Google Git
Sign in
llvm/llvm-project.git/refs/heads/main/./llvm/test/CodeGen/NVPTX
tree: 8090a7c22a5de5c2283536700bba0d3a6795f623
  1. access-non-generic.ll
  2. activemask.ll
  3. add-sub-128bit.ll
  4. addr-mode.ll
  5. address-folder.ll
  6. address-folder.mir
  7. addrspacecast-cse.ll
  8. addrspacecast-folding.ll
  9. addrspacecast-gvar.ll
  10. addrspacecast-ptx64.ll
  11. addrspacecast.ll
  12. aggr-param.ll
  13. aggregate-return.ll
  14. alias-errors.ll
  15. alias.ll
  16. and-or-setcc.ll
  17. annotations.ll
  18. anonymous-fn-param.ll
  19. APIntLoadStore.ll
  20. APIntParam.ll
  21. APIntSextParam.ll
  22. APIntZextParam.ll
  23. applypriority-async-bulk-global-evict-priority.ll
  24. applypriority-async-bulk-tensor-evict-priority.ll
  25. applypriority-async-bulk-tensor-override-evict-priority.ll
  26. applypriority.ll
  27. arbitrary-fp-to-float.ll
  28. arg-lowering.ll
  29. arithmetic-fp-sm20.ll
  30. arithmetic-int.ll
  31. asm-printer-ptx-module-directives.ll
  32. async-copy.ll
  33. atomic-alignment.err.ll
  34. atomic-lower-local.ll
  35. atomicrmw-allow-ftz-atomics.ll
  36. atomicrmw-expand.err.ll
  37. atomicrmw-sm60.ll
  38. atomicrmw-sm70.ll
  39. atomicrmw-sm90.ll
  40. atomicrmw.py
  41. atomics-b128.ll
  42. atomics-sm60.ll
  43. atomics.ll
  44. b52037.ll
  45. barrier.ll
  46. bf16-instructions.ll
  47. bf16-neg-noftz.ll
  48. bf16-setp-noftz.ll
  49. bf16.ll
  50. bf16x2-instructions-approx.ll
  51. bf16x2-instructions.ll
  52. bfe.ll
  53. blocksareclusters-kernel-attr.ll
  54. bmsk.ll
  55. boolean-patterns.ll
  56. branch-fold.ll
  57. branch-fold.mir
  58. brkpt.ll
  59. bswap.ll
  60. bug17709.ll
  61. bug21465.ll
  62. bug22246.ll
  63. bug22322.ll
  64. bug26185-2.ll
  65. bug26185.ll
  66. bug41651.ll
  67. bug52623.ll
  68. bypass-div.ll
  69. byval-arg-vectorize.ll
  70. byval-const-global.ll
  71. cache-hint-atomics.ll
  72. cache-hint-cache-policy.ll
  73. cache-hint-intrinsics.ll
  74. cache-hint-invalid.ll
  75. cache-hint-load-store.ll
  76. cache-hint-sm-version.ll
  77. cache-hint-transforms.ll
  78. call-with-alloca-buffer.ll
  79. call_bitcast_byval.ll
  80. callchain.ll
  81. calling-conv.ll
  82. calls-with-phi.ll
  83. chain-different-as.ll
  84. cluster-dim.ll
  85. clusterlaunchcontrol-multicast.ll
  86. clusterlaunchcontrol.ll
  87. cmpxchg-sm60.ll
  88. cmpxchg-sm70.ll
  89. cmpxchg-sm90.ll
  90. cmpxchg-unsupported-syncscope.err.ll
  91. cmpxchg.ll
  92. cmpxchg.py
  93. combine-mad.ll
  94. combine-min-max.ll
  95. combine-mul-wide-type.ll
  96. combine-wide.ll
  97. common-linkage.ll
  98. compare-int.ll
  99. compute-ptx-value-vts.ll
  100. constant-vectors.ll
