Google Git Google Git
Sign in
llvm/llvm-project.git/refs/heads/main/./llvm/test/CodeGen/NVPTX
tree: 1b2ce808428dd39e36a3eca0ce1df201ecfa2b37 [search]
  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-load-store-128-cluster.ll
  35. atomic-load-store-128-invalid.ll
  36. atomic-load-store-128-mir.ll
  37. atomic-load-store-128-ptx83.ll
  38. atomic-load-store-128.ll
  39. atomic-lower-local.ll
  40. atomicrmw-allow-ftz-atomics.ll
  41. atomicrmw-elementwise-128.ll
  42. atomicrmw-elementwise-sm60.ll
  43. atomicrmw-elementwise-sm70.ll
  44. atomicrmw-elementwise-sm90.ll
  45. atomicrmw-expand.err.ll
  46. atomicrmw-ignore-denormal-mode.ll
  47. atomicrmw-sm60.ll
  48. atomicrmw-sm70.ll
  49. atomicrmw-sm90.ll
  50. atomicrmw-v1-type-legalization.ll
  51. atomicrmw.py
  52. atomics-b128.ll
  53. atomics-sm60.ll
  54. atomics-system-scope-sm50.err.ll
  55. atomics.ll
  56. b52037.ll
  57. barrier.ll
  58. bf16-add.ll
  59. bf16-instructions.ll
  60. bf16-mul.ll
  61. bf16-neg-noftz.ll
  62. bf16-setp-noftz.ll
  63. bf16-sub.ll
  64. bf16.ll
  65. bf16x2-instructions-approx.ll
  66. bf16x2-instructions.ll
  67. bfe.ll
  68. blocksareclusters-kernel-attr.ll
  69. bmsk.ll
  70. boolean-patterns.ll
  71. branch-fold.ll
  72. branch-fold.mir
  73. brkpt.ll
  74. bswap.ll
  75. bug17709.ll
  76. bug21465.ll
  77. bug22246.ll
  78. bug22322.ll
  79. bug26185-2.ll
  80. bug26185.ll
  81. bug41651.ll
  82. bug52623.ll
  83. bypass-div.ll
  84. byval-arg-vectorize.ll
  85. byval-const-global.ll
  86. cache-hint-atomics.ll
  87. cache-hint-cache-policy.ll
  88. cache-hint-intrinsics.ll
  89. cache-hint-invalid.ll
  90. cache-hint-load-store.ll
  91. cache-hint-sm-version.ll
  92. cache-hint-transforms.ll
  93. cache-hint-unaligned-store-aa.ll
  94. call-with-alloca-buffer.ll
  95. call_bitcast_byval.ll
  96. callchain.ll
  97. calling-conv.ll
  98. callprototype-dollar-local-label.ll
  99. callprototype-local-label.ll
  100. calls-with-phi.ll
  101. canonicalize-dynamic-shared-alias.ll
  102. canonicalize-dynamic-shared-all-constant.ll
  103. canonicalize-dynamic-shared-constant.ll
  104. canonicalize-dynamic-shared-debug-info.ll
  105. canonicalize-dynamic-shared-pipeline.ll
  106. canonicalize-dynamic-shared-thinlto.ll
  107. canonicalize-dynamic-shared-used.ll
  108. canonicalize-dynamic-shared.ll
  109. chain-different-as.ll
  110. clmad.ll
  111. cluster-dim.ll
  112. clusterlaunchcontrol-multicast.ll
  113. clusterlaunchcontrol.ll
  114. cmpxchg-sm60.ll
  115. cmpxchg-sm70.ll
  116. cmpxchg-sm90.ll
  117. cmpxchg-unsupported-syncscope.err.ll
  118. cmpxchg.ll
  119. cmpxchg.py
  120. combine-mad.ll
  121. combine-min-max.ll
  122. combine-mul-wide-type.ll
  123. combine-wide.ll
