[AMDGPU] Add intrinsics for tbuffer load and store

Intrinsic already existed for llvm.SI.tbuffer.store

Needed tbuffer.load and also re-implementing the intrinsic as llvm.amdgcn.tbuffer.*

Added CodeGen tests for the 2 new variants added.
Left the original llvm.SI.tbuffer.store implementation to avoid issues with existing code

Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, tony-tye, tpr

Differential Revision: https://reviews.llvm.org/D30687

llvm-svn: 306031

10 files changed, 333 insertions, 25 deletions

diff --git a/llvm/test/CodeGen/AMDGPU/llvm.SI.tbuffer.store.ll b/llvm/test/CodeGen/AMDGPU/llvm.SI.tbuffer.store.ll
index 645c6a6b8d7..cd9c082ed94 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.SI.tbuffer.store.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.SI.tbuffer.store.ll
@@ -2,7 +2,7 @@
 ;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s
 
 ;CHECK-LABEL: {{^}}test1:
-;CHECK: tbuffer_store_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, 0x20, -1, 0, -1, 0, 14, 4, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, -1, 0, 0
+;CHECK: tbuffer_store_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, dfmt:14, nfmt:4, 0 offen offset:32 glc slc
 define amdgpu_vs void @test1(i32 %a1, i32 %vaddr) {
     %vdata = insertelement <4 x i32> undef, i32 %a1, i32 0
     call void @llvm.SI.tbuffer.store.v4i32(<16 x i8> undef, <4 x i32> %vdata,
@@ -11,8 +11,38 @@ define amdgpu_vs void @test1(i32 %a1, i32 %vaddr) {
     ret void
 }
 
+;CHECK-LABEL: {{^}}test1_idx:
+;CHECK: tbuffer_store_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, dfmt:14, nfmt:4, 0 idxen offset:32 glc slc
+define amdgpu_vs void @test1_idx(i32 %a1, i32 %vaddr) {
+    %vdata = insertelement <4 x i32> undef, i32 %a1, i32 0
+    call void @llvm.SI.tbuffer.store.v4i32(<16 x i8> undef, <4 x i32> %vdata,
+        i32 4, i32 %vaddr, i32 0, i32 32, i32 14, i32 4, i32 0, i32 1, i32 1,
+        i32 1, i32 0)
+    ret void
+}
+
+;CHECK-LABEL: {{^}}test1_scalar_offset:
+;CHECK: tbuffer_store_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, dfmt:14, nfmt:4, {{s[0-9]+}} idxen offset:32 glc slc
+define amdgpu_vs void @test1_scalar_offset(i32 %a1, i32 %vaddr, i32 inreg %soffset) {
+    %vdata = insertelement <4 x i32> undef, i32 %a1, i32 0
+    call void @llvm.SI.tbuffer.store.v4i32(<16 x i8> undef, <4 x i32> %vdata,
+        i32 4, i32 %vaddr, i32 %soffset, i32 32, i32 14, i32 4, i32 0, i32 1, i32 1,
+        i32 1, i32 0)
+    ret void
+}
+
+;CHECK-LABEL: {{^}}test1_no_glc_slc:
+;CHECK: tbuffer_store_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, dfmt:14, nfmt:4, 0 offen offset:32
+define amdgpu_vs void @test1_no_glc_slc(i32 %a1, i32 %vaddr) {
+    %vdata = insertelement <4 x i32> undef, i32 %a1, i32 0
+    call void @llvm.SI.tbuffer.store.v4i32(<16 x i8> undef, <4 x i32> %vdata,
+        i32 4, i32 %vaddr, i32 0, i32 32, i32 14, i32 4, i32 1, i32 0, i32 0,
+        i32 0, i32 0)
+    ret void
+}
+
 ;CHECK-LABEL: {{^}}test2:
-;CHECK: tbuffer_store_format_xyz {{v\[[0-9]+:[0-9]+\]}}, 0x18, -1, 0, -1, 0, 13, 4, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, -1, 0, 0
+;CHECK: tbuffer_store_format_xyz {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, dfmt:13, nfmt:4, 0 offen offset:24 glc slc
 define amdgpu_vs void @test2(i32 %a1, i32 %vaddr) {
     %vdata = insertelement <4 x i32> undef, i32 %a1, i32 0
     call void @llvm.SI.tbuffer.store.v4i32(<16 x i8> undef, <4 x i32> %vdata,
@@ -22,7 +52,7 @@ define amdgpu_vs void @test2(i32 %a1, i32 %vaddr) {
 }
 
 ;CHECK-LABEL: {{^}}test3:
-;CHECK: tbuffer_store_format_xy {{v\[[0-9]+:[0-9]+\]}}, 0x10, -1, 0, -1, 0, 11, 4, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, -1, 0, 0
+;CHECK: tbuffer_store_format_xy {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, dfmt:11, nfmt:4, 0 offen offset:16 glc slc
 define amdgpu_vs void @test3(i32 %a1, i32 %vaddr) {
     %vdata = insertelement <2 x i32> undef, i32 %a1, i32 0
     call void @llvm.SI.tbuffer.store.v2i32(<16 x i8> undef, <2 x i32> %vdata,
@@ -32,7 +62,7 @@ define amdgpu_vs void @test3(i32 %a1, i32 %vaddr) {
 }
 
