maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/MC/AMDGPU/mtbuf.s

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

380 lines
25 KiB
ArmAsm
Raw Normal View History

[AMDGPU][MC] Corrected MTBUF parsing and decoding MTBUF implementation has many issues and this change addresses most of these: - refactored duplicated code; - hardcoded constants moved out of high-level code; - fixed a decoding error when nfmt or dfmt are zero (bug 36932); - corrected parsing of operand separators (bug 46403); - corrected handling of missing operands (bug 46404); - corrected handling of out-of-range modifiers (bug 46421); - corrected default value (bug 46467). Reviewers: arsenm, rampitec, vpykhtin, artem.tamazov, kzhuravl Differential Revision: https://reviews.llvm.org/D83760
2020-07-16 00:44:07 +08:00
// RUN: not llvm-mc -arch=amdgcn -mcpu=tahiti -show-encoding %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=SICI %s
// RUN: not llvm-mc -arch=amdgcn -mcpu=bonaire -show-encoding %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=SICI %s
// RUN: not llvm-mc -arch=amdgcn -mcpu=tonga -show-encoding %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
[AMDGPU][MC] Corrected parser to avoid generation of excessive error messages Summary of changes: - Changed parser to eliminate generation of excessive error messages; - Corrected lit tests to match all expected error messages; - Corrected lit tests to guard against unwanted extra messages (added option "--implicit-check-not=error:"); - Added missing checks and fixed some typos in tests. See bug 46907: https://bugs.llvm.org/show_bug.cgi?id=46907 Reviewers: arsenm, rampitec Differential Revision: https://reviews.llvm.org/D86940
2020-09-03 00:42:18 +08:00
// RUN: not llvm-mc -arch=amdgcn -mcpu=tahiti %s 2>&1 | FileCheck -check-prefixes=GCN-ERR,SICI-ERR --implicit-check-not=error: %s
// RUN: not llvm-mc -arch=amdgcn -mcpu=bonaire %s 2>&1 | FileCheck -check-prefixes=GCN-ERR,SICI-ERR --implicit-check-not=error: %s
// RUN: not llvm-mc -arch=amdgcn -mcpu=tonga %s 2>&1 | FileCheck -check-prefixes=GCN-ERR,VI-ERR --implicit-check-not=error: %s
[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
2017-06-23 00:29:22 +08:00
//===----------------------------------------------------------------------===//
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// Positive tests for legacy dfmt/nfmt syntax.
[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
2017-06-23 00:29:22 +08:00
//===----------------------------------------------------------------------===//
tbuffer_load_format_x v1, off, s[4:7], dfmt:15, nfmt:2, s1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_load_format_x v1, off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x78,0xe9,0x00,0x01,0x01,0x01]
// VI: tbuffer_load_format_x v1, off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x78,0xe9,0x00,0x01,0x01,0x01]
[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
2017-06-23 00:29:22 +08:00
tbuffer_load_format_xy v[1:2], off, s[4:7], dfmt:15, nfmt:2, s1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_load_format_xy v[1:2], off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x79,0xe9,0x00,0x01,0x01,0x01]
// VI: tbuffer_load_format_xy v[1:2], off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x80,0x78,0xe9,0x00,0x01,0x01,0x01]
[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
2017-06-23 00:29:22 +08:00
[AMDGPU] Implemented dwordx3 variants of buffer/tbuffer load/store intrinsics Now we have vec3 MVTs, this commit implements dwordx3 variants of the buffer intrinsics. On gfx6, a dwordx3 buffer load intrinsic is implemented as a dwordx4 instruction, and a dwordx3 buffer store intrinsic is not supported. We need to support the dwordx3 load intrinsic because it is generated by subtarget-unaware code in InstCombine. Differential Revision: https://reviews.llvm.org/D58904 Change-Id: I016729d8557b98a52f529638ae97c340a5922a4e llvm-svn: 356755
2019-03-22 22:58:02 +08:00
tbuffer_load_format_xyz v[1:3], off, s[4:7], dfmt:15, nfmt:2, s1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_load_format_xyz v[1:3], off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x7a,0xe9,0x00,0x01,0x01,0x01]
// VI: tbuffer_load_format_xyz v[1:3], off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x79,0xe9,0x00,0x01,0x01,0x01]
[AMDGPU][MC] Enabled instruction TBUFFER_LOAD_FORMAT_XYZ for SI/CI See bug 36958: https://bugs.llvm.org/show_bug.cgi?id=36958 Differential Revision: https://reviews.llvm.org/D45099 Reviewers: artem.tamazov, arsenm, timcorringham llvm-svn: 329197
2018-04-04 21:54:55 +08:00
[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
2017-06-23 00:29:22 +08:00
tbuffer_load_format_xyzw v[1:4], off, s[4:7], dfmt:15, nfmt:2, s1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_load_format_xyzw v[1:4], off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x7b,0xe9,0x00,0x01,0x01,0x01]
