From 1a9195d817d35a0464394018a3575ccfe49eda80 Mon Sep 17 00:00:00 2001 From: Graham Hunter Date: Tue, 17 Sep 2019 10:19:23 +0000 Subject: [PATCH] [SVE][MVT] Fixed-length vector MVT ranges * Reordered MVT simple types to group scalable vector types together. * New range functions in MachineValueType.h to only iterate over the fixed-length int/fp vector types. * Stopped backends which don't support scalable vector types from iterating over scalable types. Reviewers: sdesmalen, greened Reviewed By: greened Differential Revision: https://reviews.llvm.org/D66339 llvm-svn: 372099 --- llvm/include/llvm/CodeGen/ValueTypes.td | 118 ++++++------ llvm/include/llvm/Support/MachineValueType.h | 202 ++++++++++++--------- llvm/lib/CodeGen/TargetLoweringBase.cpp | 3 +- llvm/lib/Target/AArch64/AArch64ISelLowering.cpp | 8 +- llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp | 2 +- llvm/lib/Target/ARM/ARMISelLowering.cpp | 8 +- llvm/lib/Target/Hexagon/HexagonISelLowering.cpp | 6 +- llvm/lib/Target/Hexagon/HexagonSubtarget.h | 2 +- .../Target/Hexagon/HexagonTargetTransformInfo.cpp | 2 + llvm/lib/Target/Mips/MipsISelLowering.cpp | 2 +- llvm/lib/Target/Mips/MipsSEISelLowering.cpp | 4 +- llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp | 2 +- llvm/lib/Target/PowerPC/PPCISelLowering.cpp | 4 +- llvm/lib/Target/Sparc/SparcISelLowering.cpp | 2 +- llvm/lib/Target/SystemZ/SystemZISelLowering.cpp | 6 +- .../Target/WebAssembly/WebAssemblyISelLowering.cpp | 4 +- llvm/lib/Target/X86/X86ISelLowering.cpp | 8 +- llvm/utils/TableGen/CodeGenDAGPatterns.cpp | 10 +- 18 files changed, 214 insertions(+), 179 deletions(-) diff --git a/llvm/include/llvm/CodeGen/ValueTypes.td b/llvm/include/llvm/CodeGen/ValueTypes.td index 3293c29..1d80e25 100644 --- a/llvm/include/llvm/CodeGen/ValueTypes.td +++ b/llvm/include/llvm/CodeGen/ValueTypes.td @@ -87,65 +87,65 @@ def v32i64 : ValueType<2048,61>; // 32 x i64 vector value def v1i128 : ValueType<128, 62>; // 1 x i128 vector value -def nxv1i1 : ValueType<1, 63>; // n x 1 x i1 vector value -def nxv2i1 : ValueType<2, 64>; // n x 2 x i1 vector value -def nxv4i1 : ValueType<4, 65>; // n x 4 x i1 vector value -def nxv8i1 : ValueType<8, 66>; // n x 8 x i1 vector value -def nxv16i1 : ValueType<16, 67>; // n x 16 x i1 vector value -def nxv32i1 : ValueType<32, 68>; // n x 32 x i1 vector value - -def nxv1i8 : ValueType<8, 69>; // n x 1 x i8 vector value -def nxv2i8 : ValueType<16, 70>; // n x 2 x i8 vector value -def nxv4i8 : ValueType<32, 71>; // n x 4 x i8 vector value -def nxv8i8 : ValueType<64, 72>; // n x 8 x i8 vector value -def nxv16i8 : ValueType<128, 73>; // n x 16 x i8 vector value -def nxv32i8 : ValueType<256, 74>; // n x 32 x i8 vector value - -def nxv1i16 : ValueType<16, 75>; // n x 1 x i16 vector value -def nxv2i16 : ValueType<32, 76>; // n x 2 x i16 vector value -def nxv4i16 : ValueType<64, 77>; // n x 4 x i16 vector value -def nxv8i16 : ValueType<128, 78>; // n x 8 x i16 vector value -def nxv16i16: ValueType<256, 79>; // n x 16 x i16 vector value -def nxv32i16: ValueType<512, 80>; // n x 32 x i16 vector value - -def nxv1i32 : ValueType<32, 81>; // n x 1 x i32 vector value -def nxv2i32 : ValueType<64, 82>; // n x 2 x i32 vector value -def nxv4i32 : ValueType<128, 83>; // n x 4 x i32 vector value -def nxv8i32 : ValueType<256, 84>; // n x 8 x i32 vector value -def nxv16i32: ValueType<512, 85>; // n x 16 x i32 vector value -def nxv32i32: ValueType<1024,86>; // n x 32 x i32 vector value - -def nxv1i64 : ValueType<64, 87>; // n x 1 x i64 vector value -def nxv2i64 : ValueType<128, 88>; // n x 2 x i64 vector value -def nxv4i64 : ValueType<256, 89>; // n x 4 x i64 vector value -def nxv8i64 : ValueType<512, 90>; // n x 8 x i64 vector value -def nxv16i64: ValueType<1024,91>; // n x 16 x i64 vector value -def nxv32i64: ValueType<2048,92>; // n x 32 x i64 vector value - -def v2f16 : ValueType<32 , 93>; // 2 x f16 vector value -def v3f16 : ValueType<48 , 94>; // 3 x f16 vector value -def v4f16 : ValueType<64 , 95>; // 4 x f16 vector value -def v8f16 : ValueType<128, 96>; // 8 x f16 vector value -def v16f16 : ValueType<256, 97>; // 8 x f16 vector value -def v32f16 : ValueType<512, 