdgcn_image_gather4 : AMDGPUImageSample;
+def int_amdgcn_image_gather4_cl : AMDGPUImageSample;
+def int_amdgcn_image_gather4_l : AMDGPUImageSample;
+def int_amdgcn_image_gather4_b : AMDGPUImageSample;
+def int_amdgcn_image_gather4_b_cl : AMDGPUImageSample;
+def int_amdgcn_image_gather4_lz : AMDGPUImageSample;
+
+// Gather4 with comparison
+def int_amdgcn_image_gather4_c : AMDGPUImageSample;
+def int_amdgcn_image_gather4_c_cl : AMDGPUImageSample;
+def int_amdgcn_image_gather4_c_l : AMDGPUImageSample;
+def int_amdgcn_image_gather4_c_b : AMDGPUImageSample;
+def int_amdgcn_image_gather4_c_b_cl : AMDGPUImageSample;
+def int_amdgcn_image_gather4_c_lz : AMDGPUImageSample;
+
+// Gather4 with offsets
+def int_amdgcn_image_gather4_o : AMDGPUImageSample;
+def int_amdgcn_image_gather4_cl_o : AMDGPUImageSample;
+def int_amdgcn_image_gather4_l_o : AMDGPUImageSample;
+def int_amdgcn_image_gather4_b_o : AMDGPUImageSample;
+def int_amdgcn_image_gather4_b_cl_o : AMDGPUImageSample;
+def int_amdgcn_image_gather4_lz_o : AMDGPUImageSample;
+
+// Gather4 with comparison and offsets
+def int_amdgcn_image_gather4_c_o : AMDGPUImageSample;
+def int_amdgcn_image_gather4_c_cl_o : AMDGPUImageSample;
+def int_amdgcn_image_gather4_c_l_o : AMDGPUImageSample;
+def int_amdgcn_image_gather4_c_b_o : AMDGPUImageSample;
+def int_amdgcn_image_gather4_c_b_cl_o : AMDGPUImageSample;
+def int_amdgcn_image_gather4_c_lz_o : AMDGPUImageSample;
+
+def int_amdgcn_image_getlod : AMDGPUImageSample;
+
class AMDGPUImageAtomic : Intrinsic <
[llvm_i32_ty],
[llvm_i32_ty, // vdata(VGPR)
diff --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td
index fcd3cb19dbe..e9c3e46a9d7 100644
--- a/llvm/lib/Target/AMDGPU/SIInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -2440,6 +2440,31 @@ multiclass SampleRawPatterns<SDPatternOperator name, string opcode> {
def : SampleRawPattern<name, !cast<MIMG>(opcode # _V4_V16), v16i32>;
}
+
+// Image + sampler for amdgcn
+// TODO:
+// 1. Handle half data type like v4f16, and add D16 bit support;
+// 2. Handle v4i32 rsrc type (Register Class for the instruction to be SReg_128).
+// 3. Add A16 support when we pass address of half type.
+multiclass AMDGCNSamplePattern<SDPatternOperator name, MIMG opcode, ValueType vt> {
+ def : Pat<
+ (v4f32 (name vt:$addr, v8i32:$rsrc, v4i32:$sampler, i32:$dmask, i1:$unorm, i1:$glc,
+ i1:$slc, i1:$lwe, i1:$da)),
+ (opcode $addr, $rsrc, $sampler,
+ (as_i32imm $dmask), (as_i1imm $unorm), (as_i1imm $glc), (as_i1imm $slc),
+ 0, 0, (as_i1imm $lwe), (as_i1imm $da))
+ >;
+}
+
+multiclass AMDGCNSamplePatterns<SDPatternOperator name, string opcode> {
+ defm : AMDGCNSamplePattern<name, !cast<MIMG>(opcode # _V4_V1), f32>;
+ defm : AMDGCNSamplePattern<name, !cast<MIMG>(opcode # _V4_V2), v2f32>;
+ defm : AMDGCNSamplePattern<name, !cast<MIMG>(opcode # _V4_V4), v4f32>;
+ defm : AMDGCNSamplePattern<name, !cast<MIMG>(opcode # _V4_V8), v8f32>;
+ defm : AMDGCNSamplePattern<name, !cast<MIMG>(opcode # _V4_V16), v16f32>;
+}
+
+
// Image only
class ImagePattern<SDPatternOperator name, MIMG opcode, ValueType vt> : Pat <
(name vt:$addr, v8i32:$rsrc, imm:$dmask, imm:$unorm,
@@ -2503,6 +2528,13 @@ class ImageAtomicCmpSwapPattern<MIMG opcode, ValueType vt> : Pat <
sub0)
>;
+// ======= SI Image Intrinsics ================
+
+// Image load
+defm : ImagePatterns<int_SI_image_load, "IMAGE_LOAD">;
+defm : ImagePatterns<int_SI_image_load_mip, "IMAGE_LOAD_MIP">;
+def : ImagePattern<int_SI_getresinfo, IMAGE_GET_RESINFO_V4_V1, i32>;
+
// Basic sample
defm : SampleRawPatterns<int_SI_image_sample, "IMAGE_SAMPLE">;
defm : SampleRawPatterns<int_SI_image_sample_cl, "IMAGE_SAMPLE_CL">;
@@ -2596,13 +2628,111 @@ def : SampleRawPattern<int_SI_getlod, IMAGE_GET_LOD_V4_V1, i32>;
def : SampleRawPattern<int_SI_getlod, IMAGE_GET_LOD_V4_V2, v2i32>;
def : SampleRawPattern<int_SI_getlod, IMAGE_GET_LOD_V4_V4, v4i32>;