// VI: tbuffer_load_format_xyzw v[1:4], off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x80,0x79,0xe9,0x00,0x01,0x01,0x01]
[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
2017-06-23 00:29:22 +08:00
tbuffer_store_format_x v1, off, s[4:7], dfmt:15, nfmt:2, s1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_store_format_x v1, off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x7c,0xe9,0x00,0x01,0x01,0x01]
// VI: tbuffer_store_format_x v1, off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x7a,0xe9,0x00,0x01,0x01,0x01]
[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
2017-06-23 00:29:22 +08:00
tbuffer_store_format_xy v[1:2], off, s[4:7], dfmt:15, nfmt:2, s1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_store_format_xy v[1:2], off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x7d,0xe9,0x00,0x01,0x01,0x01]
// VI: tbuffer_store_format_xy v[1:2], off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x80,0x7a,0xe9,0x00,0x01,0x01,0x01]
[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
2017-06-23 00:29:22 +08:00
tbuffer_store_format_xyzw v[1:4], off, s[4:7], dfmt:15, nfmt:2, s1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_store_format_xyzw v[1:4], off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x7f,0xe9,0x00,0x01,0x01,0x01]
// VI: tbuffer_store_format_xyzw v[1:4], off, s[4:7], s1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x80,0x7b,0xe9,0x00,0x01,0x01,0x01]
[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
2017-06-23 00:29:22 +08:00
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], dfmt:15, nfmt:2, ttmp1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x7f,0xe9,0x00,0x01,0x1d,0x71]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x80,0x7b,0xe9,0x00,0x01,0x1d,0x71]
[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
2017-06-23 00:29:22 +08:00
[AMDGPU] New tbuffer intrinsics Summary: This commit adds new intrinsics llvm.amdgcn.raw.tbuffer.load llvm.amdgcn.struct.tbuffer.load llvm.amdgcn.raw.tbuffer.store llvm.amdgcn.struct.tbuffer.store with the following changes from the llvm.amdgcn.tbuffer.* intrinsics: * there are separate raw and struct versions: raw does not have an index arg and sets idxen=0 in the instruction, and struct always sets idxen=1 in the instruction even if the index is 0, to allow for the fact that gfx9 does bounds checking differently depending on whether idxen is set; * there is a combined format arg (dfmt+nfmt) * there is a combined cachepolicy arg (glc+slc) * there are now only two offset args: one for the offset that is included in bounds checking and swizzling, to be split between the instruction's voffset and immoffset fields, and one for the offset that is excluded from bounds checking and swizzling, to go into the instruction's soffset field. The AMDISD::TBUFFER_* SD nodes always have an index operand, all three offset operands, combined format operand, combined cachepolicy operand, and an extra idxen operand. The tbuffer pseudo- and real instructions now also have a combined format operand. The obsolescent llvm.amdgcn.tbuffer.* and llvm.SI.tbuffer.store intrinsics continue to work. V2: Separate raw and struct intrinsics. V3: Moved extract_glc and extract_slc defs to a more sensible place. V4: Rebased on D49995. V5: Only two separate offset args instead of three. V6: Pseudo- and real instructions have joint format operand. V7: Restored optionality of dfmt and nfmt in assembler. V8: Addressed minor review comments. Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D49026 Change-Id: If22ad77e349fac3a5d2f72dda53c010377d470d4 llvm-svn: 340268
2018-08-21 19:06:05 +08:00
// nfmt is optional:
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], dfmt:15, ttmp1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_RESERVED_15] ; encoding: [0x00,0x00,0x7f,0xe8,0x00,0x01,0x1d,0x71]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_RESERVED_15] ; encoding: [0x00,0x80,0x7b,0xe8,0x00,0x01,0x1d,0x71]
[AMDGPU] New tbuffer intrinsics Summary: This commit adds new intrinsics llvm.amdgcn.raw.tbuffer.load llvm.amdgcn.struct.tbuffer.load llvm.amdgcn.raw.tbuffer.store llvm.amdgcn.struct.tbuffer.store with the following changes from the llvm.amdgcn.tbuffer.* intrinsics: * there are separate raw and struct versions: raw does not have an index arg and sets idxen=0 in the instruction, and struct always sets idxen=1 in the instruction even if the index is 0, to allow for the fact that gfx9 does bounds checking differently depending on whether idxen is set; * there is a combined format arg (dfmt+nfmt) * there is a combined cachepolicy arg (glc+slc) * there are now only two offset args: one for the offset that is included in bounds checking and swizzling, to be split between the instruction's voffset and immoffset fields, and one for the offset that is excluded from bounds checking and swizzling, to go into the instruction's soffset field. The AMDISD::TBUFFER_* SD nodes always have an index operand, all three offset operands, combined format operand, combined cachepolicy operand, and an extra idxen operand. The tbuffer pseudo- and real instructions now also have a combined format operand. The obsolescent llvm.amdgcn.tbuffer.