  101. convergent-mir-call.ll
  102. convert-call-to-indirect.ll
  103. convert-fp-i128.ll
  104. convert-fp-i8.ll
  105. convert-fp.ll
  106. convert-int-sm20.ll
  107. convert-sm100.ll
  108. convert-sm100a.ll
  109. convert-sm103a.ll
  110. convert-sm80-sf.ll
  111. convert-sm80.ll
  112. convert-sm89.ll
  113. convert-sm90.ll
  114. convert-ue5m3x2.ll
  115. convert_fp4x2_sm_100f.ll
  116. convert_fp4x2_to_bf16x2.ll
  117. convert_fp6x2_sm_100f.ll
  118. convert_fp6x2_to_bf16x2.ll
  119. convert_fp8x2_sm_100f.ll
  120. convert_fp8x2_to_bf16x2.ll
  121. convert_s2f6x2_sm_100a.ll
  122. copysign.ll
  123. cp-async-bulk-prefetch-evict-priority.ll
  124. cp-async-bulk-ptx86.ll
  125. cp-async-bulk-s2g-sm100.ll
  126. cp-async-bulk-tensor-g2s-1cta.ll
  127. cp-async-bulk-tensor-g2s-2cta.ll
  128. cp-async-bulk-tensor-g2s-cta-sm100.ll
  129. cp-async-bulk-tensor-g2s-cta-sm100a.ll
  130. cp-async-bulk-tensor-g2s-cta-sm90.ll
  131. cp-async-bulk-tensor-g2s-gather4.ll
  132. cp-async-bulk-tensor-g2s-im2colw.ll
  133. cp-async-bulk-tensor-g2s-im2colw128.ll
  134. cp-async-bulk-tensor-g2s-invalid.ll
  135. cp-async-bulk-tensor-g2s.ll
  136. cp-async-bulk-tensor-prefetch-evict-priority.ll
  137. cp-async-bulk-tensor-prefetch-override-evict-priority.ll
  138. cp-async-bulk-tensor-prefetch-override.ll
  139. cp-async-bulk-tensor-prefetch-sm100a.ll
  140. cp-async-bulk-tensor-prefetch.ll
  141. cp-async-bulk-tensor-reduce-im2colw.ll
  142. cp-async-bulk-tensor-reduce-override.ll
  143. cp-async-bulk-tensor-reduce.ll
  144. cp-async-bulk-tensor-s2g-im2colw.ll
  145. cp-async-bulk-tensor-s2g-override.ll
  146. cp-async-bulk-tensor-s2g-scatter4.ll
  147. cp-async-bulk-tensor-s2g.ll
  148. cp-async-bulk.ll
  149. cse-mov-sym.ll
  150. ctlz.ll
  151. ctpop.ll
  152. cttz.ll
  153. dag-cse.ll
  154. dead-shfl.ll
  155. default-sm.ll
  156. demote-vars.ll
  157. disable-opt.ll
  158. discard.ll
  159. disjoint-or-addr.ll
  160. distributed-shared-cluster.ll
  161. div-ri.ll
  162. div.ll
  163. divrem-combine.ll
  164. dot-product.ll
  165. dynamic-stackalloc-regression.ll
  166. dynamic_stackalloc.ll
  167. elect.ll
  168. empty-type.ll
  169. envreg.ll
  170. extern-shared-valid-name.ll
  171. extloadv.ll
  172. extractelement.ll
  173. f128-no-libcall-error.ll
  174. f16-abs.ll
  175. f16-add-sat.ll
  176. f16-ex2.ll
  177. f16-instructions.ll
  178. f16-mul-sat.ll
  179. f16-sub-sat.ll
  180. f16x2-instructions.ll
  181. f32-ex2.ll
  182. f32-lg2.ll
  183. f32x2-convert-i32x2.ll
  184. f32x2-instructions.ll
  185. fabs-intrinsics.ll
  186. fast-math.ll
  187. fcos-no-fast-math.ll
  188. fence-proxy-sm90-ptx86.ll
  189. fence-proxy-sm90.ll