  124. common-linkage.ll
  125. compare-int.ll
  126. compute-ptx-value-vts.ll
  127. constant-vectors.ll
  128. convergent-mir-call.ll
  129. convert-call-to-indirect.ll
  130. convert-fp-i128.ll
  131. convert-fp-i8.ll
  132. convert-fp.ll
  133. convert-fp16-pzo.ll
  134. convert-fp4-pzo.ll
  135. convert-fp4-scale.ll
  136. convert-fp6-pzo.ll
  137. convert-fp6-scale.ll
  138. convert-fp8-pzo.ll
  139. convert-fp8-scale.ll
  140. convert-fptrunc-round.ll
  141. convert-int-sm20.ll
  142. convert-sm100.ll
  143. convert-sm100a.ll
  144. convert-sm103a.ll
  145. convert-sm80-sf.ll
  146. convert-sm80.ll
  147. convert-sm89.ll
  148. convert-sm90.ll
  149. convert-ue5m3x2.ll
  150. convert_fp4x2_sm_100f.ll
  151. convert_fp4x2_to_bf16x2.ll
  152. convert_fp6x2_sm_100f.ll
  153. convert_fp6x2_to_bf16x2.ll
  154. convert_fp8x2_sm_100f.ll
  155. convert_fp8x2_to_bf16x2.ll
  156. convert_s2f6x2_sm_100a.ll
  157. copysign.ll
  158. cp-async-bulk-g2s-cta-invalid.ll
  159. cp-async-bulk-g2s-cta-oob.ll
  160. cp-async-bulk-g2s-cta-relaxed.ll
  161. cp-async-bulk-g2s-cta-validate-data.ll
  162. cp-async-bulk-g2s-invalid.ll
  163. cp-async-bulk-g2s-mc32.ll
  164. cp-async-bulk-g2s-relaxed.ll
  165. cp-async-bulk-g2s-validate-data.ll
  166. cp-async-bulk-prefetch-evict-priority.ll
  167. cp-async-bulk-ptx86.ll
  168. cp-async-bulk-s2g-sm100.ll
  169. cp-async-bulk-tensor-g2s-1cta.ll
  170. cp-async-bulk-tensor-g2s-2cta.ll
  171. cp-async-bulk-tensor-g2s-cta-override.ll
  172. cp-async-bulk-tensor-g2s-cta-sm100.ll
  173. cp-async-bulk-tensor-g2s-cta-sm100a.ll
  174. cp-async-bulk-tensor-g2s-cta-sm90.ll
  175. cp-async-bulk-tensor-g2s-cta-validate-data.ll
  176. cp-async-bulk-tensor-g2s-gather4.ll
  177. cp-async-bulk-tensor-g2s-im2colw.ll
  178. cp-async-bulk-tensor-g2s-im2colw128.ll
  179. cp-async-bulk-tensor-g2s-invalid.ll
  180. cp-async-bulk-tensor-g2s-mc32.ll
  181. cp-async-bulk-tensor-g2s-override.ll
  182. cp-async-bulk-tensor-g2s-validate-data.ll
  183. cp-async-bulk-tensor-g2s.ll
  184. cp-async-bulk-tensor-prefetch-evict-priority.ll
  185. cp-async-bulk-tensor-prefetch-override-evict-priority.ll
  186. cp-async-bulk-tensor-prefetch-override.ll
  187. cp-async-bulk-tensor-prefetch-sm100a.ll
  188. cp-async-bulk-tensor-prefetch.ll
  189. cp-async-bulk-tensor-reduce-im2colw.ll
  190. cp-async-bulk-tensor-reduce-override.ll
  191. cp-async-bulk-tensor-reduce.ll
  192. cp-async-bulk-tensor-s2g-im2colw.ll
  193. cp-async-bulk-tensor-s2g-override.ll
  194. cp-async-bulk-tensor-s2g-scatter4.ll
  195. cp-async-bulk-tensor-s2g.ll
  196. cp-async-bulk.ll
  197. cse-mov-sym.ll
  198. ctlz.ll
  199. ctpop.ll
  200. cttz.ll
  201. custom-abi-preserve-reg.ll
  202. dag-cse.ll
  203. dead-shfl.ll
