summaryrefslogtreecommitdiff
path: root/test/CodeGen/NVPTX
AgeCommit message (Expand)Author
2017-01-18[NVPTX] Implement min/max in tablegen, rather than with custom DAGComine logic.Justin Lebar
2017-01-18[NVPTX] Lower integer absolute value idiom to abs instruction.Justin Lebar
2017-01-18[NVPTX] Improve lowering of llvm.ctpop.Justin Lebar
2017-01-18[NVPTX] Add lowering for llvm.bitreverse.Justin Lebar
2017-01-18[NVPTX] Fix function names in ctlz.ll test. Test-only change.Justin Lebar
2017-01-18[NVPTX] Improve lowering of llvm.ctlz.Justin Lebar
2017-01-15[NVPTX] Add fptosi tests to convert-fp.ll.Justin Lebar
2017-01-15[NVPTX] Add codegen tests for llvm.fma.Justin Lebar
2017-01-15[NVPTX] Modernize intrinics.ll test.Justin Lebar
2017-01-15[NVPTX] Let there be One True Way to set NVVMReflect params.Justin Lebar
2017-01-13[NVPTX] Added support for half-precision floating point.Artem Belevich
2017-01-13[NVPTX] Only lower sin/cos to approximate instructions if unsafe math is allo...Artem Belevich
2017-01-10[TM] Restore default TargetOptions in TargetMachine::resetTargetOptions.Justin Lebar
2017-01-10[NVPTX] Add CHECK-LABEL where appropriate to fast-math.ll test.Justin Lebar
2017-01-06[SelectionDAG] Correctly transform range metadata to AssertZExtDavid Majnemer
2016-12-22[NVVMIntrRange] Only set range metadata if none is already presentDavid Majnemer
2016-12-20[IR] Remove the DIExpression field from DIGlobalVariable.Adrian Prantl
2016-12-16Revert "[IR] Remove the DIExpression field from DIGlobalVariable."Adrian Prantl
2016-12-16[IR] Remove the DIExpression field from DIGlobalVariable.Adrian Prantl
2016-12-16Revert "[IR] Remove the DIExpression field from DIGlobalVariable."Adrian Prantl
2016-12-16[IR] Remove the DIExpression field from DIGlobalVariable.Adrian Prantl
2016-12-14Whitespace cleanup in test/CodeGen/NVPTX/annotations.ll.Justin Lebar
2016-12-14[NVPTX] Support .maxnreg annotation.Justin Lebar
2016-10-31[NVPTX] Remove NVPTXFavorNonGenericAddrSpaces pass.Justin Lebar
2016-10-28[NVPTX] Compute 'rem' using the result of 'div', if possible.Justin Lebar
2016-09-28[NVPTX] Added intrinsics for atom.gen.{sys|cta}.* instructions.Artem Belevich
2016-09-21llvm/test/CodeGen/NVPTX/zero-cs.ll: Relax an expression to match in -Asserts.NAKAMURA Takumi
2016-09-21[NVPTX] Check if callsite is defined when computing argument allignmentJacques Pienaar
2016-09-13DebugInfo: New metadata representation for global variables.Peter Collingbourne
2016-09-11[NVPTX] Use ldg for explicitly invariant loads.Justin Lebar
2016-09-09[NVPTX] Implement llvm.fabs.f32, llvm.max.f32, etc.Justin Lebar
2016-08-19[NVPTX] Switch nvptx-use-infer-addrspace to true.Justin Lebar
2016-08-12[NVPTX] Use untyped (.b) integer registers in PTX.Artem Belevich
2016-08-02[NVPTX] remove unnecessary named metadata update that happens to break debug ...Artem Belevich
2016-07-26Fix NVPTX/call-with-alloca-buffer.ll after r276777.Justin Lebar
2016-07-20[NVPTX] Enable the load-store vectorizer on nvptx.Justin Lebar
2016-07-20[NVPTX] Renamed NVPTXLowerKernelArgs -> NVPTXLowerArgs. NFC.Artem Belevich
2016-07-20[NVPTX] deal with all aggregate return types.Artem Belevich
2016-07-20[NVPTX] Improve lowering of byval args of device functions.Artem Belevich
2016-07-18[NVPTX] Make sure we adjust alignment at all call sitesArtem Belevich
2016-07-18[NVPTX] Force minimum alignment of 4 for byval arguments of device-side funct...Artem Belevich
2016-07-07NVPTX: Remove the legacy ptx intrinsicsJustin Bogner
2016-07-06[NVPTX] Add sm_60, sm_61, sm_62 targets to LLVM.Justin Lebar
2016-07-06NVPTX: Replace uses of cuda.syncthreads with nvvm.barrier0Justin Bogner
2016-06-29Revert r273313 "[NVPTX] Improve lowering of byval args of device functions."Artem Belevich
2016-06-27Only emit extension for zeroext/signext arguments if type is < 32 bitsJustin Holewinski
2016-06-21[NVPTX] Improve lowering of byval args of device functions.Artem Belevich
2016-06-09[NVPTX] Add intrinsics for shfl instructions.Justin Lebar
2016-05-26[NVPTX] Added NVVMIntrRange passArtem Belevich
2016-05-02[NVPTX] Fix sign/zero-extending ldg/ldu instruction selectionJustin Holewinski
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-20 21:20:19 +0000