* and llvm.SI.tbuffer.store intrinsics continue to work. V2: Separate raw and struct intrinsics. V3: Moved extract_glc and extract_slc defs to a more sensible place. V4: Rebased on D49995. V5: Only two separate offset args instead of three. V6: Pseudo- and real instructions have joint format operand. V7: Restored optionality of dfmt and nfmt in assembler. V8: Addressed minor review comments. Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D49026 Change-Id: If22ad77e349fac3a5d2f72dda53c010377d470d4 llvm-svn: 340268
2018-08-21 19:06:05 +08:00
// dfmt is optional:
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], nfmt:2, ttmp1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x0f,0xe9,0x00,0x01,0x1d,0x71]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x80,0x0b,0xe9,0x00,0x01,0x1d,0x71]
[AMDGPU] New tbuffer intrinsics Summary: This commit adds new intrinsics llvm.amdgcn.raw.tbuffer.load llvm.amdgcn.struct.tbuffer.load llvm.amdgcn.raw.tbuffer.store llvm.amdgcn.struct.tbuffer.store with the following changes from the llvm.amdgcn.tbuffer.* intrinsics: * there are separate raw and struct versions: raw does not have an index arg and sets idxen=0 in the instruction, and struct always sets idxen=1 in the instruction even if the index is 0, to allow for the fact that gfx9 does bounds checking differently depending on whether idxen is set; * there is a combined format arg (dfmt+nfmt) * there is a combined cachepolicy arg (glc+slc) * there are now only two offset args: one for the offset that is included in bounds checking and swizzling, to be split between the instruction's voffset and immoffset fields, and one for the offset that is excluded from bounds checking and swizzling, to go into the instruction's soffset field. The AMDISD::TBUFFER_* SD nodes always have an index operand, all three offset operands, combined format operand, combined cachepolicy operand, and an extra idxen operand. The tbuffer pseudo- and real instructions now also have a combined format operand. The obsolescent llvm.amdgcn.tbuffer.* and llvm.SI.tbuffer.store intrinsics continue to work. V2: Separate raw and struct intrinsics. V3: Moved extract_glc and extract_slc defs to a more sensible place. V4: Rebased on D49995. V5: Only two separate offset args instead of three. V6: Pseudo- and real instructions have joint format operand. V7: Restored optionality of dfmt and nfmt in assembler. V8: Addressed minor review comments. Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D49026 Change-Id: If22ad77e349fac3a5d2f72dda53c010377d470d4 llvm-svn: 340268
2018-08-21 19:06:05 +08:00
// nfmt and dfmt can be in either order:
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], nfmt:2, dfmt:15, ttmp1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x7f,0xe9,0x00,0x01,0x1d,0x71]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x80,0x7b,0xe9,0x00,0x01,0x1d,0x71]
[AMDGPU] New tbuffer intrinsics Summary: This commit adds new intrinsics llvm.amdgcn.raw.tbuffer.load llvm.amdgcn.struct.tbuffer.load llvm.amdgcn.raw.tbuffer.store llvm.amdgcn.struct.tbuffer.store with the following changes from the llvm.amdgcn.tbuffer.* intrinsics: * there are separate raw and struct versions: raw does not have an index arg and sets idxen=0 in the instruction, and struct always sets idxen=1 in the instruction even if the index is 0, to allow for the fact that gfx9 does bounds checking differently depending on whether idxen is set; * there is a combined format arg (dfmt+nfmt) * there is a combined cachepolicy arg (glc+slc) * there are now only two offset args: one for the offset that is included in bounds checking and swizzling, to be split between the instruction's voffset and immoffset fields, and one for the offset that is excluded from bounds checking and swizzling, to go into the instruction's soffset field. The AMDISD::TBUFFER_* SD nodes always have an index operand, all three offset operands, combined format operand, combined cachepolicy operand, and an extra idxen operand. The tbuffer pseudo- and real instructions now also have a combined format operand. The obsolescent llvm.amdgcn.tbuffer.* and llvm.SI.tbuffer.store intrinsics continue to work. V2: Separate raw and struct intrinsics. V3: Moved extract_glc and extract_slc defs to a more sensible place. V4: Rebased on D49995. V5: Only two separate offset args instead of three. V6: Pseudo- and real instructions have joint format operand. V7: Restored optionality of dfmt and nfmt in assembler. V8: Addressed minor review comments. Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D49026 Change-Id: If22ad77e349fac3a5d2f72dda53c010377d470d4 llvm-svn: 340268