  204. default-sm.ll
  205. demote-vars.ll
  206. denormal-constant-fold.ll
  207. disable-opt.ll
  208. discard.ll
  209. disjoint-or-addr.ll
  210. distributed-shared-cluster.ll
  211. div-ri.ll
  212. div.ll
  213. divrem-combine.ll
  214. dot-product.ll
  215. dynamic-stackalloc-regression.ll
  216. dynamic_stackalloc.ll
  217. elect.ll
  218. empty-type.ll
  219. envreg.ll
  220. extern-shared-valid-name.ll
  221. extloadv.ll
  222. extract-subvector-bitcast.ll
  223. extractelement.ll
  224. f128-no-libcall-error.ll
  225. f16-abs.ll
  226. f16-add.ll
  227. f16-ex2.ll
  228. f16-instructions.ll
  229. f16-mul.ll
  230. f16-sub.ll
  231. f16x2-instructions.ll
  232. f32-ex2.ll
  233. f32-lg2.ll
  234. f32x2-convert-i32x2.ll
  235. f32x2-instructions.ll
  236. fabs-intrinsics.ll
  237. fast-math.ll
  238. fcos-no-fast-math.ll
  239. fence-proxy-sm90-ptx86.ll
  240. fence-proxy-sm90.ll
  241. fence-proxy-tensormap-invalid.ll
  242. fence-proxy-tensormap.ll
  243. fence-proxy.ll
  244. fence.ll
  245. fence.py
  246. fenv-no-libcall-error.ll
  247. fexp2.ll
  248. filetype-null.ll
  249. flo.ll
  250. float-to-arbitrary-fp.ll
  251. flog2.ll
  252. fma-assoc.ll
  253. fma-disable.ll
  254. fma-oob.ll
  255. fma-relu-contract.ll
  256. fma-relu-fma-intrinsic.ll
  257. fma-relu-instruction-flag.ll
  258. fma.ll
  259. fmax3.ll
  260. fminimum-fmaximum.ll
  261. fns.ll
  262. fold-movs.ll
  263. forward-ld-param.ll
  264. fp-add-f32x2.ll
  265. fp-add-invalid.ll
  266. fp-arith-sat.ll
  267. fp-contract-f32x2.ll
  268. fp-contract.ll
  269. fp-fma-f32x2.ll
  270. fp-fma-invalid.ll
  271. fp-fold-sub-f32x2.ll
  272. fp-fold-sub.ll
  273. fp-global.ll
  274. fp-literals.ll
  275. fp-mul-f32x2.ll
  276. fp-mul-invalid.ll
  277. fp-mul.ll
  278. fp128-compare-no-libcall-error.ll
  279. fp128-conv-no-libcall-error.ll
  280. fp128-global.ll
  281. fp128-storage-type.ll
  282. frameindex-lifetime.ll
  283. frem-precise.ll
  284. frem.ll
  285. fsin-no-fast-math.ll
  286. function-align.ll
  287. funnel-shift-clamp.ll
  288. generic-to-nvvm-ir.ll
  289. generic-to-nvvm.ll
  290. global-addrspace.ll
  291. global-ctor-empty.ll
  292. global-cycle-alias.ll
  293. global-cycle-internal-subcycle.ll
  294. global-cycle-internal.ll
  295. global-cycle.ll
  296. global-incomplete-init.ll
  297. global-ordering.ll
  298. global-variable-big.ll
  299. global-visibility.ll
  300. globals_init.ll
  301. globals_lowering.ll
  302. griddepcontrol.ll
  303. gvar-init.ll
  304. gvn-scalar-pre-reg-pressure.ll
  305. half.ll
  306. i1-array-global.ll
  307. i1-ext-load.ll
  308. i1-global.ll
  309. i1-icmp.ll
  310. i1-int-to-fp.ll
  311. i1-load-chain.ll
  312. i1-load-lower.ll
  313. i1-param.ll