-def : ImagePattern<int_SI_getresinfo, IMAGE_GET_RESINFO_V4_V1, i32>;
-defm : ImagePatterns<int_SI_image_load, "IMAGE_LOAD">;
-defm : ImagePatterns<int_SI_image_load_mip, "IMAGE_LOAD_MIP">;
+
+// ======= amdgcn Image Intrinsics ==============
+
+// Image load
defm : ImageLoadPatterns<int_amdgcn_image_load, "IMAGE_LOAD">;
defm : ImageLoadPatterns<int_amdgcn_image_load_mip, "IMAGE_LOAD_MIP">;
+
+// Image store
defm : ImageStorePatterns<int_amdgcn_image_store, "IMAGE_STORE">;
defm : ImageStorePatterns<int_amdgcn_image_store_mip, "IMAGE_STORE_MIP">;
+
+// Basic sample
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample, "IMAGE_SAMPLE">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_cl, "IMAGE_SAMPLE_CL">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_d, "IMAGE_SAMPLE_D">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_d_cl, "IMAGE_SAMPLE_D_CL">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_l, "IMAGE_SAMPLE_L">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_b, "IMAGE_SAMPLE_B">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_b_cl, "IMAGE_SAMPLE_B_CL">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_lz, "IMAGE_SAMPLE_LZ">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_cd, "IMAGE_SAMPLE_CD">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_cd_cl, "IMAGE_SAMPLE_CD_CL">;
+
+// Sample with comparison
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c, "IMAGE_SAMPLE_C">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_cl, "IMAGE_SAMPLE_C_CL">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_d, "IMAGE_SAMPLE_C_D">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_d_cl, "IMAGE_SAMPLE_C_D_CL">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_l, "IMAGE_SAMPLE_C_L">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_b, "IMAGE_SAMPLE_C_B">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_b_cl, "IMAGE_SAMPLE_C_B_CL">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_lz, "IMAGE_SAMPLE_C_LZ">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_cd, "IMAGE_SAMPLE_C_CD">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_cd_cl, "IMAGE_SAMPLE_C_CD_CL">;
+
+// Sample with offsets
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_o, "IMAGE_SAMPLE_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_cl_o, "IMAGE_SAMPLE_CL_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_d_o, "IMAGE_SAMPLE_D_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_d_cl_o, "IMAGE_SAMPLE_D_CL_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_l_o, "IMAGE_SAMPLE_L_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_b_o, "IMAGE_SAMPLE_B_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_b_cl_o, "IMAGE_SAMPLE_B_CL_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_lz_o, "IMAGE_SAMPLE_LZ_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_cd_o, "IMAGE_SAMPLE_CD_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_cd_cl_o, "IMAGE_SAMPLE_CD_CL_O">;
+
+// Sample with comparison and offsets
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_o, "IMAGE_SAMPLE_C_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_cl_o, "IMAGE_SAMPLE_C_CL_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_d_o, "IMAGE_SAMPLE_C_D_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_d_cl_o, "IMAGE_SAMPLE_C_D_CL_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_l_o, "IMAGE_SAMPLE_C_L_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_b_o, "IMAGE_SAMPLE_C_B_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_b_cl_o, "IMAGE_SAMPLE_C_B_CL_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_lz_o, "IMAGE_SAMPLE_C_LZ_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_cd_o, "IMAGE_SAMPLE_C_CD_O">;
+defm : AMDGCNSamplePatterns<int_amdgcn_image_sample_c_cd_cl_o, "IMAGE_SAMPLE_C_CD_CL_O">;
+
+// Gather opcodes
+// Only the variants which make sense are defined.
