AMDGPU/SI: Add d16 support for buffer intrinsics.

Differential Revision:
  https://reviews.llvm.org/D38906

Reviewers:
  Matt and Brian.

llvm-svn: 322402

6 files changed, 332 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.load.format.d16.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.load.format.d16.ll
new file mode 100644
index 00000000000..43776728d5c
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.load.format.d16.ll
@@ -0,0 +1,41 @@
+; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=UNPACKED %s
+; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED %s
+; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED %s
+
+; GCN-LABEL: {{^}}buffer_load_format_d16_x:
+; GCN: buffer_load_format_d16_x v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], 0
+define amdgpu_ps half @buffer_load_format_d16_x(<4 x i32> inreg %rsrc) {
+main_body:
+  %data = call half @llvm.amdgcn.buffer.load.format.f16(<4 x i32> %rsrc, i32 0, i32 0, i1 0, i1 0)
+  ret half %data
+}
+
+; GCN-LABEL: {{^}}buffer_load_format_d16_xy:
+; UNPACKED: buffer_load_format_d16_xy v{{\[}}{{[0-9]+}}:[[HI:[0-9]+]]{{\]}}, off, s[{{[0-9]+:[0-9]+}}], 0
+; UNPACKED: v_mov_b32_e32 v{{[0-9]+}}, v[[HI]]
+
+; PACKED: buffer_load_format_d16_xy v[[FULL:[0-9]+]], off, s[{{[0-9]+:[0-9]+}}], 0
+; PACKED: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v[[FULL]]
+define amdgpu_ps half @buffer_load_format_d16_xy(<4 x i32> inreg %rsrc) {
+main_body:
+  %data = call <2 x half> @llvm.amdgcn.buffer.load.format.v2f16(<4 x i32> %rsrc, i32 0, i32 0, i1 0, i1 0)
+  %elt = extractelement <2 x half> %data, i32 1
+  ret half %elt
+}
+
+; GCN-LABEL: {{^}}buffer_load_format_d16_xyzw:
+; UNPACKED: buffer_load_format_d16_xyzw v{{\[}}{{[0-9]+}}:[[HI:[0-9]+]]{{\]}}, off, s[{{[0-9]+:[0-9]+}}], 0
+; UNPACKED: v_mov_b32_e32 v{{[0-9]+}}, v[[HI]]
+
+; PACKED: buffer_load_format_d16_xyzw v{{\[}}{{[0-9]+}}:[[HI:[0-9]+]]{{\]}}, off, s[{{[0-9]+:[0-9]+}}], 0
+; PACKED: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v[[HI]]
+define amdgpu_ps half @buffer_load_format_d16_xyzw(<4 x i32> inreg %rsrc) {
+main_body:
+  %data = call <4 x half> @llvm.amdgcn.buffer.load.format.v4f16(<4 x i32> %rsrc, i32 0, i32 0, i1 0, i1 0)
+  %elt = extractelement <4 x half> %data, i32 3
+  ret half %elt
+}
+
+declare half @llvm.amdgcn.buffer.load.format.f16(<4 x i32>, i32, i32, i1, i1)
+declare <2 x half> @llvm.amdgcn.buffer.load.format.v2f16(<4 x i32>, i32, i32, i1, i1)
+declare <4 x half> @llvm.amdgcn.buffer.load.format.v4f16(<4 x i32>, i32, i32, i1, i1)
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.store.format.d16.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.store.format.d16.ll
new file mode 100644
index 00000000000..bcaa600a483
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.store.format.d16.ll
@@ -0,0 +1,50 @@
+; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=UNPACKED %s
+; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED -check-prefix=GFX81 %s
+; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED -check-prefix=GFX9 %s
+
+; GCN-LABEL: {{^}}buffer_store_format_d16_x:
+; GCN: v_trunc_f16_e32 v[[LO:[0-9]+]], s{{[0-9]+}}
+; GCN: buffer_store_format_d16_x v[[LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
+define amdgpu_kernel void @buffer_store_format_d16_x(<4 x i32> %rsrc, half %data, i32 %index) {
+main_body:
+  call void @llvm.amdgcn.buffer.store.format.f16(half %data, <4 x i32> %rsrc, i32 %index, i32 0, i1 0, i1 0)
