/llvm-project/mlir/test/Integration/GPU/CUDA/TensorCore/ |
H A D | wmma-matmul-f32.mlir | 10 %0 = memref.alloc() : memref<16x16xf16> 11 %22 = memref.alloc() : memref<16x16xf32> 12 %1 = memref.alloc() : memref<16x16xf32> 17 %c16 = arith.constant 16 : index 24 memref.store %f1, %0[%arg0, %arg1] : memref<16x16xf16> 30 memref.store %f0, %22[%arg0, %arg1] : memref<16x16xf32> 34 %2 = memref.cast %0 : memref<16x16xf16> to memref<*xf16> 35 %33 = memref.cast %22 : memref<16x16xf32> to memref<*xf32> 36 %3 = memref.cast %1 : memref<16x16xf32> to memref<*xf32> 42 %A = gpu.subgroup_mma_load_matrix %0[%c0, %c0] {leadDimension = 16 [all...] |
/llvm-project/llvm/test/Analysis/CostModel/X86/ |
H A D | mul-latency.ll | 16 ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = mul i64 undef, 16 17 ; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2i64 = mul <2 x i64> undef, <i64 8, i64 16> 18 ; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4i64 = mul <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16> 19 ; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8i64 = mul <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256> 20 ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = mul i32 undef, 16 21 ; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4i32 = mul <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16> 22 ; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i32 = mul <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256> 23 ; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i32 = mul <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i3 [all...] |
H A D | mul.ll | 16 ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = mul i64 undef, 16 17 ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = mul <2 x i64> undef, <i64 8, i64 16> 18 ; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4i64 = mul <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16> 19 ; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i64 = mul <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256> 20 ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = mul i32 undef, 16 21 ; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4i32 = mul <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16> 22 ; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8i32 = mul <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256> 23 ; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16i32 = mul <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i3 [all...] |
H A D | mul-sizelatency.ll | 16 ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = mul i64 undef, 16 17 ; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2i64 = mul <2 x i64> undef, <i64 8, i64 16> 18 ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V4i64 = mul <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16> 19 ; SSE2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8i64 = mul <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256> 20 ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = mul i32 undef, 16 21 ; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = mul <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16> 22 ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8i32 = mul <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256> 23 ; SSE2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V16i32 = mul <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i3 [all...] |
H A D | mul-codesize.ll | 16 ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = mul i64 undef, 16 17 ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2i64 = mul <2 x i64> undef, <i64 8, i64 16> 18 ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4i64 = mul <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16> 19 ; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8i64 = mul <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256> 20 ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = mul i32 undef, 16 21 ; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = mul <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16> 22 ; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8i32 = mul <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256> 23 ; SSE2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V16i32 = mul <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i3 [all...] |
