Show patches with: Submitter = Andrew Stubbs       |   79 patches
Patch Series A/R/T S/W/F Date Submitter Delegate State
[committed] amdgcn: Match new XNACK defaults in mkoffload [committed] amdgcn: Match new XNACK defaults in mkoffload - - - -1- 2024-01-08 Andrew Stubbs Repeat Merge
[committed] amdgcn: Don't double-count AVGPRs [committed] amdgcn: Don't double-count AVGPRs - - - -1- 2024-01-08 Andrew Stubbs Repeat Merge
[committed] amdgcn: XNACK support [committed] amdgcn: XNACK support - - - --1 2023-12-13 Andrew Stubbs Not Applicable
[v3,6/6] libgomp: fine-grained pinned memory allocator libgomp: OpenMP pinned memory omp_alloc - - - -1- 2023-12-11 Andrew Stubbs Unresolved
[v3,5/6] libgomp, nvptx: Cuda pinned memory libgomp: OpenMP pinned memory omp_alloc - - - -1- 2023-12-11 Andrew Stubbs Unresolved
[v3,4/6] openmp: -foffload-memory=pinned libgomp: OpenMP pinned memory omp_alloc - - - -1- 2023-12-11 Andrew Stubbs Unresolved
[v3,3/6] openmp: Add -foffload-memory libgomp: OpenMP pinned memory omp_alloc - - - -1- 2023-12-11 Andrew Stubbs Unresolved
[v3,2/6] libgomp, openmp: Add ompx_pinned_mem_alloc libgomp: OpenMP pinned memory omp_alloc - - - -1- 2023-12-11 Andrew Stubbs Unresolved
[v3,1/6] libgomp: basic pinned memory on Linux libgomp: OpenMP pinned memory omp_alloc - - - -1- 2023-12-11 Andrew Stubbs Unresolved
[committed,v4,3/3] amdgcn, libgomp: low-latency allocator libgomp: OpenMP low-latency omp_alloc - - - -1- 2023-12-06 Andrew Stubbs Unresolved
[committed,v4,2/3] openmp, nvptx: low-lat memory access traits libgomp: OpenMP low-latency omp_alloc - - - -1- 2023-12-06 Andrew Stubbs Unresolved
[committed,v4,1/3] libgomp, nvptx: low-latency memory allocator libgomp: OpenMP low-latency omp_alloc - - - -1- 2023-12-06 Andrew Stubbs Unresolved
[v3,3/3] amdgcn, libgomp: low-latency allocator libgomp: OpenMP low-latency omp_alloc - - - -1- 2023-12-03 Andrew Stubbs Unresolved
[v3,2/3] openmp, nvptx: low-lat memory access traits libgomp: OpenMP low-latency omp_alloc - - - -1- 2023-12-03 Andrew Stubbs Unresolved
[v3,1/3] libgomp, nvptx: low-latency memory allocator libgomp: OpenMP low-latency omp_alloc - - - -1- 2023-12-03 Andrew Stubbs Unresolved
[committed] amdgcn: Disallow TImode vector permute [committed] amdgcn: Disallow TImode vector permute - - - 1-- 2023-11-27 Andrew Stubbs Accepted
[committed] amdgcn: Fix vector TImode reload loop [committed] amdgcn: Fix vector TImode reload loop - - - -1- 2023-11-22 Andrew Stubbs Unresolved
[committed] amdgcn: Add Accelerator VGPR registers [committed] amdgcn: Add Accelerator VGPR registers - - - -1- 2023-11-15 Andrew Stubbs Unresolved
[committed] amdgcn: simplify secondary reload patterns [committed] amdgcn: simplify secondary reload patterns - - - -1- 2023-11-15 Andrew Stubbs Unresolved
[committed] amdgcn: Fix vector min/max ICE (pr112313) [committed] amdgcn: Fix vector min/max ICE (pr112313) - - - 1-- 2023-11-10 Andrew Stubbs Accepted
[committed] amdgcn: silence warnings [committed] amdgcn: silence warnings - - - 1-- 2023-10-27 Andrew Stubbs Accepted
vect: Don't set excess bits in unform masks vect: Don't set excess bits in unform masks - - - -1- 2023-10-20 Andrew Stubbs Unresolved
[committed] amdgcn: add -march=gfx1030 EXPERIMENTAL [committed] amdgcn: add -march=gfx1030 EXPERIMENTAL - - - -1- 2023-10-20 Andrew Stubbs Unresolved
wwwdocs: gcc-14: mark amdgcn fiji deprecated wwwdocs: gcc-14: mark amdgcn fiji deprecated - - - -1- 2023-10-19 Andrew Stubbs Unresolved
[committed] amdgcn: deprecate Fiji device and multilib [committed] amdgcn: deprecate Fiji device and multilib - - - -1- 2023-10-19 Andrew Stubbs Unresolved