98>; // 8 x f16 vector value -def v1f32 : ValueType<32 , 99>; // 1 x f32 vector value -def v2f32 : ValueType<64 , 100>; // 2 x f32 vector value -def v3f32 : ValueType<96 , 101>; // 3 x f32 vector value -def v4f32 : ValueType<128, 102>; // 4 x f32 vector value -def v5f32 : ValueType<160, 103>; // 5 x f32 vector value -def v8f32 : ValueType<256, 104>; // 8 x f32 vector value -def v16f32 : ValueType<512, 105>; // 16 x f32 vector value -def v32f32 : ValueType<1024, 106>; // 32 x f32 vector value -def v64f32 : ValueType<2048, 107>; // 64 x f32 vector value -def v128f32 : ValueType<4096, 108>; // 128 x f32 vector value -def v256f32 : ValueType<8182, 109>; // 256 x f32 vector value -def v512f32 : ValueType<16384, 110>; // 512 x f32 vector value -def v1024f32 : ValueType<32768, 111>; // 1024 x f32 vector value -def v2048f32 : ValueType<65536, 112>; // 2048 x f32 vector value -def v1f64 : ValueType<64, 113>; // 1 x f64 vector value -def v2f64 : ValueType<128, 114>; // 2 x f64 vector value -def v4f64 : ValueType<256, 115>; // 4 x f64 vector value -def v8f64 : ValueType<512, 116>; // 8 x f64 vector value +def v2f16 : ValueType<32 , 63>; // 2 x f16 vector value +def v3f16 : ValueType<48 , 64>; // 3 x f16 vector value +def v4f16 : ValueType<64 , 65>; // 4 x f16 vector value +def v8f16 : ValueType<128, 66>; // 8 x f16 vector value +def v16f16 : ValueType<256, 67>; // 8 x f16 vector value +def v32f16 : ValueType<512, 68>; // 8 x f16 vector value +def v1f32 : ValueType<32 , 69>; // 1 x f32 vector value +def v2f32 : ValueType<64 , 70>; // 2 x f32 vector value +def v3f32 : ValueType<96 , 71>; // 3 x f32 vector value +def v4f32 : ValueType<128, 72>; // 4 x f32 vector value +def v5f32 : ValueType<160, 73>; // 5 x f32 vector value +def v8f32 : ValueType<256, 74>; // 8 x f32 vector value +def v16f32 : ValueType<512, 75>; // 16 x f32 vector value +def v32f32 : ValueType<1024, 76>; // 32 x f32 vector value +def v64f32 : ValueType<2048, 77>; // 64 x f32 vector value +def v128f32 : ValueType<4096, 78>; // 128 x f32 vector value +def v256f32 : ValueType<8182, 79>; // 256 x f32 vector value +def v512f32 : ValueType<16384, 80>; // 512 x f32 vector value +def v1024f32 : ValueType<32768, 81>; // 1024 x f32 vector value +def v2048f32 : ValueType<65536, 82>; // 2048 x f32 vector value +def v1f64 : ValueType<64, 83>; // 1 x f64 vector value +def v2f64 : ValueType<128, 84>; // 2 x f64 vector value +def v4f64 : ValueType<256, 85>; // 4 x f64 vector value +def v8f64 : ValueType<512, 86>; // 8 x f64 vector value + +def nxv1i1 : ValueType<1, 87>; // n x 1 x i1 vector value +def nxv2i1 : ValueType<2, 88>; // n x 2 x i1 vector value +def nxv4i1 : ValueType<4, 89>; // n x 4 x i1 vector value +def nxv8i1 : ValueType<8, 90>; // n x 8 x i1 vector value +def nxv16i1 : ValueType<16, 91>; // n x 16 x i1 vector value +def nxv32i1 : ValueType<32, 92>; // n x 32 x i1 vector value + +def nxv1i8 : ValueType<8, 93>; // n x 1 x i8 vector value +def nxv2i8 : ValueType<16, 94>; // n x 2 x i8 vector value +def nxv4i8 : ValueType<32, 95>; // n x 4 x i8 vector value +def nxv8i8 : ValueType<64, 96>; // n x 8 x i8 vector value +def nxv16i8 : ValueType<128, 97>; // n x 16 x i8 vector value +def nxv32i8 : ValueType<256, 98>; // n x 32 x i8 vector value + +def nxv1i16 : ValueType<16, 99>; // n x 1 x i16 vector value +def nxv2i16 : ValueType<32, 100>; // n x 2 x i16 vector value +def nxv4i16 : ValueType<64, 101>; // n x 4 x i16 vector value +def nxv8i16 : ValueType<128, 102>; // n x 8 x i16 vector value +def nxv16i16: ValueType<256, 103>; // n x 16 x i16 vector value +def nxv32i16: ValueType<512, 104>; // n x 32 x i16 vector value + +def nxv1i32 : ValueType<32, 105>; // n x 1 x i32 vector value +def nxv2i32 : ValueType<64, 106>; // n x 2 x i32 vector value +def nxv4i32 : ValueType<128, 107>; // n x 4 x i32 vector value +def nxv8i32 : ValueType<256, 108>; // n x 8 x i32 vector value +def nxv16i32: ValueType<512, 109>; // n x 16 x i32 vector value +def nxv32i32: ValueType<1024,110>; // n x 32 x i32 vector value + +def nxv1i64 : ValueType<64, 111>; // n x 1 x i64 vector value +def nxv2i64 : ValueType<128, 112>; // n x 2 x i64 vector value +def