  190. fence-proxy-tensormap-invalid.ll
  191. fence-proxy-tensormap.ll
  192. fence-proxy.ll
  193. fence.ll
  194. fence.py
  195. fexp2.ll
  196. filetype-null.ll
  197. flo.ll
  198. float-to-arbitrary-fp.ll
  199. flog2.ll
  200. fma-assoc.ll
  201. fma-disable.ll
  202. fma-oob.ll
  203. fma-relu-contract.ll
  204. fma-relu-fma-intrinsic.ll
  205. fma-relu-instruction-flag.ll
  206. fma.ll
  207. fmax3.ll
  208. fminimum-fmaximum.ll
  209. fns.ll
  210. fold-movs.ll
  211. forward-ld-param.ll
  212. fp-arith-sat.ll
  213. fp-contract-f32x2.ll
  214. fp-contract.ll
  215. fp-fold-sub.ll
  216. fp-literals.ll
  217. fp128-conv-no-libcall-error.ll
  218. fp128-global.ll
  219. fp128-storage-type.ll
  220. frameindex-lifetime.ll
  221. frem.ll
  222. fsin-no-fast-math.ll
  223. function-align.ll
  224. funnel-shift-clamp.ll
  225. generic-to-nvvm-ir.ll
  226. generic-to-nvvm.ll
  227. global-addrspace.ll
  228. global-ctor-empty.ll
  229. global-cycle-alias.ll
  230. global-cycle-internal-subcycle.ll
  231. global-cycle-internal.ll
  232. global-cycle.ll
  233. global-incomplete-init.ll
  234. global-ordering.ll
  235. global-variable-big.ll
  236. global-visibility.ll
  237. globals_init.ll
  238. globals_lowering.ll
  239. griddepcontrol.ll
  240. gvar-init.ll
  241. gvn-scalar-pre-reg-pressure.ll
  242. half.ll
  243. i1-array-global.ll
  244. i1-ext-load.ll
  245. i1-global.ll
  246. i1-icmp.ll
  247. i1-int-to-fp.ll
  248. i1-load-lower.ll
  249. i1-param.ll
  250. i1-select.ll
  251. i128-array.ll
  252. i128-global.ll
  253. i128-ld-st.ll
  254. i128-param.ll
  255. i128-retval.ll
  256. i128-struct.ll
  257. i128.ll
  258. i16x2-instructions.ll
  259. i32x2-instructions.ll
  260. i8-param.ll
  261. i8x2-instructions.ll
  262. i8x4-instructions.ll
  263. idioms.ll
  264. imad.ll
  265. indirect_byval.ll
  266. inline-asm-b128-test1.ll
  267. inline-asm-b128-test2.ll
  268. inline-asm-b128-test3.ll
  269. inline-asm-line-info-inlined-at.ll
  270. inline-asm-line-info-per-instruction.ll
  271. inline-asm-line-number-before.ll
  272. inline-asm.ll
  273. inlineasm-output-template.ll
  274. insert-vector-elt-bitcast-legalize.ll
  275. insert-vector-elt-shuffle-i8.ll
  276. insertelt-dynamic.ll
  277. intr-range.ll
  278. intrinsic-immarg-print-mismatched-signature.ll
  279. intrinsic-old.ll
  280. intrinsics-sm90-ptx81.ll
  281. intrinsics-sm90.ll
  282. intrinsics.ll
  283. isspacep.ll
  284. jump-table.ll
  285. kernel-param-align.ll
  286. ld-addrspace.ll
  287. ld-generic.ll
  288. ld-param-sink.ll
  289. ld-st-addrrspace.py
  290. ldg-invariant-256.ll
  291. ldg-invariant.ll
  292. ldparam-v4.ll
  293. ldu-i8.ll
  294. ldu-ldg.ll