  314. i1-select.ll
  315. i128-array.ll
  316. i128-global.ll
  317. i128-ld-st.ll
  318. i128-param.ll
  319. i128-retval.ll
  320. i128-struct.ll
  321. i128.ll
  322. i16x2-instructions.ll
  323. i32x2-instructions.ll
  324. i8-param.ll
  325. i8x2-instructions.ll
  326. i8x4-instructions.ll
  327. idioms.ll
  328. imad.ll
  329. indirect_byval.ll
  330. infer-address-space-join.ll
  331. infer-volatile-address-spaces.ll
  332. inline-asm-b128-test1.ll
  333. inline-asm-b128-test2.ll
  334. inline-asm-b128-test3.ll
  335. inline-asm-line-info-inlined-at.ll
  336. inline-asm-line-info-per-inst-compiler-generated.ll
  337. inline-asm-line-info-per-instruction.ll
  338. inline-asm-line-number-before.ll
  339. inline-asm.ll
  340. inlineasm-output-template.ll
  341. insert-vector-elt-bitcast-legalize.ll
  342. insert-vector-elt-shuffle-i8.ll
  343. insertelt-dynamic.ll
  344. intr-range.ll
  345. intrinsic-immarg-print-mismatched-signature.ll
  346. intrinsic-old.ll
  347. intrinsics-sm90-ptx81.ll
  348. intrinsics-sm90.ll
  349. intrinsics.ll
  350. isspacep.ll
  351. jump-table.ll
  352. kernel-param-align.ll
  353. ld-addrspace.ll
  354. ld-generic.ll
  355. ld-param-sink.ll
  356. ld-st-addrrspace.py
  357. ldg-invariant-256.ll
  358. ldg-invariant.ll
  359. ldparam-v4.ll
  360. ldu-i8.ll
  361. ldu-ldg.ll
  362. ldu-reg-plus-offset.ll
  363. lit.local.cfg
  364. llc-pipeline-npm.ll
  365. load-sext-i1.ll
  366. load-sm60.ll
  367. load-sm70.ll
  368. load-sm90.ll
  369. load-store-128.ll
  370. load-store-256-addressing-invariant.ll
  371. load-store-256-addressing.ll
  372. load-store-atomic.err.ll
  373. load-store-scalars.ll
  374. load-store-sm-70.ll
  375. load-store-sm-90.ll
  376. load-store-vectors-256.ll
  377. load-store-vectors.ll
  378. load-with-non-coherent-cache.ll
  379. load.py
  380. LoadStoreVectorizer.ll
  381. local-stack-frame.ll
  382. loop-vectorize.ll
  383. lower-aggr-copies-shared.ll
  384. lower-aggr-copies.ll
  385. lower-alloca.ll
  386. lower-args-alignment.ll
  387. lower-args-gridconstant.ll
  388. lower-args.ll
  389. lower-byval-args-dbg.ll
  390. lower-byval-args-icmp.ll
  391. lower-byval-args-idempotent.ll
  392. lower-byval-args-mem-attrs.ll
  393. lower-byval-args.ll
  394. lower-ctor-dtor.ll
  395. lower-kernel-ptr-arg.ll
  396. machine-cse-predicate-inversion-multiple-users.ll
  397. machine-cse-predicate-inversion-rollback.mir
  398. machine-cse-predicate-inversion-vector-float.ll
  399. machine-cse-predicate-inversion.ll
  400. machine-cse-predicate-no-inversion.ll
  401. machine-cse-sreg.mir
  402. machine-sink.ll
  403. machinelicm-no-preheader.mir
  404. MachineSink-call.ll
  405. MachineSink-convergent.ll
  406. managed.ll