+  ret void
+}
+
+; GCN-LABEL: {{^}}buffer_store_format_d16_xy:
+
+; UNPACKED: flat_load_ushort v[[HI:[0-9]+]], v[{{[0-9]+:[0-9]+}}] glc slc
+; UNPACKED: flat_load_ushort v[[LO:[0-9]+]], v[{{[0-9]+:[0-9]+}}] glc slc
+; UNPACKED: buffer_store_format_d16_xy v{{\[}}[[LO]]:[[HI]]{{\]}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
+
+; PACKED: buffer_store_format_d16_xy v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
+define amdgpu_kernel void @buffer_store_format_d16_xy(<4 x i32> %rsrc, <2 x half> %data, i32 %index) {
+main_body:
+  call void @llvm.amdgcn.buffer.store.format.v2f16(<2 x half> %data, <4 x i32> %rsrc, i32 %index, i32 0, i1 0, i1 0)
+  ret void
+}
+
+; GCN-LABEL: {{^}}buffer_store_format_d16_xyzw:
+
+; UNPACKED: flat_load_ushort v[[HI:[0-9]+]], v[{{[0-9]+:[0-9]+}}] glc slc
+; UNPACKED: flat_load_ushort v{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}] glc slc
+; UNPACKED: flat_load_ushort v{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}] glc slc
+; UNPACKED: flat_load_ushort v[[LO:[0-9]+]], v[{{[0-9]+:[0-9]+}}] glc slc
+; UNPACKED: buffer_store_format_d16_xyzw v{{\[}}[[LO]]:[[HI]]{{\]}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
+
+; GFX81: v_or_b32_e32 v[[HI:[0-9]+]]
+; GFX81: v_or_b32_e32 v[[LO:[0-9]+]]
+
+; GFX9: v_mov_b32_e32 v[[LO:[0-9]+]]
+; GFX9: v_mov_b32_e32 v[[HI:[0-9]+]]
+
+; PACKED: buffer_store_format_d16_xyzw v{{\[}}[[LO]]:[[HI]]{{\]}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
+define amdgpu_kernel void @buffer_store_format_d16_xyzw(<4 x i32> %rsrc, <4 x half> %data, i32 %index) {
+main_body:
+  call void @llvm.amdgcn.buffer.store.format.v4f16(<4 x half> %data, <4 x i32> %rsrc, i32 %index, i32 0, i1 0, i1 0)
+  ret void
+}
+
+declare void @llvm.amdgcn.buffer.store.format.f16(half, <4 x i32>, i32, i32, i1, i1)
+declare void @llvm.amdgcn.buffer.store.format.v2f16(<2 x half>, <4 x i32>, i32, i32, i1, i1)
+declare void @llvm.amdgcn.buffer.store.format.v4f16(<4 x half>, <4 x i32>, i32, i32, i1, i1)
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.load.d16.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.load.d16.ll
new file mode 100644
index 00000000000..96d698ee51c
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.load.d16.ll
@@ -0,0 +1,41 @@
+; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=UNPACKED %s
+; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED %s
+; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED %s
+
+; GCN-LABEL: {{^}}tbuffer_load_d16_x:
+; GCN: tbuffer_load_format_d16_x v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}],  dfmt:6,  nfmt:1, 0
+define amdgpu_ps half @tbuffer_load_d16_x(<4 x i32> inreg %rsrc) {
+main_body:
+  %data = call half @llvm.amdgcn.tbuffer.load.f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0, i32 6, i32 1, i1 0, i1 0)
+  ret half %data
+}
+
+; GCN-LABEL: {{^}}tbuffer_load_d16_xy:
+; UNPACKED: tbuffer_load_format_d16_xy v{{\[}}{{[0-9]+}}:[[HI:[0-9]+]]{{\]}}, off, s[{{[0-9]+:[0-9]+}}],  dfmt:6,  nfmt:1, 0
+; UNPACKED: v_mov_b32_e32 v{{[0-9]+}}, v[[HI]]
+
+; PACKED: tbuffer_load_format_d16_xy v[[FULL:[0-9]+]], off, s[{{[0-9]+:[0-9]+}}],  dfmt:6,  nfmt:1, 0
+; PACKED: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v[[FULL]]
+define amdgpu_ps half @tbuffer_load_d16_xy(<4 x i32> inreg %rsrc) {
+main_body:
+  %data = call <2 x half> @llvm.amdgcn.tbuffer.load.v2f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0, i32 6, i32 1, i1 0, i1 0)
+  %elt = extractelement <2 x half> %data, i32 1
+  ret half %elt
+}
+
+; GCN-LABEL: {{^}}tbuffer_load_d16_xyzw:
+; UNPACKED: tbuffer_load_format_d16_xyzw v{{\[}}{{[0-9]+}}:[[HI:[0-9]+]]{{\]}}, off, s[{{[0-9]+:[0-9]+}}],  dfmt:6,  nfmt:1, 0
+; UNPACKED: v_mov_b32_e32 v{{[0-9]+}}, v[[HI]]
+
+; PACKED: tbuffer_load_format_d16_xyzw v{{\[}}{{[0-9]+}}:[[HI:[0-9]+]]{{\]}}, off, s[{{[0-9]+:[0-9]+}}],  dfmt:6,  nfmt:1, 0
+; PACKED: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v[[HI]]
+define amdgpu_ps half @tbuffer_load_d16_xyzw(<4 x i32> inreg %rsrc) {
+main_body:
+  %data = call <4 x half> @llvm.amdgcn.tbuffer.load.v4f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0, i32 6, i32 1, i1 0, i1 0)
+  %elt = extractelement <4 x half> %data, i32 3
+  ret half %elt
+}
+
+declare half @llvm.amdgcn.tbuffer.load.f16(<4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
+declare <2 x half> @llvm.amdgcn.tbuffer.load.v2f16(<4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
+declare <4 x half> @llvm.amdgcn.tbuffer.load.v4f16(<4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.store.d16.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.store.d16.ll
new file mode 100644
index 00000000000..6ccdc2d7f2c
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tbuffer.store.d16.ll
@@ -0,0 +1,53 @@
+; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=UNPACKED %s
+; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED -check-prefix=GFX81 %s
+; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED -check-prefix=GFX9 %s
+
+
+; GCN-LABEL: {{^}}tbuffer_store_d16_x:
+; GCN: v_trunc_f16_e32 v[[LO:[0-9]+]], s{{[0-9]+}}
+; GCN: tbuffer_store_format_d16_x v[[LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}],  dfmt:1,  nfmt:2, 0 idxen
+define amdgpu_kernel void @tbuffer_store_d16_x(<4 x i32> %rsrc, half %data, i32 %vindex) {
+main_body:
+  call void @llvm.amdgcn.tbuffer.store.f16(half %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0, i32 1, i32 2, i1 0, i1 0)
+  ret void
+}
+
+
+; GCN-LABEL: {{^}}tbuffer_store_d16_xy:
+
+; UNPACKED: flat_load_ushort v[[HI:[0-9]+]], v[{{[0-9]+:[0-9]+}}] glc slc
+; UNPACKED: flat_load_ushort v[[LO:[0-9]+]], v[{{[0-9]+:[0-9]+}}] glc slc
+; UNPACKED: tbuffer_store_format_d16_xy v{{\[}}[[LO]]:[[HI]]{{\]}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}],  dfmt:1,  nfmt:2, 0 idxen
+
+; PACKED: tbuffer_store_format_d16_xy v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}],  dfmt:1,  nfmt:2, 0 idxen
+define amdgpu_kernel void @tbuffer_store_d16_xy(<4 x i32> %rsrc, <2 x half> %data, i32 %vindex) {
+main_body:
+  call void @llvm.amdgcn.tbuffer.store.v2f16(<2 x half> %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0, i32 1, i32 2, i1 0, i1 0)
+  ret void
+}
+
+
+; GCN-LABEL: {{^}}tbuffer_store_d16_xyzw:
+
+; UNPACKED: flat_load_ushort v[[HI:[0-9]+]], v[{{[0-9]+:[0-9]+}}] glc slc
+; UNPACKED: flat_load_ushort v{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}] glc slc
+; UNPACKED: flat_load_ushort v{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}] glc slc
+; UNPACKED: flat_load_ushort v[[LO:[0-9]+]], v[{{[0-9]+:[0-9]+}}] glc slc
+; UNPACKED: tbuffer_store_format_d16_xyzw v{{\[}}[[LO]]:[[HI]]{{\]}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}],  dfmt:1,  nfmt:2, 0 idxen
+
+; GFX81: v_or_b32_e32 v[[HI:[0-9]+]]