  295. ldu-reg-plus-offset.ll
  296. lit.local.cfg
  297. llc-pipeline-npm.ll
  298. load-sext-i1.ll
  299. load-store-256-addressing-invariant.ll
  300. load-store-256-addressing.ll
  301. load-store-atomic.err.ll
  302. load-store-scalars.ll
  303. load-store-sm-70.ll
  304. load-store-sm-90.ll
  305. load-store-vectors-256.ll
  306. load-store-vectors.ll
  307. load-with-non-coherent-cache.ll
  308. LoadStoreVectorizer.ll
  309. local-stack-frame.ll
  310. loop-vectorize.ll
  311. lower-aggr-copies-shared.ll
  312. lower-aggr-copies.ll
  313. lower-alloca.ll
  314. lower-args-alignment.ll
  315. lower-args-gridconstant.ll
  316. lower-args.ll
  317. lower-byval-args-dbg.ll
  318. lower-byval-args-idempotent.ll
  319. lower-byval-args-mem-attrs.ll
  320. lower-byval-args.ll
  321. lower-ctor-dtor.ll
  322. lower-kernel-ptr-arg.ll
  323. machine-cse-predicate-inversion-multiple-users.ll
  324. machine-cse-predicate-inversion-rollback.mir
  325. machine-cse-predicate-inversion-vector-float.ll
  326. machine-cse-predicate-inversion.ll
  327. machine-cse-predicate-no-inversion.ll
  328. machine-sink.ll
  329. machinelicm-no-preheader.mir
  330. MachineSink-call.ll
  331. MachineSink-convergent.ll
  332. managed.ll
  333. mark-kernel-ptrs-global.ll
  334. masked-divrem.ll
  335. masked-load-3xhalf.ll
  336. masked-load-vectors.ll
  337. masked-store-variable-mask.ll
  338. masked-store-vectors-256.ll
  339. match.ll
  340. math-intrins-sm53-ptx42.ll
  341. math-intrins-sm80-ptx70-autoupgrade.ll
  342. math-intrins-sm80-ptx70-instcombine.ll
  343. math-intrins-sm80-ptx70.ll
  344. math-intrins-sm86-ptx72-autoupgrade.ll
  345. math-intrins-sm86-ptx72.ll
  346. math-intrins.ll
  347. max-align.ll
  348. maxclusterrank.ll
  349. mbarrier.ll
  350. mbarrier_arr.ll
  351. mbarrier_arr_relaxed.ll
  352. mbarrier_tx.ll
  353. mbarrier_wait_sm80_ptx70.ll
  354. mbarrier_wait_sm80_ptx71.ll
  355. mbarrier_wait_sm90_ptx78.ll
  356. mbarrier_wait_sm90_ptx80.ll
  357. mbarrier_wait_sm90_ptx86.ll
  358. memcpy-alloca-align.ll
  359. minmax-negative.ll
  360. misaligned-vector-ldst.ll
  361. misched_func_call.ll
  362. mixed-precision-fp.ll
  363. mma-no-sink-after-laneid-check.ll
  364. module-inline-asm.ll
  365. movmatrix.ll
  366. mulhi-intrins.ll
  367. mulwide.ll
  368. naked-fn-with-frame-pointer.ll
  369. nanosleep.ll
  370. no-extra-parens.ll
  371. no-f32x2.ll
  372. no-stack-protector-libcall-error.ll
  373. noduplicate-syncthreads.ll
  374. nofunc.ll
  375. noreturn.ll
  376. nounroll.ll
  377. nvcl-param-align.ll
  378. nvptx-aa-inline-asm.ll
  379. nvptx-aa.ll
  380. nvptx-fold-fma.ll
  381. nvptx-prec-divf32-flag.ll