 ;CHECK-LABEL: {{^}}test4:
-;CHECK: tbuffer_store_format_x {{v[0-9]+}}, 0x8, -1, 0, -1, 0, 4, 4, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, -1, 0, 0
+;CHECK: tbuffer_store_format_x {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, dfmt:4, nfmt:4, 0 offen offset:8 glc slc
 define amdgpu_vs void @test4(i32 %vdata, i32 %vaddr) {
     call void @llvm.SI.tbuffer.store.i32(<16 x i8> undef, i32 %vdata,
         i32 1, i32 %vaddr, i32 0, i32 8, i32 4, i32 4, i32 1, i32 0, i32 1,
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.load.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.load.ll
new file mode 100644
index 00000000000..712ee7ad1e5
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.load.ll
@@ -0,0 +1,109 @@
+;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: {{^}}tbuffer_load:
+; GCN: tbuffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, off, {{s\[[0-9]+:[0-9]+\]}}, dfmt:14, nfmt:4, 0
+; GCN: tbuffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, off, {{s\[[0-9]+:[0-9]+\]}}, dfmt:15, nfmt:3, 0 glc
+; GCN: tbuffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, off, {{s\[[0-9]+:[0-9]+\]}}, dfmt:6, nfmt:1, 0 slc
+; GCN: tbuffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, off, {{s\[[0-9]+:[0-9]+\]}}, dfmt:6, nfmt:1, 0
+; GCN: s_waitcnt
+define amdgpu_vs {<4 x float>, <4 x float>, <4 x float>, <4 x float>} @tbuffer_load(<4 x i32> inreg) {
+main_body:
+    %vdata     = call <4 x i32> @llvm.amdgcn.tbuffer.load.v4i32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 0, i32 14, i32 4, i1 0, i1 0)
+    %vdata_glc = call <4 x i32> @llvm.amdgcn.tbuffer.load.v4i32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 0, i32 15, i32 3, i1 1, i1 0)
+    %vdata_slc = call <4 x i32> @llvm.amdgcn.tbuffer.load.v4i32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 0, i32 6, i32 1, i1 0, i1 1)
+    %vdata_f32 = call <4 x float> @llvm.amdgcn.tbuffer.load.v4f32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 0, i32 6, i32 1, i1 0, i1 0)
+    %vdata.f     = bitcast <4 x i32> %vdata to <4 x float>
+    %vdata_glc.f = bitcast <4 x i32> %vdata_glc to <4 x float>
+    %vdata_slc.f = bitcast <4 x i32> %vdata_slc to <4 x float>
+    %r0 = insertvalue {<4 x float>, <4 x float>, <4 x float>, <4 x float>} undef, <4 x float> %vdata.f, 0
+    %r1 = insertvalue {<4 x float>, <4 x float>, <4 x float>, <4 x float>} %r0, <4 x float> %vdata_glc.f, 1
+    %r2 = insertvalue {<4 x float>, <4 x float>, <4 x float>, <4 x float>} %r1, <4 x float> %vdata_slc.f, 2
+    %r3 = insertvalue {<4 x float>, <4 x float>, <4 x float>, <4 x float>} %r2, <4 x float> %vdata_f32, 3
+    ret {<4 x float>, <4 x float>, <4 x float>, <4 x float>} %r3
+}
+
+; GCN-LABEL: {{^}}tbuffer_load_immoffs:
+; GCN: tbuffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, off, {{s\[[0-9]+:[0-9]+\]}}, dfmt:14, nfmt:4, 0 offset:42
+define amdgpu_vs <4 x float> @tbuffer_load_immoffs(<4 x i32> inreg) {
+main_body:
+    %vdata   = call <4 x i32> @llvm.amdgcn.tbuffer.load.v4i32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 42, i32 14, i32 4, i1 0, i1 0)
+    %vdata.f = bitcast <4 x i32> %vdata to <4 x float>
+    ret <4 x float> %vdata.f
+}
+
+; GCN-LABEL: {{^}}tbuffer_load_immoffs_large
+; GCN: tbuffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, off, {{s\[[0-9]+:[0-9]+\]}}, dfmt:15, nfmt:2, 61 offset:4095
+; GCN: tbuffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, off, {{s\[[0-9]+:[0-9]+\]}}, dfmt:14, nfmt:3, {{s[0-9]+}} offset:73
+; GCN: tbuffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, off, {{s\[[0-9]+:[0-9]+\]}}, dfmt:13, nfmt:4, {{s[0-9]+}} offset:1
