summaryrefslogtreecommitdiff
path: root/test/CodeGen/R600
Commit message (Collapse)AuthorAge
* R600/SI: Implement fp32<->fp64 conversionsNiels Ole Salscheider2013-08-08
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187988 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Implement sint<->fp64 conversionsNiels Ole Salscheider2013-08-08
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187987 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Use VSrc_* register classes as the default classes for typesTom Stellard2013-08-06
| | | | | | | | | | | | | | | | | Since the VSrc_* register classes contain both VGPRs and SGPRs, copies that used be emitted by isel like this: SGPR = COPY VGPR Will now be emitted like this: VSrC = COPY VGPR This patch also adds a pass that tries to identify and fix situations where a VGPR to SGPR copy may occur. Hopefully, these changes will make it impossible for the compiler to generate illegal VGPR to SGPR copies. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187831 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Add more special cases for opcodes to ensureSRegLimit()Tom Stellard2013-08-06
| | | | | | Also factor out the register class lookup to its own function. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187830 91177308-0d34-0410-b5e6-96231b3b80d8
* Factor FlattenCFG out from SimplifyCFGTom Stellard2013-08-06
| | | | | | Patch by: Mei Ye git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187764 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Add missing test for r187749Tom Stellard2013-08-05
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187754 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Add 64-bit float load/store supportTom Stellard2013-08-01
| | | | | | | | | | | | | | | | | | * Added R600_Reg64 class * Added T#Index#.XY registers definition * Added v2i32 register reads from parameter and global space * Added f32 and i32 elements extraction from v2f32 and v2i32 * Added v2i32 -> v2f32 conversions Tom Stellard: - Mark vec2 operations as expand. The addition of a vec2 register class made them all legal. Patch by: Dmitry Cherkassov Signed-off-by: Dmitry Cherkassov <dcherkassov@gmail.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187582 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Use 64-bit alignment for 64-bit kernel argumentsTom Stellard2013-08-01
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187581 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Custom lower i64 ZERO_EXTENDTom Stellard2013-08-01
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187580 91177308-0d34-0410-b5e6-96231b3b80d8
* Revert "R600: Non vector only instruction can be scheduled on trans unit"Tom Stellard2013-07-31
| | | | | | This reverts commit 98ce62780ea7185ba710868bf83c8077e8d7f6d6. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187526 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Avoid more than 4 literals in the same instruction group at schedulingVincent Lejeune2013-07-31
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187515 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Non vector only instruction can be scheduled on trans unitVincent Lejeune2013-07-31
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187514 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Expand vector fp <-> int conversionsTom Stellard2013-07-30
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187421 91177308-0d34-0410-b5e6-96231b3b80d8
* [R600] Replicate old DAGCombiner behavior in target specific DAG combine.Quentin Colombet2013-07-30
| | | | | | | | build_vector is lowered to REG_SEQUENCE, which is something the register allocator does a good job at optimizing. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187397 91177308-0d34-0410-b5e6-96231b3b80d8
* [DAGCombiner] insert_vector_elt: Avoid building a vector twice.Quentin Colombet2013-07-30
| | | | | | | | | | | | | | | | | | This patch prevents the following combine when the input vector is used more than once. insert_vector_elt (build_vector elt0, ..., eltN), NewEltIdx, idx => build_vector elt0, ..., NewEltIdx, ..., eltN The reasons are: - Building a vector may be expensive, so try to reuse the existing part of a vector instead of creating a new one (think big vectors). - elt0 to eltN now have two users instead of one. This may prevent some other optimizations. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187396 91177308-0d34-0410-b5e6-96231b3b80d8
* DAGCombiner: Pass the correct type to TargetLowering::isF(Abs|Neg)FreeTom Stellard2013-07-23
| | | | | | | This commit also implements these functions for R600 and removes a test case that was relying on the buggy behavior. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187007 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Treat CONSTANT_ADDRESS loads like GLOBAL_ADDRESS loads when necessaryTom Stellard2013-07-23
| | | | | | | | | | These are really the same address space in hardware. The only difference is that CONSTANT_ADDRESS uses a special cache for faster access. When we are unable to use the constant kcache for some reason (e.g. smaller types or lack of indirect addressing) then the instruction selector must use GLOBAL_ADDRESS loads instead. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187006 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Add support for 24-bit MAD instructionsTom Stellard2013-07-23
| | | | | | Reviewed-by: Vincent Lejeune <vljn at ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186923 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Add support for 24-bit MUL instructionsTom Stellard2013-07-23
| | | | | | Reviewed-by: Vincent Lejeune <vljn at ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186922 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Improve support for < 32-bit loadsTom Stellard2013-07-23
| | | | | | Reviewed-by: Vincent Lejeune <vljn at ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186921 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Move CONST_ADDRESS folding into AMDGPUDAGToDAGISel::Select()Tom Stellard2013-07-23
| | | | | | | | | | | This increases the number of opportunites we have for folding. With the previous implementation we were unable to fold into any instructions other than the first when multiple instructions were selected from a single SDNode. Reviewed-by: Vincent Lejeune <vljn at ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186919 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Use KCache for kernel argumentsTom Stellard2013-07-23