  382. NVPTXAA_before_BasicAA.ll
  383. nvvm-abs.ll
  384. nvvm-annotations-D120129.ll
  385. nvvm-reflect-arch-O0.ll
  386. nvvm-reflect-arch.ll
  387. nvvm-reflect-module-flag.ll
  388. nvvm-reflect-ocl.ll
  389. nvvm-reflect-opaque.ll
  390. nvvm-reflect-options.ll
  391. nvvm-reflect.ll
  392. op-fence.ll
  393. packed-aggr-self-ptx70.ll
  394. packed-aggr.ll
  395. param-add.ll
  396. param-align.ll
  397. param-load-store.ll
  398. param-overalign.ll
  399. param-space-subqualifiers.ll
  400. param-vectorize-device.ll
  401. param-vectorize-kernel.ll
  402. pass-name.ll
  403. peephole-cvta-local-short-ptr.mir
  404. pm-event.ll
  405. pow2_mask_cmp.ll
  406. powi.ll
  407. pr126337.ll
  408. pr13291-i1-store.ll
  409. pr16278.ll
  410. pr17529.ll
  411. prefetch-inferas-test.ll
  412. prefetch.ll
  413. prmt-const-folding.ll
  414. prmt.ll
  415. promote-param-align.ll
  416. proxy-reg-erasure-kill-flag.mir
  417. proxy-reg-erasure-ptx.ll
  418. proxy-reg-erasure.mir
  419. ptx-version-validation.ll
  420. rcp-opt.ll
  421. read-global-variable-constant.ll
  422. reduction-intrinsics.ll
  423. redux-sync-f32.ll
  424. redux-sync.ll
  425. refl1.ll
  426. reg-copy.ll
  427. reg-types.ll
  428. reqnctapercluster-const-fold.ll
  429. reqntid-const-fold.ll
  430. reserved-smem-offset.ll
  431. ret-align-mismatch.ll
  432. rotate-add.ll
  433. rotate.ll
  434. rotate_64.ll
  435. rsqrt-opt.ll
  436. rsqrt.ll
  437. sad-intrins.ll
  438. scalar-to-vector.ll
  439. scalarize-non-coalescable-v2f32.ll
  440. sched1.ll
  441. sched2.ll
  442. setmaxnreg-sm100a.ll
  443. setmaxnreg.ll
  444. sext-in-reg.ll
  445. sext-params.ll
  446. sext-setcc.ll
  447. shfl-p.ll
  448. shfl-sync-p.ll
  449. shfl-sync.ll
  450. shfl.ll
  451. shift-logic-cse.ll
  452. shift-opt.ll
  453. shift-parts.ll
  454. short-ptr.ll
  455. shuffle-vec-undef-init.ll
  456. simple-call.ll
  457. sm-110-rename.ll
  458. sm-version.ll
  459. speculative-execution-divergent-target.ll
  460. sqrt-approx.ll
  461. srl-bitcast-bv.ll
  462. st-addrspace.ll
  463. st-generic.ll
  464. st-param-imm.ll
  465. st_async_mbarrier.ll
  466. st_async_mbarrier_b128.ll
  467. st_async_release.ll
  468. st_async_release_multimem.ll
  469. st_bulk.ll
  470. stackaddress.ll
  471. stacksaverestore.ll
  472. stop-after-npm.ll
  473. store-retval.ll
  474. store-undef.ll
  475. sub-byte-constant-vector-convert.ll
  476. sub-byte-constant-vectors-i4-i2.ll
  477. surf-read-cuda.ll
  478. surf-read.ll
  479. surf-tex.py
  480. surf-write-cuda.ll
  481. surf-write.ll
  482. switch-loop-header.mir
  483. switch.ll
  484. symbol-naming.ll
  485. szext.ll
  486. tag-invariant-loads.ll