  407. mark-kernel-ptrs-global.ll
  408. masked-divrem.ll
  409. masked-load-3xhalf.ll
  410. masked-load-vectors.ll
  411. masked-store-variable-mask.ll
  412. masked-store-vectors-256.ll
  413. match.ll
  414. math-intrins-sm53-ptx42.ll
  415. math-intrins-sm80-ptx70-autoupgrade.ll
  416. math-intrins-sm80-ptx70-instcombine.ll
  417. math-intrins-sm80-ptx70.ll
  418. math-intrins-sm86-ptx72-autoupgrade.ll
  419. math-intrins-sm86-ptx72.ll
  420. math-intrins.ll
  421. max-align.ll
  422. maxclusterrank.ll
  423. mbarrier.ll
  424. mbarrier_arr.ll
  425. mbarrier_arr_relaxed.ll
  426. mbarrier_layout_sm90_ptx93.ll
  427. mbarrier_tx.ll
  428. mbarrier_wait_sm80_ptx70.ll
  429. mbarrier_wait_sm80_ptx71.ll
  430. mbarrier_wait_sm90_ptx78.ll
  431. mbarrier_wait_sm90_ptx80.ll
  432. mbarrier_wait_sm90_ptx86.ll
  433. memcpy-alloca-align.ll
  434. minmax-negative.ll
  435. misaligned-vector-ldst.ll
  436. misched_func_call.ll
  437. mixed-precision-add-f32x2-downconvert-invalid.ll
  438. mixed-precision-add-f32x2-downconvert.ll
  439. mixed-precision-add-f32x2-upconvert-invalid.ll
  440. mixed-precision-add-f32x2-upconvert.ll
  441. mixed-precision-f32x2-sm-version.ll
  442. mixed-precision-fp.ll
  443. mixed-precision-mul-f32x2-downconvert-invalid.ll
  444. mixed-precision-mul-f32x2-downconvert.ll
  445. mixed-precision-sub-f32x2-downconvert-invalid.ll
  446. mixed-precision-sub-f32x2-downconvert.ll
  447. mixed-precision-sub-f32x2-upconvert-invalid.ll
  448. mixed-precision-sub-f32x2-upconvert.ll
  449. mma-no-sink-after-laneid-check.ll
  450. module-inline-asm.ll
  451. movmatrix.ll
  452. mul-with-overflow.ll
  453. mulhi-intrins.ll
  454. mulwide.ll
  455. naked-fn-with-frame-pointer.ll
  456. nanosleep.ll
  457. no-addrsig.ll
  458. no-extra-parens.ll
  459. no-f32x2.ll
  460. no-stack-protector-libcall-error.ll
  461. noduplicate-syncthreads.ll
  462. nofunc.ll
  463. noreturn.ll
  464. nounroll.ll
  465. nvcl-param-align.ll
  466. nvptx-aa-inline-asm.ll
  467. nvptx-aa.ll
  468. nvptx-fold-fma.ll
  469. nvptx-prec-divf32-flag.ll
  470. NVPTXAA_before_BasicAA.ll
  471. nvvm-abs.ll
  472. nvvm-annotations-D120129.ll
  473. nvvm-reflect-arch-O0.ll
  474. nvvm-reflect-arch.ll
  475. nvvm-reflect-module-flag.ll
  476. nvvm-reflect-ocl.ll
  477. nvvm-reflect-opaque.ll
  478. nvvm-reflect-options.ll
  479. nvvm-reflect.ll
  480. odd-integer-width.ll
  481. op-fence.ll
  482. packed-aggr-self-ptx70.ll
  483. packed-aggr.ll
  484. param-add.ll
  485. param-align.ll
  486. param-load-store.ll
  487. param-overalign.ll
  488. param-space-subqualifiers.ll
  489. param-vectorize-device.ll
  490. param-vectorize-kernel.ll
  491. pass-name.ll
  492. peephole-cvta-local-short-ptr.mir
  493. pm-event.ll