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4, IMAGE_GATHER4_V4_V2, v2f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4, IMAGE_GATHER4_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_cl, IMAGE_GATHER4_CL_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_l, IMAGE_GATHER4_L_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_b, IMAGE_GATHER4_B_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_b_cl, IMAGE_GATHER4_B_CL_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_b_cl, IMAGE_GATHER4_B_CL_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_lz, IMAGE_GATHER4_LZ_V4_V2, v2f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_lz, IMAGE_GATHER4_LZ_V4_V4, v4f32>;
+
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c, IMAGE_GATHER4_C_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_cl, IMAGE_GATHER4_C_CL_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_cl, IMAGE_GATHER4_C_CL_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_l, IMAGE_GATHER4_C_L_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_l, IMAGE_GATHER4_C_L_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_b, IMAGE_GATHER4_C_B_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_b, IMAGE_GATHER4_C_B_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_b_cl, IMAGE_GATHER4_C_B_CL_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_lz, IMAGE_GATHER4_C_LZ_V4_V4, v4f32>;
+
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_o, IMAGE_GATHER4_O_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_cl_o, IMAGE_GATHER4_CL_O_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_cl_o, IMAGE_GATHER4_CL_O_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_l_o, IMAGE_GATHER4_L_O_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_l_o, IMAGE_GATHER4_L_O_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_b_o, IMAGE_GATHER4_B_O_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_b_o, IMAGE_GATHER4_B_O_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_b_cl_o, IMAGE_GATHER4_B_CL_O_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_lz_o, IMAGE_GATHER4_LZ_O_V4_V4, v4f32>;
+
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_o, IMAGE_GATHER4_C_O_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_o, IMAGE_GATHER4_C_O_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_cl_o, IMAGE_GATHER4_C_CL_O_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_l_o, IMAGE_GATHER4_C_L_O_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_b_o, IMAGE_GATHER4_C_B_O_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_b_cl_o, IMAGE_GATHER4_C_B_CL_O_V4_V8, v8f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_lz_o, IMAGE_GATHER4_C_LZ_O_V4_V4, v4f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_gather4_c_lz_o, IMAGE_GATHER4_C_LZ_O_V4_V8, v8f32>;
+
+defm : AMDGCNSamplePattern<int_amdgcn_image_getlod, IMAGE_GET_LOD_V4_V1, f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_getlod, IMAGE_GET_LOD_V4_V2, v2f32>;
+defm : AMDGCNSamplePattern<int_amdgcn_image_getlod, IMAGE_GET_LOD_V4_V4, v4f32>;
+
+// Image atomics
defm : ImageAtomicPatterns<int_amdgcn_image_atomic_swap, "IMAGE_ATOMIC_SWAP">;
def : ImageAtomicCmpSwapPattern<IMAGE_ATOMIC_CMPSWAP_V1, i32>;
def : ImageAtomicCmpSwapPattern<IMAGE_ATOMIC_CMPSWAP_V2, v2i32>;
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.gather4.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.gather4.ll
new file mode 100644
index 00000000000..854793e22c2
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.gather4.ll
@@ -0,0 +1,364 @@
+; RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=GCN %s
+; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck --check-prefix=GCN %s
+
+; GCN-LABEL: {{^}}gather4_v2:
+; GCN: image_gather4 {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_v2(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.v4f32.v2f32.v8i32(<2 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4:
+; GCN: image_gather4 {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_cl:
+; GCN: image_gather4_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.cl.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_l:
+; GCN: image_gather4_l {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_l(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.l.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_b:
+; GCN: image_gather4_b {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_b(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.b.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_b_cl:
+; GCN: image_gather4_b_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_b_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.b.cl.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_b_cl_v8:
+; GCN: image_gather4_b_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_b_cl_v8(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.b.cl.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_lz_v2:
+; GCN: image_gather4_lz {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_lz_v2(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.lz.v4f32.v2f32.v8i32(<2 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_lz:
+; GCN: image_gather4_lz {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_lz(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.lz.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+
+
+; GCN-LABEL: {{^}}gather4_o:
+; GCN: image_gather4_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_o(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_cl_o:
+; GCN: image_gather4_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_cl_o(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.cl.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_cl_o_v8:
+; GCN: image_gather4_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_cl_o_v8(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.cl.o.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_l_o:
+; GCN: image_gather4_l_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_l_o(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.l.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_l_o_v8:
+; GCN: image_gather4_l_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_l_o_v8(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.l.o.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_b_o:
+; GCN: image_gather4_b_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_b_o(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.b.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_b_o_v8:
+; GCN: image_gather4_b_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_b_o_v8(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.b.o.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_b_cl_o:
+; GCN: image_gather4_b_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_b_cl_o(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.b.cl.o.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_lz_o:
+; GCN: image_gather4_lz_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_lz_o(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.lz.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+
+; GCN-LABEL: {{^}}gather4_c:
+; GCN: image_gather4_c {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_cl:
+; GCN: image_gather4_c_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.cl.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_cl_v8:
+; GCN: image_gather4_c_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_cl_v8(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.cl.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_l:
+; GCN: image_gather4_c_l {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_l(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.l.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_l_v8:
+; GCN: image_gather4_c_l {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_l_v8(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.l.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_b:
+; GCN: image_gather4_c_b {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_b(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.b.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_b_v8:
+; GCN: image_gather4_c_b {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_b_v8(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.b.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_b_cl:
+; GCN: image_gather4_c_b_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_b_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.b.cl.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_lz:
+; GCN: image_gather4_c_lz {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_lz(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.lz.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+
+; GCN-LABEL: {{^}}gather4_c_o:
+; GCN: image_gather4_c_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_o(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_o_v8:
+; GCN: image_gather4_c_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_o_v8(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.o.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_cl_o:
+; GCN: image_gather4_c_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_cl_o(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.cl.o.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_l_o:
+; GCN: image_gather4_c_l_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_l_o(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.l.o.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_b_o:
+; GCN: image_gather4_c_b_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_b_o(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.b.o.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_b_cl_o:
+; GCN: image_gather4_c_b_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_b_cl_o(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.b.cl.o.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_lz_o:
+; GCN: image_gather4_c_lz_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_lz_o(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.lz.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}gather4_c_lz_o_v8:
+; GCN: image_gather4_c_lz_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x1 da
+define void @gather4_c_lz_o_v8(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.gather4.c.lz.o.v4f32.v8f32.v8i32(<8 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 1, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+
+declare <4 x float> @llvm.amdgcn.image.gather4.v4f32.v2f32.v8i32(<2 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.cl.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.l.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.b.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.b.cl.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.b.cl.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.lz.v4f32.v2f32.v8i32(<2 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.lz.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+
+declare <4 x float> @llvm.amdgcn.image.gather4.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.cl.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.cl.o.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.l.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.l.o.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.b.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.b.o.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.b.cl.o.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.lz.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+
+declare <4 x float> @llvm.amdgcn.image.gather4.c.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.cl.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.cl.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.l.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.l.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.b.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.b.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.b.cl.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.lz.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+
+declare <4 x float> @llvm.amdgcn.image.gather4.c.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.o.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.cl.o.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.l.o.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.b.o.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.b.cl.o.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.lz.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.gather4.c.lz.o.v4f32.v8f32.v8i32(<8 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+
+
+attributes #0 = { nounwind readnone }
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.getlod.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.getlod.ll
new file mode 100644
index 00000000000..ef810a33001
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.getlod.ll
@@ -0,0 +1,37 @@
+; RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=GCN %s
+; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck --check-prefix=GCN %s
+
+; GCN-LABEL: {{^}}getlod:
+; GCN: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf da
+define void @getlod(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.getlod.v4f32.f32.v8i32(float undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}getlod_v2:
+; GCN: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf da
+define void @getlod_v2(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.getlod.v4f32.v2f32.v8i32(<2 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}getlod_v4:
+; GCN: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf da
+define void @getlod_v4(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.getlod.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 1)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+
+declare <4 x float> @llvm.amdgcn.image.getlod.v4f32.f32.v8i32(float, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.getlod.v4f32.v2f32.v8i32(<2 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.getlod.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+
+
+attributes #0 = { nounwind readnone }
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.ll
new file mode 100644
index 00000000000..7a1ef0bf986
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.ll
@@ -0,0 +1,208 @@
+; RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=GCN %s
+; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck --check-prefix=GCN %s
+
+; GCN-LABEL: {{^}}sample:
+; GCN: image_sample {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_cl:
+; GCN: image_sample_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.cl.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_d:
+; GCN: image_sample_d {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_d(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.d.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_d_cl:
+; GCN: image_sample_d_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_d_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.d.cl.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_l:
+; GCN: image_sample_l {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_l(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.l.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_b:
+; GCN: image_sample_b {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_b(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.b.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_b_cl:
+; GCN: image_sample_b_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_b_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.b.cl.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_lz:
+; GCN: image_sample_lz {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_lz(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.lz.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_cd:
+; GCN: image_sample_cd {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_cd(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.cd.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_cd_cl:
+; GCN: image_sample_cd_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_cd_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.cd.cl.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c:
+; GCN: image_sample_c {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_cl:
+; GCN: image_sample_c_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.cl.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_d:
+; GCN: image_sample_c_d {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_d(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.d.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_d_cl:
+; GCN: image_sample_c_d_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_d_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.d.cl.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_l:
+; GCN: image_sample_c_l {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_l(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.l.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_b:
+; GCN: image_sample_c_b {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_b(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.b.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_b_cl:
+; GCN: image_sample_c_b_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_b_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.b.cl.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_lz:
+; GCN: image_sample_c_lz {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_lz(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.lz.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_cd:
+; GCN: image_sample_c_cd {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_cd(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.cd.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_cd_cl:
+; GCN: image_sample_c_cd_cl {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_cd_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+
+declare <4 x float> @llvm.amdgcn.image.sample.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.cl.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.d.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.d.cl.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.l.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.b.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.b.cl.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.lz.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.cd.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.cd.cl.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+
+declare <4 x float> @llvm.amdgcn.image.sample.c.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.cl.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.d.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.d.cl.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.l.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.b.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.b.cl.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.lz.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.cd.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+
+
+attributes #0 = { nounwind readnone }
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.o.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.o.ll
new file mode 100644
index 00000000000..d10fd082469
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.o.ll
@@ -0,0 +1,208 @@
+; RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=GCN %s
+; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck --check-prefix=GCN %s
+
+; GCN-LABEL: {{^}}sample:
+; GCN: image_sample_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_cl:
+; GCN: image_sample_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.cl.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_d:
+; GCN: image_sample_d_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_d(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.d.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_d_cl:
+; GCN: image_sample_d_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_d_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.d.cl.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_l:
+; GCN: image_sample_l_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_l(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.l.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_b:
+; GCN: image_sample_b_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_b(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.b.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_b_cl:
+; GCN: image_sample_b_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_b_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.b.cl.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_lz:
+; GCN: image_sample_lz_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_lz(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.lz.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_cd:
+; GCN: image_sample_cd_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_cd(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.cd.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_cd_cl:
+; GCN: image_sample_cd_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_cd_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.cd.cl.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c:
+; GCN: image_sample_c_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_cl:
+; GCN: image_sample_c_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.cl.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_d:
+; GCN: image_sample_c_d_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_d(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.d.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_d_cl:
+; GCN: image_sample_c_d_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_d_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.d.cl.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_l:
+; GCN: image_sample_c_l_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_l(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.l.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_b:
+; GCN: image_sample_c_b_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_b(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.b.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_b_cl:
+; GCN: image_sample_c_b_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_b_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.b.cl.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_lz:
+; GCN: image_sample_c_lz_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_lz(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.lz.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_cd:
+; GCN: image_sample_c_cd_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_cd(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.cd.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+; GCN-LABEL: {{^}}sample_c_cd_cl:
+; GCN: image_sample_c_cd_cl_o {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf
+define void @sample_c_cd_cl(<4 x float> addrspace(1)* %out) {
+main_body:
+ %r = call <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.o.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 0)
+ store <4 x float> %r, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+
+declare <4 x float> @llvm.amdgcn.image.sample.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.cl.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.d.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.d.cl.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.l.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.b.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.b.cl.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.lz.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.cd.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.cd.cl.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+
+declare <4 x float> @llvm.amdgcn.image.sample.c.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.cl.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.d.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.d.cl.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.l.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.b.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.b.cl.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.lz.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.cd.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.o.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
+
+
+attributes #0 = { nounwind readnone }
OpenPOWER on IntegriCloud