2018-08-21 19:06:05 +08:00
[AMDGPU][MC] Corrected MTBUF parsing and decoding MTBUF implementation has many issues and this change addresses most of these: - refactored duplicated code; - hardcoded constants moved out of high-level code; - fixed a decoding error when nfmt or dfmt are zero (bug 36932); - corrected parsing of operand separators (bug 46403); - corrected handling of missing operands (bug 46404); - corrected handling of out-of-range modifiers (bug 46421); - corrected default value (bug 46467). Reviewers: arsenm, rampitec, vpykhtin, artem.tamazov, kzhuravl Differential Revision: https://reviews.llvm.org/D83760
2020-07-16 00:44:07 +08:00
// nfmt and dfmt may be omitted:
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 ; encoding: [0x00,0x00,0x0f,0xe8,0x00,0x01,0x1d,0x71]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 ; encoding: [0x00,0x80,0x0b,0xe8,0x00,0x01,0x1d,0x71]
// Check dfmt/nfmt min values
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], dfmt:0, nfmt:0, ttmp1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_INVALID] ; encoding: [0x00,0x00,0x07,0xe8,0x00,0x01,0x1d,0x71]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_INVALID] ; encoding: [0x00,0x80,0x03,0xe8,0x00,0x01,0x1d,0x71]
[AMDGPU][MC] Corrected MTBUF parsing and decoding MTBUF implementation has many issues and this change addresses most of these: - refactored duplicated code; - hardcoded constants moved out of high-level code; - fixed a decoding error when nfmt or dfmt are zero (bug 36932); - corrected parsing of operand separators (bug 46403); - corrected handling of missing operands (bug 46404); - corrected handling of out-of-range modifiers (bug 46421); - corrected default value (bug 46467). Reviewers: arsenm, rampitec, vpykhtin, artem.tamazov, kzhuravl Differential Revision: https://reviews.llvm.org/D83760
2020-07-16 00:44:07 +08:00
// Check dfmt/nfmt max values
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], dfmt:15, nfmt:7, ttmp1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_FLOAT] ; encoding: [0x00,0x00,0xff,0xeb,0x00,0x01,0x1d,0x71]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_FLOAT] ; encoding: [0x00,0x80,0xfb,0xeb,0x00,0x01,0x1d,0x71]
[AMDGPU][MC] Corrected MTBUF parsing and decoding MTBUF implementation has many issues and this change addresses most of these: - refactored duplicated code; - hardcoded constants moved out of high-level code; - fixed a decoding error when nfmt or dfmt are zero (bug 36932); - corrected parsing of operand separators (bug 46403); - corrected handling of missing operands (bug 46404); - corrected handling of out-of-range modifiers (bug 46421); - corrected default value (bug 46467). Reviewers: arsenm, rampitec, vpykhtin, artem.tamazov, kzhuravl Differential Revision: https://reviews.llvm.org/D83760
2020-07-16 00:44:07 +08:00
// Check default dfmt/nfmt values
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], dfmt:1, nfmt:0, ttmp1
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 ; encoding: [0x00,0x00,0x0f,0xe8,0x00,0x01,0x1d,0x71]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 ; encoding: [0x00,0x80,0x0b,0xe8,0x00,0x01,0x1d,0x71]
// Check that comma separators are optional
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] dfmt:15 nfmt:7 ttmp1
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_FLOAT] ; encoding: [0x00,0x00,0xff,0xeb,0x00,0x01,0x1d,0x71]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_FLOAT] ; encoding: [0x00,0x80,0xfb,0xeb,0x00,0x01,0x1d,0x71]
dfmt=15
nfmt=7
// Check expressions with dfmt
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] dfmt:-1+dfmt+1 nfmt:nfmt ttmp1
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_FLOAT] ; encoding: [0x00,0x00,0xff,0xeb,0x00,0x01,0x1d,0x71]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], ttmp1 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_FLOAT] ; encoding: [0x00,0x80,0xfb,0xeb,0x00,0x01,0x1d,0x71]
[AMDGPU][MC] Corrected MTBUF parsing and decoding MTBUF implementation has many issues and this change addresses most of these: - refactored duplicated code; - hardcoded constants moved out of high-level code; - fixed a decoding error when nfmt or dfmt are zero (bug 36932); - corrected parsing of operand separators (bug 46403); - corrected handling of missing operands (bug 46404); - corrected handling of out-of-range modifiers (bug 46421); - corrected default value (bug 46467). Reviewers: arsenm, rampitec, vpykhtin, artem.tamazov, kzhuravl Differential Revision: https://reviews.llvm.org/D83760
2020-07-16 00:44:07 +08:00
//===----------------------------------------------------------------------===//
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// Negative tests for legacy dfmt/nfmt syntax.