nxv4i64 : ValueType<256, 113>; // n x 4 x i64 vector value +def nxv8i64 : ValueType<512, 114>; // n x 8 x i64 vector value +def nxv16i64: ValueType<1024,115>; // n x 16 x i64 vector value +def nxv32i64: ValueType<2048,116>; // n x 32 x i64 vector value def nxv2f16 : ValueType<32 , 117>; // n x 2 x f16 vector value def nxv4f16 : ValueType<64 , 118>; // n x 4 x f16 vector value diff --git a/llvm/include/llvm/Support/MachineValueType.h b/llvm/include/llvm/Support/MachineValueType.h index f15475b..ae3079c 100644 --- a/llvm/include/llvm/Support/MachineValueType.h +++ b/llvm/include/llvm/Support/MachineValueType.h @@ -112,72 +112,77 @@ namespace llvm { v1i128 = 62, // 1 x i128 - // Scalable integer types - nxv1i1 = 63, // n x 1 x i1 - nxv2i1 = 64, // n x 2 x i1 - nxv4i1 = 65, // n x 4 x i1 - nxv8i1 = 66, // n x 8 x i1 - nxv16i1 = 67, // n x 16 x i1 - nxv32i1 = 68, // n x 32 x i1 - - nxv1i8 = 69, // n x 1 x i8 - nxv2i8 = 70, // n x 2 x i8 - nxv4i8 = 71, // n x 4 x i8 - nxv8i8 = 72, // n x 8 x i8 - nxv16i8 = 73, // n x 16 x i8 - nxv32i8 = 74, // n x 32 x i8 - - nxv1i16 = 75, // n x 1 x i16 - nxv2i16 = 76, // n x 2 x i16 - nxv4i16 = 77, // n x 4 x i16 - nxv8i16 = 78, // n x 8 x i16 - nxv16i16 = 79, // n x 16 x i16 - nxv32i16 = 80, // n x 32 x i16 - - nxv1i32 = 81, // n x 1 x i32 - nxv2i32 = 82, // n x 2 x i32 - nxv4i32 = 83, // n x 4 x i32 - nxv8i32 = 84, // n x 8 x i32 - nxv16i32 = 85, // n x 16 x i32 - nxv32i32 = 86, // n x 32 x i32 - - nxv1i64 = 87, // n x 1 x i64 - nxv2i64 = 88, // n x 2 x i64 - nxv4i64 = 89, // n x 4 x i64 - nxv8i64 = 90, // n x 8 x i64 - nxv16i64 = 91, // n x 16 x i64 - nxv32i64 = 92, // n x 32 x i64 - - FIRST_INTEGER_VECTOR_VALUETYPE = v1i1, - LAST_INTEGER_VECTOR_VALUETYPE = nxv32i64, - - FIRST_INTEGER_SCALABLE_VALUETYPE = nxv1i1, - LAST_INTEGER_SCALABLE_VALUETYPE = nxv32i64, - - v2f16 = 93, // 2 x f16 - v3f16 = 94, // 3 x f16 - v4f16 = 95, // 4 x f16 - v8f16 = 96, // 8 x f16 - v16f16 = 97, // 16 x f16 - v32f16 = 98, // 32 x f16 - v1f32 = 99, // 1 x f32 - v2f32 = 100, // 2 x f32 - v3f32 = 101, // 3 x f32 - v4f32 = 102, // 4 x f32 - v5f32 = 103, // 5 x f32 - v8f32 = 104, // 8 x f32 - v16f32 = 105, // 16 x f32 - v32f32 = 106, // 32 x f32 - v64f32 = 107, // 64 x f32 - v128f32 = 108, // 128 x f32 - v256f32 = 109, // 256 x f32 - v512f32 = 110, // 512 x f32 - v1024f32 = 111, // 1024 x f32 - v2048f32 = 112, // 2048 x f32 - v1f64 = 113, // 1 x f64 - v2f64 = 114, // 2 x f64 - v4f64 = 115, // 4 x f64 - v8f64 = 116, // 8 x f64 + FIRST_INTEGER_FIXEDLEN_VECTOR_VALUETYPE = v1i1, + LAST_INTEGER_FIXEDLEN_VECTOR_VALUETYPE = v1i128, + + v2f16 = 63, // 2 x f16 + v3f16 = 64, // 3 x f16 + v4f16 = 65, // 4 x f16 + v8f16 = 66, // 8 x f16 + v16f16 = 67, // 16 x f16 + v32f16 = 68, // 32 x f16 + v1f32 = 69, // 1 x f32 + v2f32 = 70, // 2 x f32 + v3f32 = 71, // 3 x f32 + v4f32 = 72, // 4 x f32 + v5f32 = 73, // 5 x f32 + v8f32 = 74, // 8 x f32 + v16f32 = 75, // 16 x f32 + v32f32 = 76, // 32 x f32 + v64f32 = 77, // 64 x f32 + v128f32 = 78, // 128 x f32 + v256f32 = 79, // 256 x f32 + v512f32 = 80, // 512 x f32 + v1024f32 = 81, // 1024 x f32 + v2048f32 = 82, // 2048 x f32 + v1f64 = 83, // 1 x f64 + v2f64 = 84, // 2 x f64 + v4f64 = 85, // 4 x f64 + v8f64 = 86, // 8 x f64 + + FIRST_FP_FIXEDLEN_VECTOR_VALUETYPE = v2f16, + LAST_FP_FIXEDLEN_VECTOR_VALUETYPE = v8f64, + + FIRST_FIXEDLEN_VECTOR_VALUETYPE = v1i1, + LAST_FIXEDLEN_VECTOR_VALUETYPE = v8f64, + + nxv1i1 = 87, // n x 1 x i1 + nxv2i1 = 88, // n x 2 x i1 + nxv4i1 = 89, // n x 4 x i1 + nxv8i1 = 90, // n x 8 x i1 + nxv16i1 = 91, // n x 16 x i1 + nxv32i1 = 92, // n x 32 x i1 + + nxv1i8 = 93, // n x 1 x i8 + nxv2i8 = 94, // n x 2 x i8 + nxv4i8 = 95, // n x 4 x i8 + nxv8i8 = 96, // n x 8 x i8 + nxv16i8 = 97, // n x 16 x i8 + nxv32i8 = 98, // n x 32 x i8 + + nxv1i16 = 99, // n x 1 x i16 + nxv2i16 = 100, // n x 2 x i16 + nxv4i16 = 101, // n x 4 x i16 + nxv8i16 = 102, // n x 8 x i16 + nxv16i16 = 103, // n x 16 x i16 + nxv32i16 = 104, // n x 32 x i16 + + nxv1i32 = 105, // n x 1 x i32 + nxv2i32 = 106, // n x 2 x i32 + nxv4i32 = 107, // n x 4 x i32 + nxv8i32 = 108, // n x 8 x i32 + nxv16i32 = 109, // n x 16 x i32 + nxv32i32 = 110, // n x 32 x i32 + + nxv1i64 = 