+; GCN: s_waitcnt
+define amdgpu_vs {<4 x float>, <4 x float>, <4 x float>} @tbuffer_load_immoffs_large(<4 x i32> inreg, i32 inreg %soffs) {
+    %vdata     = call <4 x i32> @llvm.amdgcn.tbuffer.load.v4i32(<4 x i32> %0, i32 0, i32 0, i32 61, i32 4095, i32 15, i32 2, i1 0, i1 0)
+    %vdata_glc = call <4 x i32> @llvm.amdgcn.tbuffer.load.v4i32(<4 x i32> %0, i32 0, i32 0, i32 %soffs, i32 73, i32 14, i32 3, i1 0, i1 0)
+    %vdata_slc = call <4 x i32> @llvm.amdgcn.tbuffer.load.v4i32(<4 x i32> %0, i32 0, i32 0, i32 %soffs, i32 1, i32 13, i32 4, i1 0, i1 0)
+    %vdata.f     = bitcast <4 x i32> %vdata to <4 x float>
+    %vdata_glc.f = bitcast <4 x i32> %vdata_glc to <4 x float>
+    %vdata_slc.f = bitcast <4 x i32> %vdata_slc to <4 x float>
+    %r0 = insertvalue {<4 x float>, <4 x float>, <4 x float>} undef, <4 x float> %vdata.f, 0
+    %r1 = insertvalue {<4 x float>, <4 x float>, <4 x float>} %r0, <4 x float> %vdata_glc.f, 1
+    %r2 = insertvalue {<4 x float>, <4 x float>, <4 x float>} %r1, <4 x float> %vdata_slc.f, 2
+    ret {<4 x float>, <4 x float>, <4 x float>} %r2
+}
+
+; GCN-LABEL: {{^}}tbuffer_load_idx:
+; GCN: tbuffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, dfmt:14, nfmt:4, 0 idxen
+define amdgpu_vs <4 x float> @tbuffer_load_idx(<4 x i32> inreg, i32 %vindex) {
+main_body:
+    %vdata   = call <4 x i32> @llvm.amdgcn.tbuffer.load.v4i32(<4 x i32> %0, i32 %vindex, i32 0, i32 0, i32 0, i32 14, i32 4, i1 0, i1 0)
+    %vdata.f = bitcast <4 x i32> %vdata to <4 x float>
+    ret <4 x float> %vdata.f
+}
+
+; GCN-LABEL: {{^}}tbuffer_load_ofs:
+; GCN: tbuffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, dfmt:14, nfmt:4, 0 offen
+define amdgpu_vs <4 x float> @tbuffer_load_ofs(<4 x i32> inreg, i32 %voffs) {
+main_body:
+    %vdata   = call <4 x i32> @llvm.amdgcn.tbuffer.load.v4i32(<4 x i32> %0, i32 0, i32 %voffs, i32 0, i32 0, i32 14, i32 4, i1 0, i1 0)
+    %vdata.f = bitcast <4 x i32> %vdata to <4 x float>
+    ret <4 x float> %vdata.f
+}
+
+; GCN-LABEL: {{^}}tbuffer_load_ofs_imm:
+; GCN: tbuffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, dfmt:14, nfmt:4, 0 offen offset:52
+define amdgpu_vs <4 x float> @tbuffer_load_ofs_imm(<4 x i32> inreg, i32 %voffs) {
+main_body:
+    %vdata   = call <4 x i32> @llvm.amdgcn.tbuffer.load.v4i32(<4 x i32> %0, i32 0, i32 %voffs, i32 0, i32 52, i32 14, i32 4, i1 0, i1 0)
+    %vdata.f = bitcast <4 x i32> %vdata to <4 x float>
+    ret <4 x float> %vdata.f
+}
+
+; GCN-LABEL: {{^}}tbuffer_load_both:
+; GCN: tbuffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, dfmt:14, nfmt:4, 0 idxen offen
+define amdgpu_vs <4 x float> @tbuffer_load_both(<4 x i32> inreg, i32 %vindex, i32 %voffs) {
+main_body:
+    %vdata   = call <4 x i32> @llvm.amdgcn.tbuffer.load.v4i32(<4 x i32> %0, i32 %vindex, i32 %voffs, i32 0, i32 0, i32 14, i32 4, i1 0, i1 0)
+    %vdata.f = bitcast <4 x i32> %vdata to <4 x float>
+    ret <4 x float> %vdata.f
+}
+
+
+; GCN-LABEL: {{^}}buffer_load_xy:
+; GCN: tbuffer_load_format_xy {{v\[[0-9]+:[0-9]+\]}}, off, {{s\[[0-9]+:[0-9]+\]}}, dfmt:13, nfmt:4, 0
+define amdgpu_vs <2 x float> @buffer_load_xy(<4 x i32> inreg %rsrc) {
+    %vdata = call <2 x i32> @llvm.amdgcn.tbuffer.load.v2i32(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0, i32 13, i32 4, i1 0, i1 0)
+    %vdata.f = bitcast <2 x i32> %vdata to <2 x float>
+    ret <2 x float> %vdata.f
+}
+
+; GCN-LABEL: {{^}}buffer_load_x:
+; GCN: tbuffer_load_format_x {{v[0-9]+}}, off, {{s\[[0-9]+:[0-9]+\]}}, dfmt:13, nfmt:4, 0
+define amdgpu_vs float @buffer_load_x(<4 x i32> inreg %rsrc) {