[AMDGPU][MC] Corrected MTBUF parsing and decoding MTBUF implementation has many issues and this change addresses most of these: - refactored duplicated code; - hardcoded constants moved out of high-level code; - fixed a decoding error when nfmt or dfmt are zero (bug 36932); - corrected parsing of operand separators (bug 46403); - corrected handling of missing operands (bug 46404); - corrected handling of out-of-range modifiers (bug 46421); - corrected default value (bug 46467). Reviewers: arsenm, rampitec, vpykhtin, artem.tamazov, kzhuravl Differential Revision: https://reviews.llvm.org/D83760
2020-07-16 00:44:07 +08:00
//===----------------------------------------------------------------------===//
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] dfmt:-1 nfmt:1 s0
// GCN-ERR: error: out of range dfmt
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] dfmt:16 nfmt:1 s0
// GCN-ERR: error: out of range dfmt
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] dfmt:1 nfmt:-1 s0
// GCN-ERR: error: out of range nfmt
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] dfmt:1 nfmt:8 s0
// GCN-ERR: error: out of range nfmt
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7]
// GCN-ERR: error: too few operands for instruction
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7],, dfmt:1 nfmt:1 s0
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// GCN-ERR: error: unknown token in expression
[AMDGPU][MC] Corrected MTBUF parsing and decoding MTBUF implementation has many issues and this change addresses most of these: - refactored duplicated code; - hardcoded constants moved out of high-level code; - fixed a decoding error when nfmt or dfmt are zero (bug 36932); - corrected parsing of operand separators (bug 46403); - corrected handling of missing operands (bug 46404); - corrected handling of out-of-range modifiers (bug 46421); - corrected default value (bug 46467). Reviewers: arsenm, rampitec, vpykhtin, artem.tamazov, kzhuravl Differential Revision: https://reviews.llvm.org/D83760
2020-07-16 00:44:07 +08:00
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] dfmt:1,, nfmt:1 s0
// GCN-ERR: error: unknown token in expression
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] dfmt:1 nfmt:1,, s0
// GCN-ERR: error: unknown token in expression
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] dfmt:1 dfmt:1 s0
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// GCN-ERR: error: invalid operand for instruction
[AMDGPU][MC] Corrected MTBUF parsing and decoding MTBUF implementation has many issues and this change addresses most of these: - refactored duplicated code; - hardcoded constants moved out of high-level code; - fixed a decoding error when nfmt or dfmt are zero (bug 36932); - corrected parsing of operand separators (bug 46403); - corrected handling of missing operands (bug 46404); - corrected handling of out-of-range modifiers (bug 46421); - corrected default value (bug 46467). Reviewers: arsenm, rampitec, vpykhtin, artem.tamazov, kzhuravl Differential Revision: https://reviews.llvm.org/D83760
2020-07-16 00:44:07 +08:00
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] nfmt:1 nfmt:1 s0
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// GCN-ERR: error: invalid operand for instruction
[AMDGPU][MC] Corrected MTBUF parsing and decoding MTBUF implementation has many issues and this change addresses most of these: - refactored duplicated code; - hardcoded constants moved out of high-level code; - fixed a decoding error when nfmt or dfmt are zero (bug 36932); - corrected parsing of operand separators (bug 46403); - corrected handling of missing operands (bug 46404); - corrected handling of out-of-range modifiers (bug 46421); - corrected default value (bug 46467). Reviewers: arsenm, rampitec, vpykhtin, artem.tamazov, kzhuravl Differential Revision: https://reviews.llvm.org/D83760