111, // n x 1 x i64 + nxv2i64 = 112, // n x 2 x i64 + nxv4i64 = 113, // n x 4 x i64 + nxv8i64 = 114, // n x 8 x i64 + nxv16i64 = 115, // n x 16 x i64 + nxv32i64 = 116, // n x 32 x i64 + + FIRST_INTEGER_SCALABLE_VECTOR_VALUETYPE = nxv1i1, + LAST_INTEGER_SCALABLE_VECTOR_VALUETYPE = nxv32i64, nxv2f16 = 117, // n x 2 x f16 nxv4f16 = 118, // n x 4 x f16 @@ -192,11 +197,11 @@ namespace llvm { nxv4f64 = 127, // n x 4 x f64 nxv8f64 = 128, // n x 8 x f64 - FIRST_FP_VECTOR_VALUETYPE = v2f16, - LAST_FP_VECTOR_VALUETYPE = nxv8f64, + FIRST_FP_SCALABLE_VECTOR_VALUETYPE = nxv2f16, + LAST_FP_SCALABLE_VECTOR_VALUETYPE = nxv8f64, - FIRST_FP_SCALABLE_VALUETYPE = nxv2f16, - LAST_FP_SCALABLE_VALUETYPE = nxv8f64, + FIRST_SCALABLE_VECTOR_VALUETYPE = nxv1i1, + LAST_SCALABLE_VECTOR_VALUETYPE = nxv8f64, FIRST_VECTOR_VALUETYPE = v1i1, LAST_VECTOR_VALUETYPE = nxv8f64, @@ -278,16 +283,20 @@ namespace llvm { bool isFloatingPoint() const { return ((SimpleTy >= MVT::FIRST_FP_VALUETYPE && SimpleTy <= MVT::LAST_FP_VALUETYPE) || - (SimpleTy >= MVT::FIRST_FP_VECTOR_VALUETYPE && - SimpleTy <= MVT::LAST_FP_VECTOR_VALUETYPE)); + (SimpleTy >= MVT::FIRST_FP_FIXEDLEN_VECTOR_VALUETYPE && + SimpleTy <= MVT::LAST_FP_FIXEDLEN_VECTOR_VALUETYPE) || + (SimpleTy >= MVT::FIRST_FP_SCALABLE_VECTOR_VALUETYPE && + SimpleTy <= MVT::LAST_FP_SCALABLE_VECTOR_VALUETYPE)); } /// Return true if this is an integer or a vector integer type. bool isInteger() const { return ((SimpleTy >= MVT::FIRST_INTEGER_VALUETYPE && SimpleTy <= MVT::LAST_INTEGER_VALUETYPE) || - (SimpleTy >= MVT::FIRST_INTEGER_VECTOR_VALUETYPE && - SimpleTy <= MVT::LAST_INTEGER_VECTOR_VALUETYPE)); + (SimpleTy >= MVT::FIRST_INTEGER_FIXEDLEN_VECTOR_VALUETYPE && + SimpleTy <= MVT::LAST_INTEGER_FIXEDLEN_VECTOR_VALUETYPE) || + (SimpleTy >= MVT::FIRST_INTEGER_SCALABLE_VECTOR_VALUETYPE && + SimpleTy <= MVT::LAST_INTEGER_SCALABLE_VECTOR_VALUETYPE)); } /// Return true if this is an integer, not including vectors. @@ -305,10 +314,13 @@ namespace llvm { /// Return true if this is a vector value type where the /// runtime length is machine dependent bool isScalableVector() const { - return ((SimpleTy >= MVT::FIRST_INTEGER_SCALABLE_VALUETYPE && - SimpleTy <= MVT::LAST_INTEGER_SCALABLE_VALUETYPE) || - (SimpleTy >= MVT::FIRST_FP_SCALABLE_VALUETYPE && - SimpleTy <= MVT::LAST_FP_SCALABLE_VALUETYPE)); + return (SimpleTy >= MVT::FIRST_SCALABLE_VECTOR_VALUETYPE && + SimpleTy <= MVT::LAST_SCALABLE_VECTOR_VALUETYPE); + } + + bool isFixedLengthVector() const { + return (SimpleTy >= MVT::FIRST_FIXEDLEN_VECTOR_VALUETYPE && + SimpleTy <= MVT::LAST_FIXEDLEN_VECTOR_VALUETYPE); } /// Return true if this is a 16-bit vector type. @@ -1104,26 +1116,40 @@ namespace llvm { (MVT::SimpleValueType)(MVT::LAST_VECTOR_VALUETYPE + 1)); } - static mvt_range integer_vector_valuetypes() { + static mvt_range fixedlen_vector_valuetypes() { + return mvt_range( + MVT::FIRST_FIXEDLEN_VECTOR_VALUETYPE, + (MVT::SimpleValueType)(MVT::LAST_FIXEDLEN_VECTOR_VALUETYPE + 1)); + } + + static mvt_range scalable_vector_valuetypes() { return mvt_range( - MVT::FIRST_INTEGER_VECTOR_VALUETYPE, - (MVT::SimpleValueType)(MVT::LAST_INTEGER_VECTOR_VALUETYPE + 1)); + MVT::FIRST_SCALABLE_VECTOR_VALUETYPE, + (MVT::SimpleValueType)(MVT::LAST_SCALABLE_VECTOR_VALUETYPE + 1)); } - static mvt_range fp_vector_valuetypes() { + static mvt_range integer_fixedlen_vector_valuetypes() { return mvt_range( - MVT::FIRST_FP_VECTOR_VALUETYPE, - (MVT::SimpleValueType)(MVT::LAST_FP_VECTOR_VALUETYPE + 1)); + MVT::FIRST_INTEGER_FIXEDLEN_VECTOR_VALUETYPE, + (MVT::SimpleValueType)(MVT::LAST_INTEGER_FIXEDLEN_VECTOR_VALUETYPE + 1)); + } + + static mvt_range fp_fixedlen_vector_valuetypes() { + return mvt_range( + MVT::FIRST_FP_FIXEDLEN_VECTOR_VALUETYPE, + (MVT::SimpleValueType)(MVT::LAST_FP_FIXEDLEN_VECTOR_VALUETYPE + 1)); } static mvt_range integer_scalable_vector_valuetypes() { - return mvt_range(MVT::FIRST_INTEGER_SCALABLE_VALUETYPE, - (MVT::SimpleValueType)(MVT::LAST_INTEGER_SCALABLE_VALUETYPE + 1)); + return mvt_range( + MVT::FIRST_INTEGER_SCALABLE_VECTOR_VALUETYPE, + (MVT::SimpleValueType)(MVT::LAST_INTEGER_SCALABLE_VECTOR_VALUETYPE + 1)); } static mvt_range