+; GFX81: v_or_b32_e32 v[[LO:[0-9]+]]
+
+; GFX9: v_mov_b32_e32 v[[LO:[0-9]+]]
+; GFX9: v_mov_b32_e32 v[[HI:[0-9]+]]
+
+; PACKED: tbuffer_store_format_d16_xyzw v{{\[}}[[LO]]:[[HI]]{{\]}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}],  dfmt:1,  nfmt:2, 0 idxen
+define amdgpu_kernel void @tbuffer_store_d16_xyzw(<4 x i32> %rsrc, <4 x half> %data, i32 %vindex) {
+main_body:
+  call void @llvm.amdgcn.tbuffer.store.v4f16(<4 x half> %data, <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.f16(half, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
+declare void @llvm.amdgcn.tbuffer.store.v2f16(<2 x half>, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
+declare void @llvm.amdgcn.tbuffer.store.v4f16(<4 x half>, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
diff --git a/llvm/test/MC/AMDGPU/buf-fmt-d16-packed.s b/llvm/test/MC/AMDGPU/buf-fmt-d16-packed.s
new file mode 100644
index 00000000000..108e709e29e
--- /dev/null
+++ b/llvm/test/MC/AMDGPU/buf-fmt-d16-packed.s
@@ -0,0 +1,74 @@
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx810 -show-encoding %s | FileCheck -check-prefix=GCN -check-prefix=PACKED %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx900 -show-encoding %s | FileCheck -check-prefix=GCN -check-prefix=PACKED %s
+
+// RUN: not llvm-mc -arch=amdgcn -mcpu=fiji -show-encoding 2>&1 %s | FileCheck -check-prefix=UNPACKED-ERR -check-prefix=GCN-ERR %s
+
+
+//===----------------------------------------------------------------------===//
+// Buffer Format Instructions.
+//===----------------------------------------------------------------------===//
+
+buffer_load_format_d16_x v1, off, s[4:7], s1
+// PACKED: buffer_load_format_d16_x v1, off, s[4:7], s1 ; encoding: [0x00,0x00,0x20,0xe0,0x00,0x01,0x01,0x01]
+
+buffer_load_format_d16_xy v1, off, s[4:7], s1
+// PACKED: buffer_load_format_d16_xy v1, off, s[4:7], s1 ; encoding: [0x00,0x00,0x24,0xe0,0x00,0x01,0x01,0x01]
+// UNPACKED-ERR: error: instruction not supported on this GPU
+
+buffer_load_format_d16_xyz v[1:2], off, s[4:7], s1
+// PACKED: buffer_load_format_d16_xyz v[1:2], off, s[4:7], s1 ; encoding: [0x00,0x00,0x28,0xe0,0x00,0x01,0x01,0x01]
+// UNPACKED-ERR: error: instruction not supported on this GPU
+
+buffer_load_format_d16_xyzw v[1:2], off, s[4:7], s1
+// PACKED: buffer_load_format_d16_xyzw v[1:2], off, s[4:7], s1 ; encoding: [0x00,0x00,0x2c,0xe0,0x00,0x01,0x01,0x01]
+// UNPACKED-ERR: error: instruction not supported on this GPU
+
+buffer_store_format_d16_x v1, off, s[4:7], s1
+// PACKED: buffer_store_format_d16_x v1, off, s[4:7], s1 ; encoding: [0x00,0x00,0x30,0xe0,0x00,0x01,0x01,0x01]
+
+buffer_store_format_d16_xy v1, off, s[4:7], s1
+// PACKED: buffer_store_format_d16_xy v1, off, s[4:7], s1 ; encoding: [0x00,0x00,0x34,0xe0,0x00,0x01,0x01,0x01]
+// UNPACKED-ERR: error: instruction not supported on this GPU
+
+buffer_store_format_d16_xyz v[1:2], off, s[4:7], s1
+// PACKED: buffer_store_format_d16_xyz v[1:2], off, s[4:7], s1 ; encoding: [0x00,0x00,0x38,0xe0,0x00,0x01,0x01,0x01]
+// UNPACKED-ERR: error: instruction not supported on this GPU
+
+buffer_store_format_d16_xyzw v[1:2], off, s[4:7], s1
+// PACKED: buffer_store_format_d16_xyzw v[1:2], off, s[4:7], s1 ; encoding: [0x00,0x00,0x3c,0xe0,0x00,0x01,0x01,0x01]
+// UNPACKED-ERR: error: instruction not supported on this GPU
+
+
+//===----------------------------------------------------------------------===//
+// TBuffer Format Instructions.