2020-07-16 00:44:07 +08:00
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] dfmt:1 nfmt:1 dfmt:1 s0
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// GCN-ERR: error: invalid operand for instruction
[AMDGPU][MC] Corrected MTBUF parsing and decoding MTBUF implementation has many issues and this change addresses most of these: - refactored duplicated code; - hardcoded constants moved out of high-level code; - fixed a decoding error when nfmt or dfmt are zero (bug 36932); - corrected parsing of operand separators (bug 46403); - corrected handling of missing operands (bug 46404); - corrected handling of out-of-range modifiers (bug 46421); - corrected default value (bug 46467). Reviewers: arsenm, rampitec, vpykhtin, artem.tamazov, kzhuravl Differential Revision: https://reviews.llvm.org/D83760
2020-07-16 00:44:07 +08:00
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] nfmt:1 dfmt:1 nfmt:1 s0
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
// GCN-ERR: error: invalid operand for instruction
[AMDGPU][MC] Corrected MTBUF parsing and decoding MTBUF implementation has many issues and this change addresses most of these: - refactored duplicated code; - hardcoded constants moved out of high-level code; - fixed a decoding error when nfmt or dfmt are zero (bug 36932); - corrected parsing of operand separators (bug 46403); - corrected handling of missing operands (bug 46404); - corrected handling of out-of-range modifiers (bug 46421); - corrected default value (bug 46467). Reviewers: arsenm, rampitec, vpykhtin, artem.tamazov, kzhuravl Differential Revision: https://reviews.llvm.org/D83760
2020-07-16 00:44:07 +08:00
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] dfmt:1: nfmt:1 s0
// GCN-ERR: error: unknown token in expression
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7] dfmt:1 nfmt:1: s0
// GCN-ERR: error: unknown token in expression
[AMDGPU][MC] Added support of SP3 syntax for MTBUF format modifier Currently supported LLVM MTBUF syntax is shown below. It is not compatible with SP3. op dst, addr, rsrc, FORMAT, soffset This change adds support for SP3 syntax: op dst, addr, rsrc, soffset SP3FORMAT In addition to being compatible with SP3, this syntax allows using symbolic names for data, numeric and unified formats. Below is a list of added syntax variants. format:<expression> format:[<numeric-format-name>,<data-format-name>] format:[<data-format-name>,<numeric-format-name>] format:[<data-format-name>] format:[<numeric-format-name>] format:[<unified-format-name>] The last syntax variant is supported for GFX10 only. See llvm bug 37738 Reviewers: arsenm, rampitec, vpykhtin Differential Revision: https://reviews.llvm.org/D84026
2020-07-24 21:39:42 +08:00
//===----------------------------------------------------------------------===//
// Tests for symbolic MTBUF format
//===----------------------------------------------------------------------===//
// Format may be specified in numeric form (min value).
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:0
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_INVALID] ; encoding: [0x00,0x00,0x07,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_INVALID] ; encoding: [0x00,0x80,0x03,0xe8,0x00,0x01,0x1d,0x00]
// Format may be specified in numeric form (max value).
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:127
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_FLOAT] ; encoding: [0x00,0x00,0xff,0xeb,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_RESERVED_15,BUF_NUM_FORMAT_FLOAT] ; encoding: [0x00,0x80,0xfb,0xeb,0x00,0x01,0x1d,0x00]
// Format may be specified as an expression.