H A D | rem-latency.ll | 23 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = srem <16 x i32> undef, undef 26 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = srem <16 x i16> undef, undef 29 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = srem <16 x i8> undef, undef 42 %V16i32 = srem <16 x i32> undef, undef 46 %V16i16 = srem <16 x i16> undef, undef 50 %V16i8 = srem <16 x i8> undef, undef 66 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, undef 69 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = urem <16 x i16> undef, undef 72 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = urem <16 x i8> undef, undef 85 %V16i32 = urem <16 [all...] |
H A D | rem-sizelatency.ll | 23 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = srem <16 x i32> undef, undef 26 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = srem <16 x i16> undef, undef 29 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = srem <16 x i8> undef, undef 42 %V16i32 = srem <16 x i32> undef, undef 46 %V16i16 = srem <16 x i16> undef, undef 50 %V16i8 = srem <16 x i8> undef, undef 66 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, undef 69 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = urem <16 x i16> undef, undef 72 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = urem <16 x i8> undef, undef 85 %V16i32 = urem <16 [all...] |
H A D | rem-codesize.ll | 23 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = srem <16 x i32> undef, undef 26 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = srem <16 x i16> undef, undef 29 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = srem <16 x i8> undef, undef 42 %V16i32 = srem <16 x i32> undef, undef 46 %V16i16 = srem <16 x i16> undef, undef 50 %V16i8 = srem <16 x i8> undef, undef 66 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, undef 69 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = urem <16 x i16> undef, undef 72 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = urem <16 x i8> undef, undef 85 %V16i32 = urem <16 [all...] |
H A D | div-latency.ll | 23 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = sdiv <16 x i32> undef, undef 26 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = sdiv <16 x i16> undef, undef 29 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = sdiv <16 x i8> undef, undef 42 %V16i32 = sdiv <16 x i32> undef, undef 46 %V16i16 = sdiv <16 x i16> undef, undef 50 %V16i8 = sdiv <16 x i8> undef, undef 66 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, undef 69 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = udiv <16 x i16> undef, undef 72 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = udiv <16 x i8> undef, undef 85 %V16i32 = udiv <16 [all...] |
H A D | div-sizelatency.ll | 23 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = sdiv <16 x i32> undef, undef 26 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = sdiv <16 x i16> undef, undef 29 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = sdiv <16 x i8> undef, undef 42 %V16i32 = sdiv <16 x i32> undef, undef 46 %V16i16 = sdiv <16 x i16> undef, undef 50 %V16i8 = sdiv <16 x i8> undef, undef 66 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, undef 69 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = udiv <16 x i16> undef, undef 72 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = udiv <16 x i8> undef, undef 85 %V16i32 = udiv <16 [all...] |
H A D | div-codesize.ll | 23 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = sdiv <16 x i32> undef, undef 26 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = sdiv <16 x i16> undef, undef 29 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = sdiv <16 x i8> undef, undef 42 %V16i32 = sdiv <16 x i32> undef, undef 46 %V16i16 = sdiv <16 x i16> undef, undef 50 %V16i8 = sdiv <16 x i8> undef, undef 66 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, undef 69 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = udiv <16 x i16> undef, undef 72 ; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = udiv <16 x i8> undef, undef 85 %V16i32 = udiv <16 [all...] |
H A D | div.ll | 23 ; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V16i32 = sdiv <16 x i32> undef, undef 26 ; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V16i16 = sdiv <16 x i16> undef, undef 29 ; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V16i8 = sdiv <16 x i8> undef, undef 42 %V16i32 = sdiv <16 x i32> undef, undef 46 %V16i16 = sdiv <16 x i16> undef, undef 50 %V16i8 = sdiv <16 x i8> undef, undef 66 ; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V16i32 = udiv <16 x i32> undef, undef 69 ; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V16i16 = udiv <16 x i16> undef, undef 72 ; CHECK-NEXT: Cost Model: Found an estimated cost of 320 for instruction: %V16i8 = udiv <16 x i8> undef, undef 85 %V16i32 = udiv <16 [all...] |