+    %vdata = call i32 @llvm.amdgcn.tbuffer.load.i32(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0, i32 13, i32 4, i1 0, i1 0)
+    %vdata.f = bitcast i32 %vdata to float
+    ret float %vdata.f
+}
+
+declare i32 @llvm.amdgcn.tbuffer.load.i32(<4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
+declare <2 x i32> @llvm.amdgcn.tbuffer.load.v2i32(<4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
+declare <4 x i32> @llvm.amdgcn.tbuffer.load.v4i32(<4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
+declare <4 x float> @llvm.amdgcn.tbuffer.load.v4f32(<4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.store.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.store.ll
new file mode 100644
index 00000000000..997d7f52946
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.store.ll
@@ -0,0 +1,110 @@
+;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: {{^}}tbuffer_store:
+; GCN: tbuffer_store_format_xyzw v[0:3], off, s[0:3], dfmt:12, nfmt:2, 0
+; GCN: tbuffer_store_format_xyzw v[4:7], off, s[0:3], dfmt:13, nfmt:3, 0 glc
+; GCN: tbuffer_store_format_xyzw v[8:11], off, s[0:3], dfmt:14, nfmt:4, 0 slc
+; GCN: tbuffer_store_format_xyzw v[8:11], off, s[0:3], dfmt:14, nfmt:4, 0
+define amdgpu_ps void @tbuffer_store(<4 x i32> inreg, <4 x float>, <4 x float>, <4 x float>) {
+main_body:
+  %in1 = bitcast <4 x float> %1 to <4 x i32>
+  %in2 = bitcast <4 x float> %2 to <4 x i32>
+  %in3 = bitcast <4 x float> %3 to <4 x i32>
+  call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 0, i32 0, i32 0, i32 0, i32 12, i32 2, i1 0, i1 0)
+  call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in2, <4 x i32> %0, i32 0, i32 0, i32 0, i32 0, i32 13, i32 3, i1 1, i1 0)
+  call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in3, <4 x i32> %0, i32 0, i32 0, i32 0, i32 0, i32 14, i32 4, i1 0, i1 1)
+  call void @llvm.amdgcn.tbuffer.store.v4f32(<4 x float> %3, <4 x i32> %0, i32 0, i32 0, i32 0, i32 0, i32 14, i32 4, i1 0, i1 0)
+  ret void
+}
+
+; GCN-LABEL: {{^}}tbuffer_store_immoffs:
+; GCN: tbuffer_store_format_xyzw v[0:3], off, s[0:3], dfmt:5, nfmt:7, 0 offset:42
+define amdgpu_ps void @tbuffer_store_immoffs(<4 x i32> inreg, <4 x float>) {
+main_body:
+  %in1 = bitcast <4 x float> %1 to <4 x i32>
+  call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 0, i32 0, i32 0, i32 42, i32 5, i32 7, i1 0, i1 0)
+  ret void
+}
+
+; GCN-LABEL: {{^}}tbuffer_store_scalar_and_imm_offs:
+; GCN: tbuffer_store_format_xyzw v[0:3], off, s[0:3], dfmt:5, nfmt:7, {{s[0-9]+}} offset:42
+define amdgpu_ps void @tbuffer_store_scalar_and_imm_offs(<4 x i32> inreg, <4 x float> %vdata, i32 inreg %soffset) {
+main_body:
+  %in1 = bitcast <4 x float> %vdata to <4 x i32>
+  call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 0, i32 0, i32 %soffset, i32 42, i32 5, i32 7, i1 0, i1 0)
+  ret void
+}
+
+; GCN-LABEL: {{^}}buffer_store_idx:
+; GCN: tbuffer_store_format_xyzw v[0:3], v4, s[0:3], dfmt:15, nfmt:2, 0 idxen
+define amdgpu_ps void @buffer_store_idx(<4 x i32> inreg, <4 x float> %vdata, i32 %vindex) {
+main_body:
+  %in1 = bitcast <4 x float> %vdata to <4 x i32>
+  call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 %vindex, i32 0, i32 0, i32 0, i32 15, i32 2, i1 0, i1 0)
+  ret void
+}
+
+; GCN-LABEL: {{^}}buffer_store_ofs:
+; GCN: tbuffer_store_format_xyzw v[0:3], v4, s[0:3], dfmt:3, nfmt:7, 0 offen
+define amdgpu_ps void @buffer_store_ofs(<4 x i32> inreg, <4 x float> %vdata, i32 %voffset) {
+main_body:
+  %in1 = bitcast <4 x float> %vdata to <4 x i32>
+  call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 0, i32 %voffset, i32 0, i32 0, i32 3, i32 7, i1 0, i1 0)
+  ret void
+}
+
+; GCN-LABEL: {{^}}buffer_store_both:
+; GCN: tbuffer_store_format_xyzw v[0:3], v[4:5], s[0:3], dfmt:6, nfmt:4, 0 idxen offen
+define amdgpu_ps void @buffer_store_both(<4 x i32> inreg, <4 x float> %vdata, i32 %vindex, i32 %voffset) {
+main_body:
+  %in1 = bitcast <4 x float> %vdata to <4 x i32>
+  call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 %vindex, i32 %voffset, i32 0, i32 0, i32 6, i32 4, i1 0, i1 0)
+  ret void
+}
+
+; Ideally, the register allocator would avoid the wait here
+;
+; GCN-LABEL: {{^}}buffer_store_wait:
+; GCN: tbuffer_store_format_xyzw v[0:3], v4, s[0:3], dfmt:15, nfmt:3, 0 idxen
+; GCN: s_waitcnt expcnt(0)
+; GCN: buffer_load_format_xyzw v[0:3], v5, s[0:3], 0 idxen
+; GCN: s_waitcnt vmcnt(0)
+; GCN: tbuffer_store_format_xyzw v[0:3], v6, s[0:3], dfmt:16, nfmt:2, 0 idxen
+define amdgpu_ps void @buffer_store_wait(<4 x i32> inreg, <4 x float> %vdata, i32 %vindex.1, i32 %vindex.2, i32 %vindex.3) {
+main_body:
+  %in1 = bitcast <4 x float> %vdata to <4 x i32>
+  call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 %vindex.1, i32 0, i32 0, i32 0, i32 15, i32 3, i1 0, i1 0)
+  %data = call <4 x float> @llvm.amdgcn.buffer.load.format.v4f32(<4 x i32> %0, i32 %vindex.2, i32 0, i1 0, i1 0)
+  %data.i = bitcast <4 x float> %data to <4 x i32>
+  call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %data.i, <4 x i32> %0, i32 %vindex.3, i32 0, i32 0, i32 0, i32 16, i32 2, i1 0, i1 0)
+  ret void
+}
+
+; GCN-LABEL: {{^}}buffer_store_x1:
+; GCN: tbuffer_store_format_x v0, v1, s[0:3], dfmt:13, nfmt:7, 0 idxen
+define amdgpu_ps void @buffer_store_x1(<4 x i32> inreg %rsrc, float %data, i32 %vindex) {
+main_body:
+  %data.i = bitcast float %data to i32
+  call void @llvm.amdgcn.tbuffer.store.i32(i32 %data.i, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0, i32 13, i32 7, i1 0, i1 0)
+  ret void
+}
+
+; GCN-LABEL: {{^}}buffer_store_x2:
+; GCN: tbuffer_store_format_xy v[0:1], v2, s[0:3], dfmt:1, nfmt:2, 0 idxen
+define amdgpu_ps void @buffer_store_x2(<4 x i32> inreg %rsrc, <2 x float> %data, i32 %vindex) {
+main_body:
+  %data.i = bitcast <2 x float> %data to <2 x i32>
+  call void @llvm.amdgcn.tbuffer.store.v2i32(<2 x i32> %data.i, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0, i32 1, i32 2, i1 0, i1 0)
+  ret void
+}
+
+declare void @llvm.amdgcn.tbuffer.store.i32(i32, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #0
+declare void @llvm.amdgcn.tbuffer.store.v2i32(<2 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #0
+declare void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #0
+declare void @llvm.amdgcn.tbuffer.store.v4f32(<4 x float>, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #0
+declare <4 x float> @llvm.amdgcn.buffer.load.format.v4f32(<4 x i32>, i32, i32, i1, i1) #1
+
+attributes #0 = { nounwind }
+attributes #1 = { nounwind readonly }
+
diff --git a/llvm/test/CodeGen/AMDGPU/merge-store-crash.ll b/llvm/test/CodeGen/AMDGPU/merge-store-crash.ll
index ef552e295fd..1252a5c0c02 100644
--- a/llvm/test/CodeGen/AMDGPU/merge-store-crash.ll
+++ b/llvm/test/CodeGen/AMDGPU/merge-store-crash.ll
@@ -26,11 +26,11 @@ main_body:
   %tmp9 = insertelement <4 x i32> %tmp8, i32 %tmp7, i32 1
   %tmp10 = insertelement <4 x i32> %tmp9, i32 undef, i32 2
   %tmp11 = insertelement <4 x i32> %tmp10, i32 undef, i32 3
-  call void @llvm.SI.tbuffer.store.v4i32(<16 x i8> undef, <4 x i32> %tmp11, i32 4, i32 undef, i32 %arg, i32 0, i32 14, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
+  call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %tmp11, <4 x i32> undef, i32 undef, i32 0, i32 %arg, i32 0, i32 14, i32 4, i1 1, i1 1)
   ret void
 }
 