[committed] amdgcn: switch mov insns to compact syntax [committed] amdgcn: switch mov insns to compact syntax - - - -1- 2023-10-06 Andrew Stubbs Unresolved
[committed] amdgcn: silence warning [committed] amdgcn: silence warning - - - 1-- 2023-10-06 Andrew Stubbs Accepted
[OG13,committed] libgomp, nvptx, amdgcn: parallel reverse offload [OG13,committed] libgomp, nvptx, amdgcn: parallel reverse offload - - - -1- 2023-09-12 Andrew Stubbs Unresolved
libgomp, nvptx, amdgcn: parallel reverse offload libgomp, nvptx, amdgcn: parallel reverse offload - - - 1-- 2023-09-12 Andrew Stubbs Accepted
[v2,6/6] libgomp: fine-grained pinned memory allocator libgomp: OpenMP pinned memory omp_alloc - - - -1- 2023-08-23 Andrew Stubbs Unresolved
[v2,5/6] libgomp, nvptx: Cuda pinned memory libgomp: OpenMP pinned memory omp_alloc - - - -1- 2023-08-23 Andrew Stubbs Unresolved
[v2,4/6] openmp: -foffload-memory=pinned libgomp: OpenMP pinned memory omp_alloc - - - -1- 2023-08-23 Andrew Stubbs Unresolved
[v2,3/6] openmp: Add -foffload-memory libgomp: OpenMP pinned memory omp_alloc - - - -1- 2023-08-23 Andrew Stubbs Unresolved
[v2,2/6] libgomp, openmp: Add ompx_pinned_mem_alloc libgomp: OpenMP pinned memory omp_alloc - - - -1- 2023-08-23 Andrew Stubbs Unresolved
[v2,1/6] libgomp: basic pinned memory on Linux libgomp: OpenMP pinned memory omp_alloc - - - -1- 2023-08-23 Andrew Stubbs Unresolved
[v2,3/3] amdgcn, libgomp: low-latency allocator libgomp: OpenMP low-latency omp_alloc - - - -1- 2023-08-02 Andrew Stubbs Unresolved
[v2,2/3] openmp, nvptx: low-lat memory access traits libgomp: OpenMP low-latency omp_alloc - - - -1- 2023-08-02 Andrew Stubbs Unresolved
[v2,1/3] libgomp, nvptx: low-latency memory allocator libgomp: OpenMP low-latency omp_alloc - - - -1- 2023-08-02 Andrew Stubbs Unresolved
[committed] amdgcn: implement vector div and mod libfuncs [committed] amdgcn: implement vector div and mod libfuncs - - - -1- 2023-06-19 Andrew Stubbs Unresolved
[committed] amdgcn: minimal V64TImode vector support [committed] amdgcn: minimal V64TImode vector support - - - 1-- 2023-06-19 Andrew Stubbs Accepted
[committed] amdgcn: Delete inactive libfuncs [committed] amdgcn: Delete inactive libfuncs - - - 1-- 2023-06-19 Andrew Stubbs Accepted
vect: Vectorize via libfuncs vect: Vectorize via libfuncs - - - 1-- 2023-06-13 Andrew Stubbs Accepted
Add COMPLEX_VECTOR_INT modes Add COMPLEX_VECTOR_INT modes - - - 1-- 2023-05-26 Andrew Stubbs Accepted
[committed] amdgcn: Fix addsub bug [committed] amdgcn: Fix addsub bug - - - -1- 2023-04-27 Andrew Stubbs Repeat Merge
[committed,OG10] amdgcn, openmp: Fix concurrency in low-latency allocator [committed,OG10] amdgcn, openmp: Fix concurrency in low-latency allocator - - - -1- 2023-04-20 Andrew Stubbs Unresolved
[committed] amdgcn: bug fix ldexp insn [committed] amdgcn: bug fix ldexp insn - - - -1- 2023-04-20 Andrew Stubbs Repeat Merge
[committed] amdgcn: update target-supports.exp [committed] amdgcn: update target-supports.exp - - - -1- 2023-04-20 Andrew Stubbs Repeat Merge
[committed] amdgcn: HardFP divide [committed] amdgcn: HardFP divide - - - -1- 2023-04-18 Andrew Stubbs Repeat Merge
[committed] amdgcn: Add 64-bit vector not [committed] amdgcn: Add 64-bit vector not - - - -1- 2023-04-04 Andrew Stubbs Unresolved
[committed] amdgcn: Fix register size bug [committed] amdgcn: Fix register size bug - - - -1- 2023-03-23 Andrew Stubbs Unresolved
[committed] amdgcn: vec_extract no-op insns [committed] amdgcn: vec_extract no-op insns - - - -1- 2023-03-23 Andrew Stubbs Repeat Merge
[committed,OG12] libgomp: no need to attach USM pointers [committed,OG12] libgomp: no need to attach USM pointers - - - 1-- 2023-02-23 Andrew Stubbs Accepted