fp_scalable_vector_valuetypes() { - return mvt_range(MVT::FIRST_FP_SCALABLE_VALUETYPE, - (MVT::SimpleValueType)(MVT::LAST_FP_SCALABLE_VALUETYPE + 1)); + return mvt_range( + MVT::FIRST_FP_SCALABLE_VECTOR_VALUETYPE, + (MVT::SimpleValueType)(MVT::LAST_FP_SCALABLE_VECTOR_VALUETYPE + 1)); } /// @} }; diff --git a/llvm/lib/CodeGen/TargetLoweringBase.cpp b/llvm/lib/CodeGen/TargetLoweringBase.cpp index 7c6860e..0eb10a1 100644 --- a/llvm/lib/CodeGen/TargetLoweringBase.cpp +++ b/llvm/lib/CodeGen/TargetLoweringBase.cpp @@ -1266,7 +1266,8 @@ void TargetLoweringBase::computeRegisterProperties( case TypePromoteInteger: // Try to promote the elements of integer vectors. If no legal // promotion was found, fall through to the widen-vector method. - for (unsigned nVT = i + 1; nVT <= MVT::LAST_INTEGER_VECTOR_VALUETYPE; ++nVT) { + for (unsigned nVT = i + 1; + nVT <= MVT::LAST_INTEGER_FIXEDLEN_VECTOR_VALUETYPE; ++nVT) { MVT SVT = (MVT::SimpleValueType) nVT; // Promote vectors of integers to vectors with the same number // of elements, with a wider element type. diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp index 84b4e97..77311c5 100644 --- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp +++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp @@ -307,7 +307,7 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM, // AArch64 lacks both left-rotate and popcount instructions. setOperationAction(ISD::ROTL, MVT::i32, Expand); setOperationAction(ISD::ROTL, MVT::i64, Expand); - for (MVT VT : MVT::vector_valuetypes()) { + for (MVT VT : MVT::fixedlen_vector_valuetypes()) { setOperationAction(ISD::ROTL, VT, Expand); setOperationAction(ISD::ROTR, VT, Expand); } @@ -321,7 +321,7 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM, setOperationAction(ISD::SDIVREM, MVT::i32, Expand); setOperationAction(ISD::SDIVREM, MVT::i64, Expand); - for (MVT VT : MVT::vector_valuetypes()) { + for (MVT VT : MVT::fixedlen_vector_valuetypes()) { setOperationAction(ISD::SDIVREM, VT, Expand); setOperationAction(ISD::UDIVREM, VT, Expand); } @@ -754,7 +754,7 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM, setTruncStoreAction(MVT::v2i32, MVT::v2i16, Expand); // Likewise, narrowing and extending vector loads/stores aren't handled // directly. - for (MVT VT : MVT::vector_valuetypes()) { + for (MVT VT : MVT::fixedlen_vector_valuetypes()) { setOperationAction(ISD::SIGN_EXTEND_INREG, VT, Expand); if (VT == MVT::v16i8 || VT == MVT::v8i16 || VT == MVT::v4i32) { @@ -770,7 +770,7 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM, setOperationAction(ISD::BSWAP, VT, Expand); setOperationAction(ISD::CTTZ, VT, Expand); - for (MVT InnerVT : MVT::vector_valuetypes()) { + for (MVT InnerVT : MVT::fixedlen_vector_valuetypes()) { setTruncStoreAction(VT, InnerVT, Expand); setLoadExtAction(ISD::SEXTLOAD, VT, InnerVT, Expand); setLoadExtAction(ISD::ZEXTLOAD, VT, InnerVT, Expand); diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp index 6b92ad0..c24ea04 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp @@ -134,7 +134,7 @@ AMDGPUTargetLowering::AMDGPUTargetLowering(const TargetMachine &TM, setLoadExtAction(ISD::EXTLOAD, VT, MVT::i32, Expand); } - for (MVT VT : MVT::integer_vector_valuetypes()) { + for (MVT VT : MVT::integer_fixedlen_vector_valuetypes()) { setLoadExtAction(ISD::EXTLOAD, VT, MVT::v2i8, Expand); setLoadExtAction(ISD::SEXTLOAD, VT, MVT::v2i8, Expand); setLoadExtAction(ISD::ZEXTLOAD, VT, MVT::v2i8, Expand); diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp index 44c43ed..9cf1098 100644 --- a/llvm/lib/Target/ARM/ARMISelLowering.cpp +++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp @@ -704,8 +704,8 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM, setOperationAction(ISD::FMAXNUM, MVT::f16, Legal); } - for (MVT VT : MVT::vector_valuetypes()) { - for (MVT InnerVT : MVT::vector_valuetypes()) { + for (MVT VT : MVT::fixedlen_vector_valuetypes()) { + for (MVT InnerVT : MVT::fixedlen_vector_valuetypes()) { setTruncStoreAction(VT, InnerVT, Expand); addAllExtLoads(VT, InnerVT, Expand); } @@ -910,7 +910,7 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM, // It is legal to extload from v4i8 to