| | | | | | Reviewed-by: Vincent Lejeune <vljn at ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186918 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Use the same compute kernel calling convention for all GPUsTom Stellard2013-07-23
| | | | | | | | | A side-effect of this is that now the compiler expects kernel arguments to be 4-byte aligned. Reviewed-by: Vincent Lejeune <vljn at ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186916 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Use correct LoadExtType when lowering kernel argumentsTom Stellard2013-07-23
| | | | | | Reviewed-by: Vincent Lejeune <vljn at ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186915 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Clean up extended load patternsTom Stellard2013-07-23
| | | | | | Reviewed-by: Vincent Lejeune <vljn at ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186914 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Expand vector FNEGTom Stellard2013-07-23
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186913 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Don't emit empty then clause and use alu_pop_afterVincent Lejeune2013-07-19
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186725 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Fix crash with VSELECTTom Stellard2013-07-18
| | | | | | https://bugs.freedesktop.org/show_bug.cgi?id=66175 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186616 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Add support for v2f32 loadsTom Stellard2013-07-18
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186615 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Add support for v2f32 storesTom Stellard2013-07-18
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186614 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Expand VSELECT for all typesTom Stellard2013-07-18
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186613 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Add support for 64-bit loadsTom Stellard2013-07-15
| | | | | | https://bugs.freedesktop.org/show_bug.cgi?id=65873 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186339 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Reapply testcase from r186178, the big endian issue should be fixed by ↵Benjamin Kramer2013-07-12
| | | | | | r186196. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186209 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Remove the fpconst64.ll test which was failing on non-x86 buildbotsTom Stellard2013-07-12
| | | | | | | I'm guessing the failure had something to do with the double precision floating point constant used in the test. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186191 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Add support for f64 kernel argumentsTom Stellard2013-07-12
| | | | | | | | Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186182 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Implement select and compares for SITom Stellard2013-07-12
| | | | | | | | Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186181 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Add fsqrt pattern for SITom Stellard2013-07-12
| | | | | | | | Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186180 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Add double precision fsub pattern for SITom Stellard2013-07-12
| | | | | | | | Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186179 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: SI support for 64bit ConstantFPTom Stellard2013-07-12
| | | | | | | | Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186178 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Add initial double precision support for SITom Stellard2013-07-12
| | | | | | | | Patch by: Niels Ole Salscheider Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186177 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Initial local memory supportMichel Danzer2013-07-10
| | | | | | | | Enough for the radeonsi driver to use it for calculating derivatives. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186012 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Add intrinsic for retrieving the current thread IDMichel Danzer2013-07-10
| | | | | | Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186010 91177308-0d34-0410-b5e6-96231b3b80d8
* R600/SI: Add intrinsics for texture sampling with user derivativesMichel Danzer2013-07-10
| | | | | | Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186008 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Do not predicated basic block with multiple alu clauseVincent Lejeune2013-07-09
| | | | | | | | | | Test is not included as it is several 1000 lines long. To test this functionnality, a test case must generate at least 2 ALU clauses, where an ALU clause is ~110 instructions long. NOTE: This is a candidate for the stable branch. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185943 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Fix a rare bug where swizzle optimization returns wrong valuesVincent Lejeune2013-07-09
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185942 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Fix wrong export reswizzlingVincent Lejeune2013-07-09
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185941 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Use DAG lowering pass to handle fcos/fsinVincent Lejeune2013-07-09
| | | | | | NOTE: This is a candidate for the stable branch. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185940 91177308-0d34-0410-b5e6-96231b3b80d8
* Prefix failing commands with not to make clear they are expected to fail.Rafael Espindola2013-07-03
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185554 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Support schedule and packetization of trans-only instVincent Lejeune2013-06-29
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185268 91177308-0d34-0410-b5e6-96231b3b80d8
* R600: Add local memory support via LDSTom Stellard2013-06-28
| | | | | | Reviewed-by: Vincent Lejeune<vljn at ovi.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185162 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-14 19:46:15 +0000