H A D | rem.ll | 23 ; SSE-NEXT: Cost Model: Found an estimated cost of 960 for instruction: %V16i32 = srem <16 x i32> undef, undef 26 ; SSE-NEXT: Cost Model: Found an estimated cost of 1280 for instruction: %V16i16 = srem <16 x i16> undef, undef 29 ; SSE-NEXT: Cost Model: Found an estimated cost of 1600 for instruction: %V16i8 = srem <16 x i8> undef, undef 42 ; AVX-NEXT: Cost Model: Found an estimated cost of 960 for instruction: %V16i32 = srem <16 x i32> undef, undef 45 ; AVX-NEXT: Cost Model: Found an estimated cost of 1280 for instruction: %V16i16 = srem <16 x i16> undef, undef 48 ; AVX-NEXT: Cost Model: Found an estimated cost of 1600 for instruction: %V16i8 = srem <16 x i8> undef, undef 61 ; AVX512-NEXT: Cost Model: Found an estimated cost of 960 for instruction: %V16i32 = srem <16 x i32> undef, undef 64 ; AVX512-NEXT: Cost Model: Found an estimated cost of 1280 for instruction: %V16i16 = srem <16 x i16> undef, undef 67 ; AVX512-NEXT: Cost Model: Found an estimated cost of 1600 for instruction: %V16i8 = srem <16 x i8> undef, undef 80 %V16i32 = srem <16 [all...] |
/llvm-project/llvm/test/CodeGen/Hexagon/ |
H A D | reg-scavenger-valid-slot.ll | 39 %asmresult16 = extractvalue { i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32 } %0, 16 52 %1 = tail call { <16 x i32>, <16 x i32>, <16 x i32>, <16 x i32>, <16 x i32>, <16 x i32>, <16 x i32>, <16 x i32>, <16 [all...] |
H A D | reg-scavengebug.ll | 7 declare <16 x i32> @llvm.hexagon.V6.hi(<32 x i32>) #0 10 declare <16 x i32> @llvm.hexagon.V6.vshuffb(<16 x i32>) #0 13 declare <32 x i32> @llvm.hexagon.V6.vmpyubv(<16 x i32>, <16 x i32>) #0 16 declare <16 x i32> @llvm.hexagon.V6.valignb(<16 x i32>, <16 x i32>, i32) #0 19 declare <16 x i32> @llvm.hexagon.V6.vaddh(<16 [all...] |
/llvm-project/llvm/test/Analysis/CostModel/AMDGPU/ |
H A D | mul.ll | 13 ; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v4i32 = mul <4 x i32> undef, undef 25 ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v8i32 = mul <8 x i32> undef, undef 68 ; SLOW16-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v3i16 = mul <3 x i16> undef, undef 69 ; SLOW16-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v4i16 = mul <4 x i16> undef, undef 71 ; SLOW16-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %v16i16 = mul <16 x i16> undef, undef 80 ; FAST16-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v5i16 = mul <5 x i16> undef, undef 81 ; FAST16-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v16i16 = mul <16 x i16> undef, undef 90 ; SLOW16-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %v5i16 = mul <5 x i16> undef, undef 91 ; SLOW16-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %v16i16 = mul <16 x i16> undef, undef 101 ; FAST16-SIZE-NEXT: Cost Model: Found an estimated cost of 16 fo [all...] |
H A D | div.ll | 22 ; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, undef 25 ; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = sdiv <16 x i16> undef, undef 28 ; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = sdiv <16 x i8> undef, undef 41 ; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, undef 43 ; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = sdiv <8 x i16> undef, undef 44 ; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = sdiv <16 x i16> undef, undef 47 ; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = sdiv <16 [all...] |
H A D | rem.ll | 22 ; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, undef 25 ; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = srem <16 x i16> undef, undef 28 ; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = srem <16 x i8> undef, undef 41 ; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, undef 44 ; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = srem <16 x i16> undef, undef 47 ; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = srem <16 x i8> undef, undef 60 ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = srem <16 x i32> undef, undef 63 ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = srem <16 x i16> undef, undef 66 ; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = srem <16 [all...] |
/llvm-project/llvm/test/Analysis/CostModel/AArch64/ |
H A D | div.ll | 4 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128" 17 ; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = sdiv <16 x i32> undef, undef 22 ; CHECK-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = sdiv <16 x i16> undef, undef 28 ; CHECK-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = sdiv <16 x i8> undef, undef 44 %V16i32 = sdiv <16 x i32> undef, undef 50 %V16i16 = sdiv <16 x i16> undef, undef 57 %V16i8 = sdiv <16 x i8> undef, undef 75 ; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = udiv <16 x i32> undef, undef 80 ; CHECK-NEXT: Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = udiv <16 x i16> undef, undef 86 ; CHECK-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = udiv <16 [all...] |