+//===----------------------------------------------------------------------===//
+
+tbuffer_load_format_d16_x v1, off, s[4:7], dfmt:15, nfmt:2, s1
+// PACKED: tbuffer_load_format_d16_x v1, off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7c,0xe9,0x00,0x01,0x01,0x01]
+
+tbuffer_load_format_d16_xy v1, off, s[4:7], dfmt:15, nfmt:2, s1
+// PACKED: tbuffer_load_format_d16_xy v1, off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x7c,0xe9,0x00,0x01,0x01,0x01]
+// UNPACKED-ERR: error: instruction not supported on this GPU
+
+tbuffer_load_format_d16_xyz v[1:2], off, s[4:7], dfmt:15, nfmt:2, s1
+// PACKED: tbuffer_load_format_d16_xyz v[1:2], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7d,0xe9,0x00,0x01,0x01,0x01]
+// UNPACKED-ERR: error: instruction not supported on this GPU
+
+tbuffer_load_format_d16_xyzw v[1:2], off, s[4:7], dfmt:15, nfmt:2, s1
+// PACKED: tbuffer_load_format_d16_xyzw v[1:2], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x7d,0xe9,0x00,0x01,0x01,0x01]
+// UNPACKED-ERR: error: instruction not supported on this GPU
+
+tbuffer_store_format_d16_x v1, off, s[4:7], dfmt:15, nfmt:2, s1
+// PACKED: tbuffer_store_format_d16_x v1, off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7e,0xe9,0x00,0x01,0x01,0x01]
+
+tbuffer_store_format_d16_xy v1, off, s[4:7], dfmt:15, nfmt:2, s1
+// PACKED: tbuffer_store_format_d16_xy v1, off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x7e,0xe9,0x00,0x01,0x01,0x01]
+// UNPACKED-ERR: error: instruction not supported on this GPU
+
+tbuffer_store_format_d16_xyz v[1:2], off, s[4:7], dfmt:15, nfmt:2, s1
+// PACKED: tbuffer_store_format_d16_xyz v[1:2], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7f,0xe9,0x00,0x01,0x01,0x01]
+// UNPACKED-ERR: error: instruction not supported on this GPU
+
+tbuffer_store_format_d16_xyzw v[1:2], off, s[4:7], dfmt:15, nfmt:2, s1
+// PACKED: tbuffer_store_format_d16_xyzw v[1:2], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x7f,0xe9,0x00,0x01,0x01,0x01]
+// UNPACKED-ERR: error: instruction not supported on this GPU
diff --git a/llvm/test/MC/AMDGPU/buf-fmt-d16-unpacked.s b/llvm/test/MC/AMDGPU/buf-fmt-d16-unpacked.s
new file mode 100644
index 00000000000..8db9f491e03
--- /dev/null
+++ b/llvm/test/MC/AMDGPU/buf-fmt-d16-unpacked.s
@@ -0,0 +1,73 @@
+// RUN: llvm-mc -arch=amdgcn -mcpu=fiji -show-encoding %s | FileCheck -check-prefix=GCN -check-prefix=UNPACKED %s
+// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx810 -show-encoding 2>&1 %s | FileCheck -check-prefix=PACKED-ERR -check-prefix=GCN-ERR %s
+// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx900 -show-encoding 2>&1 %s | FileCheck -check-prefix=PACKED-ERR -check-prefix=GCN-ERR %s
+
+
+//===----------------------------------------------------------------------===//
+// Buffer Format Instructions.