 ; Function Attrs: nounwind
-declare void @llvm.SI.tbuffer.store.v4i32(<16 x i8>, <4 x i32>, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32) #0
+declare void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #0
 
 attributes #0 = { nounwind }
diff --git a/llvm/test/CodeGen/AMDGPU/merge-store-usedef.ll b/llvm/test/CodeGen/AMDGPU/merge-store-usedef.ll
index 1c82aeb9b7f..958692e0c92 100644
--- a/llvm/test/CodeGen/AMDGPU/merge-store-usedef.ll
+++ b/llvm/test/CodeGen/AMDGPU/merge-store-usedef.ll
@@ -11,13 +11,13 @@ define amdgpu_vs void @test1(i32 %v) #0 {
 
   store i32 %v, i32 addrspace(3)* %p0
 
-  call void @llvm.SI.tbuffer.store.i32(<16 x i8> undef, i32 %v, i32 1, i32 undef, i32 undef, i32 0, i32 4, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
+  call void @llvm.amdgcn.tbuffer.store.i32(i32 %v, <4 x i32> undef, i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i1 1, i1 0)
 
   %w = load i32, i32 addrspace(3)* %p0
   store i32 %w, i32 addrspace(3)* %p1
   ret void
 }
 
-declare void @llvm.SI.tbuffer.store.i32(<16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32) #0
+declare void @llvm.amdgcn.tbuffer.store.i32(i32, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #0
 
 attributes #0 = { nounwind }
diff --git a/llvm/test/CodeGen/AMDGPU/mubuf.ll b/llvm/test/CodeGen/AMDGPU/mubuf.ll
index 9e1d2e0490c..d883b87ec40 100644
--- a/llvm/test/CodeGen/AMDGPU/mubuf.ll
+++ b/llvm/test/CodeGen/AMDGPU/mubuf.ll
@@ -62,7 +62,8 @@ main_body:
   %tmp2 = shl i32 %6, 2
   %tmp3 = call i32 @llvm.SI.buffer.load.dword.i32.i32(<16 x i8> %tmp1, i32 %tmp2, i32 64, i32 0, i32 1, i32 0, i32 1, i32 0, i32 0)
   %tmp4 = add i32 %6, 16
-  call void @llvm.SI.tbuffer.store.i32(<16 x i8> %tmp1, i32 %tmp3, i32 1, i32 %tmp4, i32 %4, i32 0, i32 4, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
+  %tmp1.4xi32 = bitcast <16 x i8> %tmp1 to <4 x i32>
+  call void @llvm.amdgcn.tbuffer.store.i32(i32 %tmp3, <4 x i32> %tmp1.4xi32, i32 0, i32 %tmp4, i32 %4, i32 0, i32 4, i32 4, i1 1, i1 1)
   ret void
 }
 
@@ -80,7 +81,8 @@ main_body:
   %tmp2 = shl i32 %6, 2
   %tmp3 = call i32 @llvm.SI.buffer.load.dword.i32.i32(<16 x i8> %tmp1, i32 %tmp2, i32 65, i32 0, i32 1, i32 0, i32 1, i32 0, i32 0)
   %tmp4 = add i32 %6, 16
-  call void @llvm.SI.tbuffer.store.i32(<16 x i8> %tmp1, i32 %tmp3, i32 1, i32 %tmp4, i32 %4, i32 0, i32 4, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
+  %tmp1.4xi32 = bitcast <16 x i8> %tmp1 to <4 x i32>
+  call void @llvm.amdgcn.tbuffer.store.i32(i32 %tmp3, <4 x i32> %tmp1.4xi32, i32 0, i32 %tmp4, i32 %4, i32 0, i32 4, i32 4, i1 1, i1 1)
   ret void
 }
 
@@ -175,6 +177,6 @@ define amdgpu_kernel void @store_vgpr_ptr(i32 addrspace(1)* %out) #0 {
 }
 
 declare i32 @llvm.SI.buffer.load.dword.i32.i32(<16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #0
-declare void @llvm.SI.tbuffer.store.i32(<16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32)
+declare void @llvm.amdgcn.tbuffer.store.i32(i32, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
 
