summaryrefslogtreecommitdiff
path: root/generic/lib/shared
AgeCommit message (Collapse)AuthorFilesLines
2013-07-16Fix and re-enable R600 vload/vstore assemblyAaron Watry2-56/+35
The assembly optimizations were making unsafe assumptions about which address spaces had which identifiers. Also, fix vload/vstore with 64-bit pointers. This was broken previously on Radeon SI. This version still only has assembly versions of int/uint 2/4/8/16 for global loads and stores on R600, but it does it in a way that would be very easily extended to private/local/constant and could also be handled easily on other architectures. v2: 1) Leave v[load|store]_impl.ll in generic/lib 2) Remove vload_if.ll and vstore_if.ll interfaces 3) Fix address+offset calculations 3) Remove offset from assembly arg list git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@186416 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-16libclc: vload/vstore disable assembly and fix offset calculationAaron Watry4-243/+20
This commit gets us back to pure CLC and fixes offset calculations. The next commit will re-enable the assembly implementation for R600, fix bugs related to 64-bit address spaces, and also fix the incorrect assumption that address space identifiers are the same in all architectures. git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@186415 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-08Add __CLC_ prefix to all macro definitions in headersTom Stellard8-30/+30
libclc was defining and undefing GENTYPE and several other macros with common names in its header files. This was preventing applications from defining macros with identical names as command line arguments to the compiler, because the definitions in the header files were masking the macros defined as compiler arguements. Reviewed-by: Aaron Watry <awatry@gmail.com> git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@185838 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-26libclc: Add assembly versions of vstore for global [u]int4/8/16Tom Stellard3-6/+166
The assembly should be generic, but at least currently R600 only supports 32-bit stores of [u]int1/4, and I believe that only global is well-supported. R600 lowers the 8/16 component stores to multiple 4-component stores. The unoptimized C versions of the other stuff is left in place. Patch by: Aaron Watry git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@185009 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-26libclc: Add assembly versions of vload for global int4/8/16Tom Stellard3-2/+160
The assembly should be generic, but at least currently R600 only supports 32-bit loads of int1/4, and I believe that only global is well-supported. R600 lowers the 8/16 component vectors to multiple 4-bit loads. The unoptimized C versions of the other stuff is left in place. Patch by: Aaron Watry git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@185008 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-26libclc: Initial vstore implementationTom Stellard1-0/+56
Assumes that the target supports byte-addressable stores. Completely unoptimized. Patch by: Aaron Watry git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@185007 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-26libclc: Initial vload implementationTom Stellard1-0/+47
Should work for all targets and data types. Completely unoptimized. Patch by: Aaron Watry git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@185006 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-26libclc: Add clamp(vec, scalar, scalar) and max(vec, scalar)Tom Stellard2-0/+12
For any GENTYPE that isn't scalar, we need to implement a mixed vector/scalar version of clamp/max. This depends on the min() patches I sent to the list a few minutes ago. Patch by: Aaron Watry git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@185003 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-26libclc: Implement the min(vec, scalar) version of the min builtin.Tom Stellard1-0/+6
Checks if the current GENTYPE is scalar, and if not, then defines a separate implementation of the function which casts the second arg to vector before proceeding. Patch by: Aaron Watry git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@185002 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-26libclc: implement initial version of min()Tom Stellard2-0/+14
This doesn't handle the integer cases for min(vector, scalar). Patch by: Aaron Watry git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@185001 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-26libclc: Move max builtin to shared/Tom Stellard2-0/+14
Max(x,y) is available for all integer/floating types. Patch by: Aaron Watry git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@184995 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-26libclc: Add clamp() builtin for integer/floating pointTom Stellard2-0/+14
Created under a new shared/ directory for functions which are available for both integer and floating point types. Patch by: Aaron Watry git-svn-id: https://llvm.org/svn/llvm-project/libclc/trunk@184994 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3 (git 2.39.1) at 2025-05-04 13:06:05 +0000