+//===----------------------------------------------------------------------===//
+
+buffer_load_format_d16_x v1, off, s[4:7], s1
+// UNPACKED: buffer_load_format_d16_x v1, off, s[4:7], s1 ; encoding: [0x00,0x00,0x20,0xe0,0x00,0x01,0x01,0x01]
+
+buffer_load_format_d16_xy v[1:2], off, s[4:7], s1
+// UNPACKED: buffer_load_format_d16_xy v[1:2], off, s[4:7], s1 ; encoding: [0x00,0x00,0x24,0xe0,0x00,0x01,0x01,0x01]
+// PACKED-ERR: error: instruction not supported on this GPU
+
+buffer_load_format_d16_xyz v[1:3], off, s[4:7], s1
+// UNPACKED: buffer_load_format_d16_xyz v[1:3], off, s[4:7], s1 ; encoding: [0x00,0x00,0x28,0xe0,0x00,0x01,0x01,0x01]
+// PACKED-ERR: error: instruction not supported on this GPU
+
+buffer_load_format_d16_xyzw v[1:4], off, s[4:7], s1
+// UNPACKED: buffer_load_format_d16_xyzw v[1:4], off, s[4:7], s1 ; encoding: [0x00,0x00,0x2c,0xe0,0x00,0x01,0x01,0x01]
+// PACKED-ERR: error: instruction not supported on this GPU
+
+buffer_store_format_d16_x v1, off, s[4:7], s1
+// UNPACKED: buffer_store_format_d16_x v1, off, s[4:7], s1 ; encoding: [0x00,0x00,0x30,0xe0,0x00,0x01,0x01,0x01]
+
+buffer_store_format_d16_xy v[1:2], off, s[4:7], s1
+// UNPACKED: buffer_store_format_d16_xy v[1:2], off, s[4:7], s1 ; encoding: [0x00,0x00,0x34,0xe0,0x00,0x01,0x01,0x01]
+// PACKED-ERR: error: instruction not supported on this GPU
+
+buffer_store_format_d16_xyz v[1:3], off, s[4:7], s1
+// UNPACKED: buffer_store_format_d16_xyz v[1:3], off, s[4:7], s1 ; encoding: [0x00,0x00,0x38,0xe0,0x00,0x01,0x01,0x01]
+// PACKED-ERR: error: instruction not supported on this GPU
+
+buffer_store_format_d16_xyzw v[1:4], off, s[4:7], s1
+// UNPACKED: buffer_store_format_d16_xyzw v[1:4], off, s[4:7], s1 ; encoding: [0x00,0x00,0x3c,0xe0,0x00,0x01,0x01,0x01]
+// PACKED-ERR: error: instruction not supported on this GPU
+
+
+//===----------------------------------------------------------------------===//
+// TBuffer Format Instructions.
+//===----------------------------------------------------------------------===//
+
+tbuffer_load_format_d16_x v1, off, s[4:7], dfmt:15, nfmt:2, s1
+// UNPACKED: tbuffer_load_format_d16_x v1, off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7c,0xe9,0x00,0x01,0x01,0x01]
+
+tbuffer_load_format_d16_xy v[1:2], off, s[4:7], dfmt:15, nfmt:2, s1
+// UNPACKED: tbuffer_load_format_d16_xy v[1:2], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x7c,0xe9,0x00,0x01,0x01,0x01]
+// PACKED-ERR: error: instruction not supported on this GPU
+
+tbuffer_load_format_d16_xyz v[1:3], off, s[4:7], dfmt:15, nfmt:2, s1
+// UNPACKED: tbuffer_load_format_d16_xyz v[1:3], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7d,0xe9,0x00,0x01,0x01,0x01]
+// PACKED-ERR: error: instruction not supported on this GPU
+
+tbuffer_load_format_d16_xyzw v[1:4], off, s[4:7], dfmt:15, nfmt:2, s1
+// UNPACKED: tbuffer_load_format_d16_xyzw v[1:4], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x7d,0xe9,0x00,0x01,0x01,0x01]
+// PACKED-ERR: error: instruction not supported on this GPU
+
+tbuffer_store_format_d16_x v1, off, s[4:7], dfmt:15, nfmt:2, s1
+// UNPACKED: tbuffer_store_format_d16_x v1, off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7e,0xe9,0x00,0x01,0x01,0x01]
+
+tbuffer_store_format_d16_xy v[1:2], off, s[4:7], dfmt:15, nfmt:2, s1
+// UNPACKED: tbuffer_store_format_d16_xy v[1:2], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x7e,0xe9,0x00,0x01,0x01,0x01]
+// PACKED-ERR: error: instruction not supported on this GPU
+
+tbuffer_store_format_d16_xyz v[1:3], off, s[4:7], dfmt:15, nfmt:2, s1
+// UNPACKED: tbuffer_store_format_d16_xyz v[1:3], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x00,0x7f,0xe9,0x00,0x01,0x01,0x01]
+// PACKED-ERR: error: instruction not supported on this GPU
+
+tbuffer_store_format_d16_xyzw v[1:4], off, s[4:7], dfmt:15, nfmt:2, s1
+// UNPACKED: tbuffer_store_format_d16_xyzw v[1:4], off, s[4:7],  dfmt:15,  nfmt:2, s1 ; encoding: [0x00,0x80,0x7f,0xe9,0x00,0x01,0x01,0x01]
+// PACKED-ERR: error: instruction not supported on this GPU