  494. pow2_mask_cmp.ll
  495. powi.ll
  496. pr126337.ll
  497. pr13291-i1-store.ll
  498. pr16278.ll
  499. pr17529.ll
  500. prefetch-inferas-test.ll
  501. prefetch-l1-32b.ll
  502. prefetch.ll
  503. prmt-const-folding.ll
  504. prmt.ll
  505. promote-param-align.ll
  506. proxy-reg-erasure-ptx.ll
  507. proxy-reg-erasure.mir
  508. ptr-global.ll
  509. ptx-version-validation.ll
  510. raw-sections-unsupported.ll
  511. rcp-opt.ll
  512. read-global-variable-constant.ll
  513. reduction-intrinsics.ll
  514. redux-sync-f32.ll
  515. redux-sync.ll
  516. refl1.ll
  517. reg-copy.ll
  518. reg-or-imm-verifier.mir
  519. reg-types.ll
  520. reqnctapercluster-const-fold.ll
  521. reqntid-const-fold.ll
  522. reserved-smem-offset.ll
  523. ret-align-mismatch.ll
  524. rotate-add.ll
  525. rotate.ll
  526. rotate_64.ll
  527. rsqrt-opt.ll
  528. rsqrt.ll
  529. sad-intrins.ll
  530. scalar-to-vector.ll
  531. scalarize-non-coalescable-v2f32.ll
  532. sched1.ll
  533. sched2.ll
  534. setmaxnreg-sm100a.ll
  535. setmaxnreg.ll
  536. setp-bool.ll
  537. sext-in-reg.ll
  538. sext-params.ll
  539. sext-setcc.ll
  540. shfl-p.ll
  541. shfl-sync-p.ll
  542. shfl-sync.ll
  543. shfl.ll
  544. shift-logic-cse.ll
  545. shift-opt.ll
  546. shift-parts.ll
  547. short-ptr.ll
  548. shuffle-vec-undef-init.ll
  549. simple-call.ll
  550. sm-110-rename.ll
  551. sm-version.ll
  552. spcompress-invalid.ll
  553. spcompress-sp2to4.ll
  554. spdecompress-invalid.ll
  555. spdecompress-sp1to16.ll
  556. spdecompress-sp1to2.ll
  557. spdecompress-sp1to4.ll
  558. spdecompress-sp1to8.ll
  559. spdecompress-sp2to16.ll
  560. spdecompress-sp2to4.ll
  561. spdecompress-sp2to8.ll
  562. spdecompress-sp4to16.ll
  563. spdecompress-sp4to8.ll
  564. speculative-execution-divergent-target.ll
  565. sqrt-approx.ll
  566. srl-bitcast-bv.ll
  567. st-addrspace.ll
  568. st-generic.ll
  569. st-param-imm.ll
  570. st_async_mbarrier.ll
  571. st_async_mbarrier_b128.ll
  572. st_async_release.ll
  573. st_async_release_multimem.ll
  574. st_bulk.ll
  575. st_bulk_i32.ll
  576. stackaddress.ll
  577. stacksaverestore.ll
  578. stop-after-npm.ll
  579. store-i1-trunc.ll
  580. store-retval.ll
  581. store-sm60.ll
  582. store-sm70.ll
  583. store-sm90.ll
  584. store-undef.ll
  585. store.py
  586. sub-byte-constant-vector-convert.ll
  587. sub-byte-constant-vectors-i4-i2.ll
  588. surf-read-cuda.ll
  589. surf-read.ll
  590. surf-tex.py
  591. surf-write-cuda.ll
  592. surf-write.ll
  593. switch-loop-header.mir
  594. switch.ll
  595. symbol-naming.ll
  596. szext.ll
  597. tag-invariant-loads.ll
  598. TailDuplication-convergent.ll
  599. tanhf.ll
  600. tcgen05-alloc-dealloc-exclusive.ll
  601. tcgen05-alloc.ll