[OG12,committed] amdgcn: OpenMP low-latency allocator [OG12,committed] amdgcn: OpenMP low-latency allocator - - - -1- 2023-02-16 Andrew Stubbs Unresolved
[committed] amdgcn: Pass -mstack-size through to runtime [committed] amdgcn: Pass -mstack-size through to runtime - - - -1- 2023-02-06 Andrew Stubbs Repeat Merge
[committed] amdgcn, libgomp: Manually allocated stacks [committed] amdgcn, libgomp: Manually allocated stacks - - - -1- 2023-02-02 Andrew Stubbs Repeat Merge
[OG12,committed] amdgcn, libgomp: custom USM allocator [OG12,committed] amdgcn, libgomp: custom USM allocator - - - -1- 2023-01-11 Andrew Stubbs Unresolved
[OG12,committed] libgomp: Fix USM bugs [OG12,committed] libgomp: Fix USM bugs - - - -1- 2022-12-16 Andrew Stubbs Unresolved
[committed] amdgcn: add fmin/fmax patterns [committed] amdgcn: add fmin/fmax patterns - - - -1- 2022-10-31 Andrew Stubbs Unresolved
[committed] amdgcn: multi-size vector reductions [committed] amdgcn: multi-size vector reductions - - - -1- 2022-10-31 Andrew Stubbs Unresolved
[committed] amdgcn: Silence unused parameter warning [committed] amdgcn: Silence unused parameter warning - - - -1- 2022-10-31 Andrew Stubbs Repeat Merge
[OG12,commit] vect: WORKAROUND vectorizer bug [OG12,commit] vect: WORKAROUND vectorizer bug - - - 1-- 2022-10-24 Andrew Stubbs Accepted
[OG12,commit] amdgcn: disallow USM on gfx908 [OG12,commit] amdgcn: disallow USM on gfx908 - - - -1- 2022-10-24 Andrew Stubbs Unresolved
[OG12,commit] amdgcn, libgomp: USM allocation update [OG12,commit] amdgcn, libgomp: USM allocation update - - - -1- 2022-10-24 Andrew Stubbs Unresolved
libgomp: fix hang on fatal error libgomp: fix hang on fatal error - - - 1-- 2022-10-14 Andrew Stubbs Accepted
[committed,6/6] amdgcn: vector testsuite tweaks amdgcn: Add V32, V16, V8, V4, and V2 vectors - - - --- 2022-10-11 Andrew Stubbs New
[committed,5/6] amdgcn: Add vector integer negate insn amdgcn: Add V32, V16, V8, V4, and V2 vectors - - - --- 2022-10-11 Andrew Stubbs New
[committed,4/6] amdgcn: vec_init for multiple vector sizes amdgcn: Add V32, V16, V8, V4, and V2 vectors - - - --- 2022-10-11 Andrew Stubbs New
[committed,3/6] amdgcn: Add vec_extract for partial vectors amdgcn: Add V32, V16, V8, V4, and V2 vectors - - - --- 2022-10-11 Andrew Stubbs New
[committed,2/6] amdgcn: Resolve insn conditions at compile time amdgcn: Add V32, V16, V8, V4, and V2 vectors - - - --- 2022-10-11 Andrew Stubbs New
[committed,1/6] amdgcn: add multiple vector sizes amdgcn: Add V32, V16, V8, V4, and V2 vectors - - - --- 2022-10-11 Andrew Stubbs New
[committed] amdgcn: remove unused variable [committed] amdgcn: remove unused variable - - - --- 2022-09-29 Andrew Stubbs New
vect: while_ult for integer mask vect: while_ult for integer mask - - - 1-- 2022-09-28 Andrew Stubbs Accepted
[3/3] vect: inbranch SIMD clones OpenMP SIMD routines - - - --- 2022-08-09 Andrew Stubbs New
[2/3] amdgcn: OpenMP SIMD routine support OpenMP SIMD routines - - - --- 2022-08-09 Andrew Stubbs New
[1/3] omp-simd-clone: Allow fixed-lane vectors OpenMP SIMD routines - - - --- 2022-08-09 Andrew Stubbs New
[committed] amdgcn: Vector procedure call ABI [committed] amdgcn: Vector procedure call ABI - - - --- 2022-08-09 Andrew Stubbs New
openmp-simd-clone: Match shift type openmp-simd-clone: Match shift type - - - --- 2022-07-29 Andrew Stubbs New
[committed] amdgcn: 64-bit vector shifts [committed] amdgcn: 64-bit vector shifts - - - --- 2022-07-29 Andrew Stubbs New
[committed] amdgcn: 64-bit not [committed] amdgcn: 64-bit not - - - --- 2022-07-29 Andrew Stubbs New