 attributes #0 = { nounwind readonly }
diff --git a/llvm/test/CodeGen/AMDGPU/scheduler-subrange-crash.ll b/llvm/test/CodeGen/AMDGPU/scheduler-subrange-crash.ll
index c0e8e58556f..47e32724d9c 100644
--- a/llvm/test/CodeGen/AMDGPU/scheduler-subrange-crash.ll
+++ b/llvm/test/CodeGen/AMDGPU/scheduler-subrange-crash.ll
@@ -25,29 +25,29 @@ main_body:
   %array_vector10 = insertelement <4 x float> %array_vector9, float 0.000000e+00, i32 2
   %array_vector11 = insertelement <4 x float> %array_vector10, float undef, i32 3
   %tmp3 = call i32 @llvm.SI.buffer.load.dword.i32.i32(<16 x i8> undef, i32 undef, i32 4864, i32 0, i32 1, i32 0, i32 1, i32 0, i32 0)
-  call void @llvm.SI.tbuffer.store.i32(<16 x i8> undef, i32 %tmp3, i32 1, i32 36, i32 %arg, i32 0, i32 4, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
+  call void @llvm.amdgcn.tbuffer.store.i32(i32 %tmp3, <4 x i32> undef, i32 0, i32 0, i32 %arg, i32 36, i32 4, i32 4, i1 1, i1 1)
   %bc = bitcast <4 x float> %array_vector3 to <4 x i32>
   %tmp4 = extractelement <4 x i32> %bc, i32 undef
-  call void @llvm.SI.tbuffer.store.i32(<16 x i8> undef, i32 %tmp4, i32 1, i32 48, i32 %arg, i32 0, i32 4, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
+  call void @llvm.amdgcn.tbuffer.store.i32(i32 %tmp4, <4 x i32> undef, i32 0, i32 0, i32 %arg, i32 48, i32 4, i32 4, i1 1, i1 1)
   %bc49 = bitcast <4 x float> %array_vector11 to <4 x i32>
   %tmp5 = extractelement <4 x i32> %bc49, i32 undef
-  call void @llvm.SI.tbuffer.store.i32(<16 x i8> undef, i32 %tmp5, i32 1, i32 72, i32 %arg, i32 0, i32 4, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
+  call void @llvm.amdgcn.tbuffer.store.i32(i32 %tmp5, <4 x i32> undef, i32 0, i32 0, i32 %arg, i32 72, i32 4, i32 4, i1 1, i1 1)
   %array_vector21 = insertelement <4 x float> <float 0.000000e+00, float undef, float undef, float undef>, float %tmp, i32 1
   %array_vector22 = insertelement <4 x float> %array_vector21, float undef, i32 2
   %array_vector23 = insertelement <4 x float> %array_vector22, float undef, i32 3
-  call void @llvm.SI.tbuffer.store.i32(<16 x i8> undef, i32 undef, i32 1, i32 28, i32 %arg, i32 0, i32 4, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
+  call void @llvm.amdgcn.tbuffer.store.i32(i32 undef, <4 x i32> undef, i32 0, i32 0, i32 %arg, i32 28, i32 4, i32 4, i1 1, i1 1)
   %bc52 = bitcast <4 x float> %array_vector23 to <4 x i32>
   %tmp6 = extractelement <4 x i32> %bc52, i32 undef
-  call void @llvm.SI.tbuffer.store.i32(<16 x i8> undef, i32 %tmp6, i32 1, i32 64, i32 %arg, i32 0, i32 4, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
-  call void @llvm.SI.tbuffer.store.i32(<16 x i8> undef, i32 undef, i32 1, i32 20, i32 %arg, i32 0, i32 4, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
-  call void @llvm.SI.tbuffer.store.i32(<16 x i8> undef, i32 undef, i32 1, i32 56, i32 %arg, i32 0, i32 4, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
-  call void @llvm.SI.tbuffer.store.i32(<16 x i8> undef, i32 undef, i32 1, i32 92, i32 %arg, i32 0, i32 4, i32 4, i32 1, i32 0, i32 1, i32 1, i32 0)
+  call void @llvm.amdgcn.tbuffer.store.i32(i32 %tmp6, <4 x i32> undef, i32 0, i32 0, i32 %arg, i32 64, i32 4, i32 4, i1 1, i1 1)
+  call void @llvm.amdgcn.tbuffer.store.i32(i32 undef, <4 x i32> undef, i32 0, i32 0, i32 %arg, i32 20, i32 4, i32 4, i1 1, i1 1)
+  call void @llvm.amdgcn.tbuffer.store.i32(i32 undef, <4 x i32> undef, i32 0, i32 0, i32 %arg, i32 56, i32 4, i32 4, i1 1, i1 1)
+  call void @llvm.amdgcn.tbuffer.store.i32(i32 undef, <4 x i32> undef, i32 0, i32 0, i32 %arg, i32 92, i32 4, i32 4, i1 1, i1 1)
   ret void
 }
 
 declare float @llvm.SI.load.const(<16 x i8>, i32) #1
 declare i32 @llvm.SI.buffer.load.dword.i32.i32(<16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #2
-declare void @llvm.SI.tbuffer.store.i32(<16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32) #3
+declare void @llvm.amdgcn.tbuffer.store.i32(i32, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #3
 
 attributes #0 = { nounwind "target-cpu"="tonga" }
 attributes #1 = { nounwind readnone }
diff --git a/llvm/test/CodeGen/AMDGPU/si-triv-disjoint-mem-access.ll b/llvm/test/CodeGen/AMDGPU/si-triv-disjoint-mem-access.ll
index 8a4cee264fd..348c7200c0b 100644
--- a/llvm/test/CodeGen/AMDGPU/si-triv-disjoint-mem-access.ll
+++ b/llvm/test/CodeGen/AMDGPU/si-triv-disjoint-mem-access.ll
@@ -1,7 +1,7 @@
 ; RUN: llc -march=amdgcn -mcpu=bonaire -enable-amdgpu-aa=0 -verify-machineinstrs -enable-misched -enable-aa-sched-mi < %s | FileCheck -check-prefix=FUNC -check-prefix=CI %s
 
-declare void @llvm.SI.tbuffer.store.i32(<16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32)
-declare void @llvm.SI.tbuffer.store.v4i32(<16 x i8>, <4 x i32>, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32)
+declare void @llvm.amdgcn.tbuffer.store.i32(i32, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
+declare void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
 declare void @llvm.amdgcn.s.barrier() #1
 declare i32 @llvm.amdgcn.workitem.id.x() #2
 
@@ -258,9 +258,8 @@ define amdgpu_kernel void @reorder_global_offsets_addr64_soffset0(i32 addrspace(
 ;   %tmp1 = load i32, i32 addrspace(3)* %ptr1, align 4
 
 ;   %vdata = insertelement <4 x i32> undef, i32 %a1, i32 0
-;   call void @llvm.SI.tbuffer.store.v4i32(<16 x i8> undef, <4 x i32> %vdata,
-;         i32 4, i32 %vaddr, i32 0, i32 32, i32 14, i32 4, i32 1, i32 0, i32 1,
-;         i32 1, i32 0)
+;   call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %vdata, <4 x i32> undef,
+;         i32 %vaddr, i32 0, i32 0, i32 32, i32 14, i32 4, i1 1, i1 1)
 