v4i16 or v4i32. for (MVT Ty : {MVT::v8i8, MVT::v4i8, MVT::v2i8, MVT::v4i16, MVT::v2i16, MVT::v2i32}) { - for (MVT VT : MVT::integer_vector_valuetypes()) { + for (MVT VT : MVT::integer_fixedlen_vector_valuetypes()) { setLoadExtAction(ISD::EXTLOAD, VT, Ty, Legal); setLoadExtAction(ISD::ZEXTLOAD, VT, Ty, Legal); setLoadExtAction(ISD::SEXTLOAD, VT, Ty, Legal); @@ -1054,7 +1054,7 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM, // ARM does not have ROTL. setOperationAction(ISD::ROTL, MVT::i32, Expand); - for (MVT VT : MVT::vector_valuetypes()) { + for (MVT VT : MVT::fixedlen_vector_valuetypes()) { setOperationAction(ISD::ROTL, VT, Expand); setOperationAction(ISD::ROTR, VT, Expand); } diff --git a/llvm/lib/Target/Hexagon/HexagonISelLowering.cpp b/llvm/lib/Target/Hexagon/HexagonISelLowering.cpp index 26a178c..ac70b4d 100644 --- a/llvm/lib/Target/Hexagon/HexagonISelLowering.cpp +++ b/llvm/lib/Target/Hexagon/HexagonISelLowering.cpp @@ -1439,12 +1439,12 @@ HexagonTargetLowering::HexagonTargetLowering(const TargetMachine &TM, ISD::CONCAT_VECTORS, ISD::VECTOR_SHUFFLE }; - for (MVT VT : MVT::vector_valuetypes()) { + for (MVT VT : MVT::fixedlen_vector_valuetypes()) { for (unsigned VectExpOp : VectExpOps) setOperationAction(VectExpOp, VT, Expand); // Expand all extending loads and truncating stores: - for (MVT TargetVT : MVT::vector_valuetypes()) { + for (MVT TargetVT : MVT::fixedlen_vector_valuetypes()) { if (TargetVT == VT) continue; setLoadExtAction(ISD::EXTLOAD, TargetVT, VT, Expand); @@ -1864,7 +1864,7 @@ bool HexagonTargetLowering::isShuffleMaskLegal(ArrayRef Mask, TargetLoweringBase::LegalizeTypeAction HexagonTargetLowering::getPreferredVectorAction(MVT VT) const { - if (VT.getVectorNumElements() == 1) + if (VT.getVectorNumElements() == 1 || VT.isScalableVector()) return TargetLoweringBase::TypeScalarizeVector; // Always widen vectors of i1. diff --git a/llvm/lib/Target/Hexagon/HexagonSubtarget.h b/llvm/lib/Target/Hexagon/HexagonSubtarget.h index 007423e..31157a0 100644 --- a/llvm/lib/Target/Hexagon/HexagonSubtarget.h +++ b/llvm/lib/Target/Hexagon/HexagonSubtarget.h @@ -228,7 +228,7 @@ public: } bool isHVXVectorType(MVT VecTy, bool IncludeBool = false) const { - if (!VecTy.isVector() || !useHVXOps()) + if (!VecTy.isVector() || !useHVXOps() || VecTy.isScalableVector()) return false; MVT ElemTy = VecTy.getVectorElementType(); if (!IncludeBool && ElemTy == MVT::i1) diff --git a/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp b/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp index 38062e8..ddbc554 100644 --- a/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp +++ b/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp @@ -45,6 +45,8 @@ bool HexagonTTIImpl::useHVX() const { bool HexagonTTIImpl::isTypeForHVX(Type *VecTy) const { assert(VecTy->isVectorTy()); + if (cast(VecTy)->isScalable()) + return false; // Avoid types like <2 x i32*>. if (!cast(VecTy)->getElementType()->isIntegerTy()) return false; diff --git a/llvm/lib/Target/Mips/MipsISelLowering.cpp b/llvm/lib/Target/Mips/MipsISelLowering.cpp index c352007..3037919 100644 --- a/llvm/lib/Target/Mips/MipsISelLowering.cpp +++ b/llvm/lib/Target/Mips/MipsISelLowering.cpp @@ -330,7 +330,7 @@ MipsTargetLowering::MipsTargetLowering(const MipsTargetMachine &TM, } // Set LoadExtAction for f16 vectors to Expand - for (MVT VT : MVT::fp_vector_valuetypes()) { + for (MVT VT : MVT::fp_fixedlen_vector_valuetypes()) { MVT F16VT = MVT::getVectorVT(MVT::f16, VT.getVectorNumElements()); if (F16VT.isValid()) setLoadExtAction(ISD::EXTLOAD, VT, F16VT, Expand); diff --git a/llvm/lib/Target/Mips/MipsSEISelLowering.cpp b/llvm/lib/Target/Mips/MipsSEISelLowering.cpp index a79c3a0..ca46385 100644 --- a/llvm/lib/Target/Mips/MipsSEISelLowering.cpp +++ b/llvm/lib/Target/Mips/MipsSEISelLowering.cpp @@ -71,8 +71,8 @@ MipsSETargetLowering::MipsSETargetLowering(const MipsTargetMachine &TM, if (Subtarget.hasDSP() || Subtarget.hasMSA()) { // Expand all truncating stores and extending loads. - for (MVT VT0 : MVT::vector_valuetypes()) { - for (MVT VT1 : MVT::vector_valuetypes()) { + for (MVT VT0 : MVT::fixedlen_vector_valuetypes()) { + for (MVT VT1 : MVT::fixedlen_vector_valuetypes()) { setTruncStoreAction(VT0, VT1, Expand); setLoadExtAction(ISD::SEXTLOAD, VT0, VT1, Expand); setLoadExtAction(ISD::ZEXTLOAD, VT0, VT1, Expand); diff --git a/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp b/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp index c76e060..9b710f2 100644 --- a/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp +++ b/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp @@ -480,7 +480,7 @@ NVPTXTargetLowering::NVPTXTargetLowering(const NVPTXTargetMachine &TM, setOperationAction(ISD::TRAP, MVT::Other, Legal); // Register custom handling for vector loads/stores - for (MVT VT : MVT::vector_valuetypes()) { + for (MVT VT : MVT::fixedlen_vector_valuetypes()) { if (IsPTXVectorType(VT)) { setOperationAction(ISD::LOAD, VT, Custom); setOperationAction(ISD::STORE, VT, Custom); diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp index 9655c21..1ddc63d 100644 --- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp +++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp @@ -551,7 +551,7 @@ PPCTargetLowering::PPCTargetLowering(const PPCTargetMachine &TM, if (Subtarget.hasAltivec()) { // First set operation action for all vector types to expand. Then we // will selectively turn on ones that can be effectively codegen'd. - for (MVT VT : MVT::vector_valuetypes()) { + for (MVT VT : MVT::fixedlen_vector_valuetypes()) { // add/sub are legal for all supported vector VT's. setOperationAction(ISD::ADD, VT, Legal); setOperationAction(ISD::SUB, VT, Legal); @@ -652,7 +652,7 @@ PPCTargetLowering::PPCTargetLowering(const PPCTargetMachine &TM, setOperationAction(ISD::ROTL, VT, Expand); setOperationAction(ISD::ROTR, VT, Expand); - for (MVT InnerVT : MVT::vector_valuetypes()) { + for (MVT InnerVT : MVT::fixedlen_vector_valuetypes()) { setTruncStoreAction(VT, InnerVT, Expand); setLoadExtAction(ISD::SEXTLOAD, VT, InnerVT, Expand); setLoadExtAction(ISD::ZEXTLOAD, VT, InnerVT, Expand); diff --git a/llvm/lib/Target/Sparc/SparcISelLowering.cpp b/llvm/lib/Target/Sparc/SparcISelLowering.cpp index 660c529..09dd839 100644 --- a/llvm/lib/Target/Sparc/SparcISelLowering.cpp +++ b/llvm/lib/Target/Sparc/SparcISelLowering.cpp @@ -1438,7 +1438,7 @@ SparcTargetLowering::SparcTargetLowering(const TargetMachine &TM, setOperationAction(Op, MVT::v2i32, Expand); } // Truncating/extending stores/loads are also not supported. - for (MVT VT : MVT::integer_vector_valuetypes()) { + for (MVT VT : MVT::integer_fixedlen_vector_valuetypes()) { setLoadExtAction(ISD::SEXTLOAD, VT, MVT::v2i32, Expand); setLoadExtAction(ISD::ZEXTLOAD, VT, MVT::v2i32, Expand); setLoadExtAction(ISD::EXTLOAD, VT, MVT::v2i32, Expand); diff --git a/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp b/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp index f79f40c..febf75c 100644 --- a/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp +++ b/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp @@ -300,14 +300,14 @@ SystemZTargetLowering::SystemZTargetLowering(const TargetMachine &TM, // Handle prefetches with PFD or PFDRL. setOperationAction(ISD::PREFETCH, MVT::Other, Custom); - for (MVT VT : MVT::vector_valuetypes()) { + for (MVT VT : MVT::fixedlen_vector_valuetypes()) { // Assume by default that all vector operations need to be expanded. for (unsigned Opcode = 0; Opcode < ISD::BUILTIN_OP_END; ++Opcode) if (getOperationAction(Opcode, VT) == Legal) setOperationAction(Opcode, VT, Expand); // Likewise all truncating stores and extending loads. - for (MVT InnerVT : MVT::vector_valuetypes()) { + for (MVT InnerVT : MVT::fixedlen_vector_valuetypes()) { setTruncStoreAction(VT, InnerVT, Expand); setLoadExtAction(ISD::SEXTLOAD, VT, InnerVT, Expand); setLoadExtAction(ISD::ZEXTLOAD, VT, InnerVT, Expand); @@ -333,7 +333,7 @@ SystemZTargetLowering::SystemZTargetLowering(const TargetMachine &TM, } // Handle integer vector types. - for (MVT VT : MVT::integer_vector_valuetypes()) { + for (MVT VT : MVT::integer_fixedlen_vector_valuetypes()) { if (isTypeLegal(VT)) { // These operations have direct equivalents. setOperationAction(ISD::EXTRACT_VECTOR_ELT, VT, Legal); diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp index 4ac9995..78dfa88 100644 --- a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp +++ b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp @@ -205,7 +205,7 @@ WebAssemblyTargetLowering::WebAssemblyTargetLowering( for (auto T : {MVT::i8, MVT::i16, MVT::i32}) setOperationAction(ISD::SIGN_EXTEND_INREG, T, Action); } - for (auto T : MVT::integer_vector_valuetypes()) + for (auto T : MVT::integer_fixedlen_vector_valuetypes()) setOperationAction(ISD::SIGN_EXTEND_INREG, T, Expand); // Dynamic stack allocation: use the default expansion. @@ -237,7 +237,7 @@ WebAssemblyTargetLowering::WebAssemblyTargetLowering( if (Subtarget->hasSIMD128()) { for (auto T : {MVT::v16i8, MVT::v8i16, MVT::v4i32, MVT::v2i64, MVT::v4f32, MVT::v2f64}) { - for (auto MemT : MVT::vector_valuetypes()) { + for (auto MemT : MVT::fixedlen_vector_valuetypes()) { if (MVT(T) != MemT) { setTruncStoreAction(T, MemT, Expand); for (auto Ext : {ISD::EXTLOAD, ISD::ZEXTLOAD, ISD::SEXTLOAD}) diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp index 1846458..58b1d47 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.cpp +++ b/llvm/lib/Target/X86/X86ISelLowering.cpp @@ -749,7 +749,7 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM, // First set operation action for all vector types to either promote // (for widening) or expand (for scalarization). Then we will selectively // turn on ones that can be effectively codegen'd. - for (MVT VT : MVT::vector_valuetypes()) { + for (MVT VT : MVT::fixedlen_vector_valuetypes()) { setOperationAction(ISD::SDIV, VT, Expand); setOperationAction(ISD::UDIV, VT, Expand); setOperationAction(ISD::SREM, VT, Expand); @@ -787,7 +787,7 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM, setOperationAction(ISD::ZERO_EXTEND, VT, Expand); setOperationAction(ISD::ANY_EXTEND, VT, Expand); setOperationAction(ISD::SELECT_CC, VT, Expand); - for (MVT InnerVT : MVT::vector_valuetypes()) { + for (MVT InnerVT : MVT::fixedlen_vector_valuetypes()) { setTruncStoreAction(InnerVT, VT, Expand); setLoadExtAction(ISD::SEXTLOAD, InnerVT, VT, Expand); @@ -948,7 +948,7 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM, // scalars) and extend in-register to a legal 128-bit vector type. For sext // loads these must work with a single scalar load. if (!ExperimentalVectorWideningLegalization) { - for (MVT VT : MVT::integer_vector_valuetypes()) { + for (MVT VT : MVT::integer_fixedlen_vector_valuetypes()) { setLoadExtAction(ISD::EXTLOAD, VT, MVT::v2i8, Custom); setLoadExtAction(ISD::EXTLOAD, VT, MVT::v2i16, Custom); setLoadExtAction(ISD::EXTLOAD, VT, MVT::v2i32, Custom); @@ -1112,7 +1112,7 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM, if (!ExperimentalVectorWideningLegalization) { // Avoid narrow result types when widening. The legal types are listed // in the next loop. - for (MVT VT : MVT::integer_vector_valuetypes()) { + for (MVT VT : MVT::integer_fixedlen_vector_valuetypes()) { setLoadExtAction(ISD::SEXTLOAD, VT, MVT::v2i8, Custom); setLoadExtAction(ISD::SEXTLOAD, VT, MVT::v2i16, Custom); setLoadExtAction(ISD::SEXTLOAD, VT, MVT::v2i32, Custom); diff --git a/llvm/utils/TableGen/CodeGenDAGPatterns.cpp b/llvm/utils/TableGen/CodeGenDAGPatterns.cpp index 07fffae..ad1f228 100644 --- a/llvm/utils/TableGen/CodeGenDAGPatterns.cpp +++ b/llvm/utils/TableGen/CodeGenDAGPatterns.cpp @@ -769,7 +769,10 @@ void TypeInfer::expandOverloads(TypeSetByHwMode::SetType &Out, for (MVT T : MVT::integer_valuetypes()) if (Legal.count(T)) Out.insert(T); - for (MVT T : MVT::integer_vector_valuetypes()) + for (MVT T : MVT::integer_fixedlen_vector_valuetypes()) + if (Legal.count(T)) + Out.insert(T); + for (MVT T : MVT::integer_scalable_vector_valuetypes()) if (Legal.count(T)) Out.insert(T); return; @@ -777,7 +780,10 @@ void TypeInfer::expandOverloads(TypeSetByHwMode::SetType &Out, for (MVT T : MVT::fp_valuetypes()) if (Legal.count(T)) Out.insert(T); - for (MVT T : MVT::fp_vector_valuetypes()) + for (MVT T : MVT::fp_fixedlen_vector_valuetypes()) + if (Legal.count(T)) + Out.insert(T); + for (MVT T : MVT::fp_scalable_vector_valuetypes()) if (Legal.count(T)) Out.insert(T); return; -- 2.7.4