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:(2 + 3 * 16)
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_16,BUF_NUM_FORMAT_SSCALED] ; encoding: [0x00,0x00,0x97,0xe9,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_16,BUF_NUM_FORMAT_SSCALED] ; encoding: [0x00,0x80,0x93,0xe9,0x00,0x01,0x1d,0x00]
// format may be specified as a list of dfmt, nfmt:
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_8,BUF_NUM_FORMAT_UNORM]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 ; encoding: [0x00,0x00,0x0f,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 ; encoding: [0x00,0x80,0x0b,0xe8,0x00,0x01,0x1d,0x00]
// nfmt and dfmt can be in either order:
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_SNORM, BUF_DATA_FORMAT_16]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_16,BUF_NUM_FORMAT_SNORM] ; encoding: [0x00,0x00,0x97,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_16,BUF_NUM_FORMAT_SNORM] ; encoding: [0x00,0x80,0x93,0xe8,0x00,0x01,0x1d,0x00]
// nfmt may be omitted:
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[ BUF_DATA_FORMAT_8_8 ]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_8_8] ; encoding: [0x00,0x00,0x1f,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_8_8] ; encoding: [0x00,0x80,0x1b,0xe8,0x00,0x01,0x1d,0x00]
// dfmt may be omitted:
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_USCALED]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x00,0x0f,0xe9,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_USCALED] ; encoding: [0x00,0x80,0x0b,0xe9,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32] ; encoding: [0x00,0x00,0x27,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32] ; encoding: [0x00,0x80,0x23,0xe8,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_16_16]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_16_16] ; encoding: [0x00,0x00,0x2f,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_16_16] ; encoding: [0x00,0x80,0x2b,0xe8,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_10_11_11]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_10_11_11] ; encoding: [0x00,0x00,0x37,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_10_11_11] ; encoding: [0x00,0x80,0x33,0xe8,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_11_11_10]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_11_11_10] ; encoding: [0x00,0x00,0x3f,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_11_11_10] ; encoding: [0x00,0x80,0x3b,0xe8,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_10_10_10_2]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_10_10_10_2] ; encoding: [0x00,0x00,0x47,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_10_10_10_2] ; encoding: [0x00,0x80,0x43,0xe8,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_2_10_10_10]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_2_10_10_10] ; encoding: [0x00,0x00,0x4f,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_2_10_10_10] ; encoding: [0x00,0x80,0x4b,0xe8,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_8_8_8_8]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_8_8_8_8] ; encoding: [0x00,0x00,0x57,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_8_8_8_8] ; encoding: [0x00,0x80,0x53,0xe8,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32_32]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32_32] ; encoding: [0x00,0x00,0x5f,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32_32] ; encoding: [0x00,0x80,0x5b,0xe8,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_16_16_16_16]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_16_16_16_16] ; encoding: [0x00,0x00,0x67,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_16_16_16_16] ; encoding: [0x00,0x80,0x63,0xe8,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32_32_32]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32_32_32] ; encoding: [0x00,0x00,0x6f,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32_32_32] ; encoding: [0x00,0x80,0x6b,0xe8,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32_32_32_32]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32_32_32_32] ; encoding: [0x00,0x00,0x77,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32_32_32_32] ; encoding: [0x00,0x80,0x73,0xe8,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_RESERVED_15]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_RESERVED_15] ; encoding: [0x00,0x00,0x7f,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_RESERVED_15] ; encoding: [0x00,0x80,0x7b,0xe8,0x00,0x01,0x1d,0x00]
// Check dfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_INVALID]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_INVALID] ; encoding: [0x00,0x00,0x07,0xe8,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_INVALID] ; encoding: [0x00,0x80,0x03,0xe8,0x00,0x01,0x1d,0x00]
// Check nfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_SSCALED]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_SSCALED] ; encoding: [0x00,0x00,0x8f,0xe9,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_SSCALED] ; encoding: [0x00,0x80,0x8b,0xe9,0x00,0x01,0x1d,0x00]
// Check nfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_UINT]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_UINT] ; encoding: [0x00,0x00,0x0f,0xea,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_UINT] ; encoding: [0x00,0x80,0x0b,0xea,0x00,0x01,0x1d,0x00]
// Check nfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_SINT]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_SINT] ; encoding: [0x00,0x00,0x8f,0xea,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_SINT] ; encoding: [0x00,0x80,0x8b,0xea,0x00,0x01,0x1d,0x00]
// Check nfmt formats
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_FLOAT]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_FLOAT] ; encoding: [0x00,0x00,0x8f,0xeb,0x00,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_FLOAT] ; encoding: [0x00,0x80,0x8b,0xeb,0x00,0x01,0x1d,0x00]