 ;   %tmp2 = load i32, i32 addrspace(3)* %ptr2, align 4
 
diff --git a/llvm/test/MC/AMDGPU/mtbuf.s b/llvm/test/MC/AMDGPU/mtbuf.s
new file mode 100644
index 00000000000..9c8d71589bd
--- /dev/null
+++ b/llvm/test/MC/AMDGPU/mtbuf.s
@@ -0,0 +1,36 @@
+// RUN: llvm-mc -arch=amdgcn -mcpu=tahiti -show-encoding %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=SICI %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=bonaire -show-encoding %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=SICI %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=tonga -show-encoding %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
+
+//===----------------------------------------------------------------------===//
+// Test for dfmt and nfmt (tbuffer only)
+//===----------------------------------------------------------------------===//
+
+tbuffer_load_format_x v1, off, s[4:7], dfmt:15, nfmt:2, s1
+// SICI: tbuffer_load_format_x v1, off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x78,0xe9,0x00,0x01,0x01,0x01]
+// VI:   tbuffer_load_format_x v1, off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x78,0xe9,0x00,0x01,0x01,0x01]
+
+tbuffer_load_format_xy v[1:2], off, s[4:7], dfmt:15, nfmt:2, s1
+// SICI: tbuffer_load_format_xy v[1:2], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x79,0xe9,0x00,0x01,0x01,0x01]
+// VI:   tbuffer_load_format_xy v[1:2], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x78,0xe9,0x00,0x01,0x01,0x01]
+
+tbuffer_load_format_xyzw v[1:4], off, s[4:7], dfmt:15, nfmt:2, s1
+// SICI: tbuffer_load_format_xyzw v[1:4], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7b,0xe9,0x00,0x01,0x01,0x01]
+// VI:   tbuffer_load_format_xyzw v[1:4], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x79,0xe9,0x00,0x01,0x01,0x01]
+
+tbuffer_store_format_x v1, off, s[4:7], dfmt:15, nfmt:2, s1
+// SICI: tbuffer_store_format_x v1, off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7c,0xe9,0x00,0x01,0x01,0x01]
+// VI:   tbuffer_store_format_x v1, off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7a,0xe9,0x00,0x01,0x01,0x01]
+
+tbuffer_store_format_xy v[1:2], off, s[4:7], dfmt:15, nfmt:2, s1
+// SICI: tbuffer_store_format_xy v[1:2], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7d,0xe9,0x00,0x01,0x01,0x01]
+// VI:   tbuffer_store_format_xy v[1:2], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x7a,0xe9,0x00,0x01,0x01,0x01]
+
+tbuffer_store_format_xyzw v[1:4], off, s[4:7], dfmt:15, nfmt:2, s1
+// SICI: tbuffer_store_format_xyzw v[1:4], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7f,0xe9,0x00,0x01,0x01,0x01]
+// VI:   tbuffer_store_format_xyzw v[1:4], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x7b,0xe9,0x00,0x01,0x01,0x01]
+
+tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], dfmt:15, nfmt:2, ttmp1
+// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7],  dfmt:15,  nfmt:2, ttmp1 ; encoding: [0x00,0x00,0x7f,0xe9,0x00,0x01,0x1d,0x71]
+// VI:   tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], dfmt:15,  nfmt:2, ttmp1 ; encoding: [0x00,0x80,0x7b,0xe9,0x00,0x01,0x1d,0x71]
+
diff --git a/llvm/test/MC/Disassembler/AMDGPU/mtbuf_vi.txt b/llvm/test/MC/Disassembler/AMDGPU/mtbuf_vi.txt
new file mode 100644
index 00000000000..519e03ede69
--- /dev/null
+++ b/llvm/test/MC/Disassembler/AMDGPU/mtbuf_vi.txt
@@ -0,0 +1,22 @@
+# RUN: llvm-mc -arch=amdgcn -mcpu=tonga -disassemble -show-encoding < %s | FileCheck %s -check-prefix=VI
+
+# VI:   tbuffer_load_format_x v1, off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x78,0xe9,0x00,0x01,0x01,0x01]
+0x00 0x00 0x78 0xe9 0x00 0x01 0x01 0x01
+
+# VI:   tbuffer_load_format_xy v[1:2], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x78,0xe9,0x00,0x01,0x01,0x01]
+0x00 0x80 0x78 0xe9 0x00 0x01 0x01 0x01
+
+# VI:   tbuffer_load_format_xyzw v[1:4], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x79,0xe9,0x00,0x01,0x01,0x01]
+0x00 0x80 0x79 0xe9 0x00 0x01 0x01 0x01
+
+# VI:   tbuffer_store_format_x v1, off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7a,0xe9,0x00,0x01,0x01,0x01]
+0x00 0x00 0x7a 0xe9 0x00 0x01 0x01 0x01
+
+# VI:   tbuffer_store_format_xy v[1:2], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x7a,0xe9,0x00,0x01,0x01,0x01]
+0x00 0x80 0x7a 0xe9 0x00 0x01 0x01 0x01
+
+# VI:   tbuffer_store_format_xyzw v[1:4], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x7b,0xe9,0x00,0x01,0x01,0x01]
+0x00 0x80 0x7b 0xe9 0x00 0x01 0x01 0x01
+
+# VI:   tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7],  dfmt:15,  nfmt:2, ttmp1 ; encoding: [0x00,0x80,0x7b,0xe9,0x00,0x01,0x1d,0x71]
+0x00 0x80 0x7b 0xe9 0x00 0x01 0x1d 0x71