  602. tcgen05-commit-sm107.ll
  603. tcgen05-commit.ll
  604. tcgen05-cp.ll
  605. tcgen05-fence.ll
  606. tcgen05-ld-red.ll
  607. tcgen05-ld.ll
  608. tcgen05-mma-block-scale-decompress-b.ll
  609. tcgen05-mma-block-scale-invalid.ll
  610. tcgen05-mma-block-scale-ptx88-aa.ll
  611. tcgen05-mma-block-scale-ptx88.ll
  612. tcgen05-mma-block-scale.ll
  613. tcgen05-mma-collector-b-i8-invalid.ll
  614. tcgen05-mma-collector-b.ll
  615. tcgen05-mma-decompress-b.ll
  616. tcgen05-mma-disable-output-lane-collector-b.ll
  617. tcgen05-mma-disable-output-lane-decompress-b.ll
  618. tcgen05-mma-disable-output-lane-i8.ll
  619. tcgen05-mma-disable-output-lane.ll
  620. tcgen05-mma-i8.ll
  621. tcgen05-mma-invalid.ll
  622. tcgen05-mma-scale-d-invalid.ll
  623. tcgen05-mma-scale-d.ll
  624. tcgen05-mma-sp-collector-b-i8-invalid.ll
  625. tcgen05-mma-sp-collector-b.ll
  626. tcgen05-mma-sp-disable-output-lane-collector-b.ll
  627. tcgen05-mma-sp-mxf4-mxf4nvf4-kind.ll
  628. tcgen05-mma-ti16-kind.ll
  629. tcgen05-mma-ws-i8.ll
  630. tcgen05-mma-ws.ll
  631. tcgen05-mma.ll
  632. tcgen05-shift.ll
  633. tcgen05-st.ll
  634. tensormap_replace.ll
  635. tensormap_replace_invalid.ll
  636. tensormap_replace_sm_100a.ll
  637. tensormap_replace_sm_103a.ll
  638. tex-read-cuda.ll
  639. tex-read.ll
  640. texsurf-queries.ll
  641. thread-fence.ll
  642. tid-range.ll
  643. trunc-setcc.ll
  644. trunc-tofp.ll
  645. unaligned-param-load-store.ll
  646. unfold-masked-merge-vector-variablemask.ll
  647. unknown-intrinsic.ll
  648. unpack-halves.ll
  649. unreachable.ll
  650. unrecognized-sm1x.ll
  651. upgrade-nvvm-annotations.ll
  652. used-bytes-mask.ll
  653. vaargs.ll
  654. variadics-backend.ll
  655. variadics-lowering.ll
  656. vec-param-load.ll
  657. vec8.ll
  658. vector-args.ll
  659. vector-call.ll
  660. vector-compare.ll
  661. vector-global.ll
  662. vector-loads.ll
  663. vector-returns.ll
  664. vector-select.ll
  665. vector-stores.ll
  666. vectorize-misaligned.ll
  667. volatile-local.ll
  668. vote.ll
  669. weak-global.ll
  670. weak-linkage.ll
  671. wgmma-sm90a-fence.ll
  672. wmma-ptx60-sm70.py
  673. wmma-ptx61-sm70.py
  674. wmma-ptx63-sm72.py
  675. wmma-ptx63-sm75.py
  676. wmma-ptx64-sm70.py
  677. wmma-ptx65-sm75.py
  678. wmma-ptx71-sm80.py
  679. wmma-ptx78-sm90.py
  680. wmma-ptx86-sm100a.py
  681. wmma-ptx86-sm101a.py
  682. wmma-ptx87-sm120a.py
  683. wmma-ptx88-sm100f.py
  684. wmma-ptx88-sm120a.py
  685. wmma-ptx88-sm120f.py
  686. wmma-ptx90-sm110f.py
  687. wmma-ptx91-sm120a.py
  688. wmma-ptx91-sm120f.py
  689. wmma-ptx94-sm100f.py
  690. wmma-ptx94-sm110f.py
  691. wmma-ptx94-sm120f.py
  692. wmma-ptx94-sm90a.py
  693. wmma.py
  694. zeroext-32bit.ll