// Check optional comma separators
tbuffer_store_format_xyzw v[1:4], v1, ttmp[4:7], s0, format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT], idxen
// SICI: tbuffer_store_format_xyzw v[1:4], v1, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] idxen ; encoding: [0x00,0x20,0xa7,0xeb,0x01,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], v1, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] idxen ; encoding: [0x00,0xa0,0xa3,0xeb,0x01,0x01,0x1d,0x00]
// Check offen and offset
tbuffer_store_format_xyzw v[1:4], v1, ttmp[4:7], s0, format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] offen offset:52
// SICI: tbuffer_store_format_xyzw v[1:4], v1, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] offen offset:52 ; encoding: [0x34,0x10,0xa7,0xeb,0x01,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], v1, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] offen offset:52 ; encoding: [0x34,0x90,0xa3,0xeb,0x01,0x01,0x1d,0x00]
// Check idxen and offen
tbuffer_store_format_xyzw v[1:4], v[1:2], ttmp[4:7], s0, format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] idxen offen offset:52
// SICI: tbuffer_store_format_xyzw v[1:4], v[1:2], ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] idxen offen offset:52 ; encoding: [0x34,0x30,0xa7,0xeb,0x01,0x01,0x1d,0x00]
// VI: tbuffer_store_format_xyzw v[1:4], v[1:2], ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] idxen offen offset:52 ; encoding: [0x34,0xb0,0xa3,0xeb,0x01,0x01,0x1d,0x00]
// Check addr64
tbuffer_store_format_xyzw v[1:4], v[1:2], ttmp[4:7], s0, format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] addr64
// SICI: tbuffer_store_format_xyzw v[1:4], v[1:2], ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] addr64 ; encoding: [0x00,0x80,0xa7,0xeb,0x01,0x01,0x1d,0x00]
// VI-ERR: error: instruction not supported on this GPU
//===----------------------------------------------------------------------===//
// Tests for symbolic format errors handling
//===----------------------------------------------------------------------===//
// Missing soffset
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], format:[BUF_DATA_FORMAT_32]
// GCN-ERR: error: not a valid operand.
// Invalid soffset
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s[255] format:[BUF_NUM_FORMAT_FLOAT]
// GCN-ERR: error: not a valid operand.
// Both legacy and symbolic formats are specified
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], dfmt:1 s0 format:[BUF_NUM_FORMAT_FLOAT]
// GCN-ERR: error: duplicate format
// Missing format number
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format: offset:52
// GCN-ERR: error: expected absolute expression
// Invalid number
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:-1
// GCN-ERR: error: out of range format
// Invalid number
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:128
// GCN-ERR: error: out of range format
MAXVAL=127
// Invalid expression
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:MAXVAL+1
// GCN-ERR: error: out of range format
// Empty list
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[]
// GCN-ERR: error: expected a format string
// More than 2 format specifiers
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT,BUF_DATA_FORMAT_8]
// GCN-ERR: error: expected a closing square bracket
// More than 2 format specifiers
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_UINT,BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT]
// GCN-ERR: error: expected a closing square bracket
// Missing brackets
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:BUF_NUM_FORMAT_UINT
// GCN-ERR: error: expected absolute expression
// Unpaired brackets
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_UINT
// GCN-ERR: error: expected a closing square bracket
// Unpaired brackets
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:BUF_NUM_FORMAT_UINT]
// GCN-ERR: error: expected absolute expression
// Missing comma
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_UINT BUF_DATA_FORMAT_32]
// GCN-ERR: error: expected a closing square bracket
// Duplicate dfmt
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32,BUF_DATA_FORMAT_32]
// GCN-ERR: error: duplicate data format
// Duplicate dfmt
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_32,BUF_DATA_FORMAT_8]
// GCN-ERR: error: duplicate data format
// Duplicate nfmt
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_UINT,BUF_NUM_FORMAT_FLOAT]
// GCN-ERR: error: duplicate numeric format
// Unknown format specifier
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT]
// GCN-ERR: error: unsupported format
// Valid but unsupported format specifier (SNORM_OGL is supported for SI/CI only)
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_SNORM_OGL]
// SICI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_SNORM_OGL] ; encoding: [0x00,0x00,0x0f,0xeb,0x00,0x01,0x1d,0x00]
// VI-ERR: error: unsupported format
// Valid but unsupported format specifier (RESERVED_6 is supported for VI/GFX9 only)
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_RESERVED_6]
// SICI-ERR: error: unsupported format
// VI: tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_NUM_FORMAT_RESERVED_6] ; encoding: [0x00,0x80,0x0b,0xeb,0x00,0x01,0x1d,0x00]
// Excessive commas
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7],, s0 format:[BUF_DATA_FORMAT_8]
// GCN-ERR: error: unknown token in expression
// Excessive commas
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0,, format:[BUF_DATA_FORMAT_8]
// GCN-ERR: error: not a valid operand.
// Excessive commas
tbuffer_store_format_xyzw v[1:4], off, ttmp[4:7], s0 format:[BUF_DATA_FORMAT_8],, offset:52
// GCN-ERR: error: unknown token in expression