H A D | rem.ll | 4 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128" 17 ; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = srem <16 x i32> undef, undef 22 ; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = srem <16 x i16> undef, undef 28 ; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i8 = srem <16 x i8> undef, undef 44 %V16i32 = srem <16 x i32> undef, undef 50 %V16i16 = srem <16 x i16> undef, undef 57 %V16i8 = srem <16 x i8> undef, undef 75 ; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = urem <16 x i32> undef, undef 80 ; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = urem <16 x i16> undef, undef 86 ; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V16i8 = urem <16 [all...] |
/llvm-project/llvm/test/CodeGen/X86/ |
H A D | avx512-vpternlog-commute.ll | 6 declare <16 x i32> @llvm.x86.avx512.pternlog.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i32) 8 define <16 x i32> @vpternlog_v16i32_012(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2) { 13 …%1 = call <16 x i32> @llvm.x86.avx512.pternlog.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x… 14 ret <16 x i32> %1 17 define <16 x i32> @vpternlog_v16i32_102(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2) { 22 …%1 = call <16 x i32> @llvm.x86.avx512.pternlog.d.512(<16 x i32> %x1, <16 x i32> %x0, <16 x i32> %x… 23 ret <16 x i32> %1 26 define <16 x i32> @vpternlog_v16i32_210(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2) { 31 …%1 = call <16 x i32> @llvm.x86.avx512.pternlog.d.512(<16 x i32> %x2, <16 x i32> %x1, <16 x i32> %x… 32 ret <16 x i32> %1 [all …]
|
/llvm-project/llvm/test/MC/AArch64/ |
H A D | neon-tbl.s | 9 tbl v0.8b, { v1.16b }, v2.8b 10 tbl v0.8b, { v1.16b, v2.16b }, v2.8b 11 tbl v0.8b, { v1.16b, v2.16b, v3.16b }, v2.8b 12 tbl v0.8b, { v1.16b, v2.16b, v3.16b, v4.16b }, v2.8b 13 tbl v0.8b, { v31.16b, v0.16b, v1.16b, v2.16b }, v2.8b 15 // CHECK: tbl v0.8b, { v1.16b }, v2.8b // encoding: [0x20,0x00,0x02,0x0e] 16 // CHECK: tbl v0.8b, { v1.16b, v2.16b }, v2.8b // encoding: [0x20,0x20,0x02,0x0e] 17 // CHECK: tbl v0.8b, { v1.16b, v2.16b, v3.16b }, v2.8b // encoding: [0x20,0x40,0x02,0x0e] 18 // CHECK: tbl v0.8b, { v1.16b, v2.16b, v3.16b, v4.16b }, v2.8b // encoding: [0x20,0x60,0x02,0x0e] 19 // CHECK: tbl v0.8b, { v31.16b, v0.16b, v1.16b, v2.16b }, v2.8b // encoding: [0xe0,0x63,0x02,0x0e] [all …]
|
/llvm-project/llvm/test/CodeGen/AArch64/ |
H A D | misched-fusion-aes.ll | 24 declare <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %d, <16 x i8> %k) 25 declare <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %d) 26 declare <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %d, <16 x i8> %k) 27 declare <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %d) 29 define void @aesea(ptr %a0, ptr %b0, ptr %c0, <16 x i8> %d, <16 x i8> %e) { 30 %d0 = load <16 x i8>, ptr %a0 31 %a1 = getelementptr inbounds <16 x i8>, ptr %a0, i64 1 32 %d1 = load <16 x i8>, ptr %a1 33 %a2 = getelementptr inbounds <16 x i8>, ptr %a0, i64 2 34 %d2 = load <16 x i8>, ptr %a2 [all …]
|
/llvm-project/llvm/test/CodeGen/ARM/ |
H A D | misched-fusion-aes.ll | 3 declare <16 x i8> @llvm.arm.neon.aese(<16 x i8> %d, <16 x i8> %k) 4 declare <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %d) 5 declare <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %d, <16 x i8> %k) 6 declare <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %d) 8 define void @aesea(ptr %a0, ptr %b0, ptr %c0, <16 x i8> %d, <16 x i8> %e) { 9 %d0 = load <16 x i8>, ptr %a0 10 %a1 = getelementptr inbounds <16 x i8>, ptr %a0, i64 1 11 %d1 = load <16 x i8>, ptr %a1 12 %a2 = getelementptr inbounds <16 x i8>, ptr %a0, i64 2 13 %d2 = load <16 x i8>, ptr %a2 [all …]
|
/llvm-project/llvm/test/CodeGen/SystemZ/ |
H A D | frame-19.ll | 5 ; We need to allocate a 16-byte spill slot and save the 8 call-saved FPRs. 6 ; The frame size should be exactly 160 + 16 + 8 * 8 = 240. 30 %v0 = load volatile <16 x i8>, ptr %ptr 31 %v1 = load volatile <16 x i8>, ptr %ptr 32 %v2 = load volatile <16 x i8>, ptr %ptr 33 %v3 = load volatile <16 x i8>, ptr %ptr 34 %v4 = load volatile <16 x i8>, ptr %ptr 35 %v5 = load volatile <16 x i8>, ptr %ptr 36 %v6 = load volatile <16 x i8>, ptr %ptr 37 %v7 = load volatile <16 x i8>, ptr %ptr [all …]
|