  487. TailDuplication-convergent.ll
  488. tanhf.ll
  489. tcgen05-alloc-dealloc-exclusive.ll
  490. tcgen05-alloc.ll
  491. tcgen05-commit-sm107.ll
  492. tcgen05-commit.ll
  493. tcgen05-cp.ll
  494. tcgen05-fence.ll
  495. tcgen05-ld-red.ll
  496. tcgen05-ld.ll
  497. tcgen05-mma-block-scale-decompress-b.ll
  498. tcgen05-mma-block-scale-invalid.ll
  499. tcgen05-mma-block-scale-ptx88-aa.ll
  500. tcgen05-mma-block-scale-ptx88.ll
  501. tcgen05-mma-block-scale.ll
  502. tcgen05-mma-collector-b-i8-invalid.ll
  503. tcgen05-mma-collector-b.ll
  504. tcgen05-mma-decompress-b.ll
  505. tcgen05-mma-disable-output-lane-collector-b.ll
  506. tcgen05-mma-disable-output-lane-decompress-b.ll
  507. tcgen05-mma-disable-output-lane-i8.ll
  508. tcgen05-mma-disable-output-lane.ll
  509. tcgen05-mma-i8.ll
  510. tcgen05-mma-invalid.ll
  511. tcgen05-mma-scale-d-invalid.ll
  512. tcgen05-mma-scale-d.ll
  513. tcgen05-mma-sp-collector-b-i8-invalid.ll
  514. tcgen05-mma-sp-collector-b.ll
  515. tcgen05-mma-sp-disable-output-lane-collector-b.ll
  516. tcgen05-mma-sp-mxf4-mxf4nvf4-kind.ll
  517. tcgen05-mma-ti16-kind.ll
  518. tcgen05-mma-ws-i8.ll
  519. tcgen05-mma-ws.ll
  520. tcgen05-mma.ll
  521. tcgen05-shift.ll
  522. tcgen05-st.ll
  523. tensormap_replace.ll
  524. tensormap_replace_invalid.ll
  525. tensormap_replace_sm_100a.ll
  526. tensormap_replace_sm_103a.ll
  527. tex-read-cuda.ll
  528. tex-read.ll
  529. texsurf-queries.ll
  530. thread-fence.ll
  531. tid-range.ll
  532. trunc-setcc.ll
  533. trunc-tofp.ll
  534. unaligned-param-load-store.ll
  535. unfold-masked-merge-vector-variablemask.ll
  536. unknown-intrinsic.ll
  537. unreachable.ll
  538. unrecognized-sm1x.ll
  539. upgrade-nvvm-annotations.ll
  540. used-bytes-mask.ll
  541. vaargs.ll
  542. variadics-backend.ll
  543. variadics-lowering.ll
  544. vec-param-load.ll
  545. vec8.ll
  546. vector-args.ll
  547. vector-call.ll
  548. vector-compare.ll
  549. vector-global.ll
  550. vector-loads.ll
  551. vector-returns.ll
  552. vector-select.ll
  553. vector-stores.ll
  554. vectorize-misaligned.ll
  555. vote.ll
  556. weak-global.ll
  557. weak-linkage.ll
  558. wgmma-sm90a-fence.ll
  559. wmma-ptx60-sm70.py
  560. wmma-ptx61-sm70.py
  561. wmma-ptx63-sm72.py
  562. wmma-ptx63-sm75.py
  563. wmma-ptx64-sm70.py
  564. wmma-ptx65-sm75.py
  565. wmma-ptx71-sm80.py
  566. wmma-ptx78-sm90.py
  567. wmma-ptx86-sm100a.py
  568. wmma-ptx86-sm101a.py
  569. wmma-ptx87-sm120a.py
  570. wmma-ptx88-sm100f.py
  571. wmma-ptx88-sm120a.py
  572. wmma-ptx88-sm120f.py
  573. wmma-ptx90-sm110f.py
  574. wmma-ptx91-sm120a.py
  575. wmma-ptx91-sm120f.py
  576. wmma.py
  577. zeroext-32bit.ll