llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-llvm-ir Author: David Green (davemgreen) <details> <summary>Changes</summary> Similar to #<!-- -->169156 again, this adds intrinsics for strict-fp compare nodes to make sure they end up as the original instruction. --- Patch is 370.71 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/169798.diff 5 Files Affected: - (modified) clang/include/clang/Basic/arm_mve_defs.td (+18-6) - (modified) clang/test/CodeGen/arm-mve-intrinsics/compare.c (+3030-1430) - (modified) llvm/include/llvm/IR/IntrinsicsARM.td (+9) - (modified) llvm/lib/Target/ARM/ARMInstrMVE.td (+34-15) - (added) llvm/test/CodeGen/Thumb2/mve-intrinsics/strict-compare.ll (+820) ``````````diff diff --git a/clang/include/clang/Basic/arm_mve_defs.td b/clang/include/clang/Basic/arm_mve_defs.td index 3714262898476..be79002bcbe64 100644 --- a/clang/include/clang/Basic/arm_mve_defs.td +++ b/clang/include/clang/Basic/arm_mve_defs.td @@ -114,12 +114,12 @@ def icmp_sgt: IRBuilder<"CreateICmpSGT">; def icmp_sge: IRBuilder<"CreateICmpSGE">; def icmp_slt: IRBuilder<"CreateICmpSLT">; def icmp_sle: IRBuilder<"CreateICmpSLE">; -def fcmp_eq: IRBuilder<"CreateFCmpOEQ">; -def fcmp_ne: IRBuilder<"CreateFCmpUNE">; // not O: it must return true on NaNs -def fcmp_gt: IRBuilder<"CreateFCmpOGT">; -def fcmp_ge: IRBuilder<"CreateFCmpOGE">; -def fcmp_ult: IRBuilder<"CreateFCmpULT">; -def fcmp_ule: IRBuilder<"CreateFCmpULE">; +def fcmp_eq_node: IRBuilder<"CreateFCmpOEQ">; +def fcmp_ne_node: IRBuilder<"CreateFCmpUNE">; // not O: it must return true on NaNs +def fcmp_gt_node: IRBuilder<"CreateFCmpOGT">; +def fcmp_ge_node: IRBuilder<"CreateFCmpOGE">; +def fcmp_ult_node: IRBuilder<"CreateFCmpULT">; +def fcmp_ule_node: IRBuilder<"CreateFCmpULE">; def splat: CGHelperFn<"ARMMVEVectorSplat">; def select: IRBuilder<"CreateSelect">; def fneg: IRBuilder<"CreateFNeg">; @@ -589,6 +589,18 @@ def fsub: strictFPAlt<fsub_node, IRInt<"vsub", [Vector]>>; def fmul: strictFPAlt<fmul_node, IRInt<"vmul", [Vector]>>; +def fcmp_eq : strictFPAlt<fcmp_eq_node, + IRInt<"cmp_eq", [Predicate, Vector]>>; +def fcmp_ne : strictFPAlt<fcmp_ne_node, + IRInt<"cmp_ne", [Predicate, Vector]>>; +def fcmp_gt : strictFPAlt<fcmp_gt_node, + IRInt<"cmp_gt", [Predicate, Vector]>>; +def fcmp_ge : strictFPAlt<fcmp_ge_node, + IRInt<"cmp_ge", [Predicate, Vector]>>; +def fcmp_ult : strictFPAlt<fcmp_ult_node, + IRInt<"cmp_lt", [Predicate, Vector]>>; +def fcmp_ule : strictFPAlt<fcmp_ule_node, + IRInt<"cmp_le", [Predicate, Vector]>>; // ----------------------------------------------------------------------------- // Convenience lists of parameter types. 'T' is just a container record, so you diff --git a/clang/test/CodeGen/arm-mve-intrinsics/compare.c b/clang/test/CodeGen/arm-mve-intrinsics/compare.c index 8886cf5c10058..dd756a401e5cd 100644 --- a/clang/test/CodeGen/arm-mve-intrinsics/compare.c +++ b/clang/test/CodeGen/arm-mve-intrinsics/compare.c @@ -1,17 +1,26 @@ // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py -// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -O0 -disable-O0-optnone -emit-llvm -o - %s | opt -S -passes=mem2reg,sroa | FileCheck %s -// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -O0 -disable-O0-optnone -DPOLYMORPHIC -emit-llvm -o - %s | opt -S -passes=mem2reg,sroa | FileCheck %s +// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -O0 -disable-O0-optnone -emit-llvm -o - %s | opt -S -passes=mem2reg | FileCheck %s --check-prefixes=CHECK,CHECK-NOSTRICT +// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -O0 -disable-O0-optnone -DPOLYMORPHIC -emit-llvm -o - %s | opt -S -passes='mem2reg,sroa,early-cse<>' | FileCheck %s --check-prefixes=CHECK,CHECK-NOSTRICT +// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -O0 -disable-O0-optnone -frounding-math -fexperimental-strict-floating-point -emit-llvm -o - %s | opt -S -passes=mem2reg | FileCheck %s --check-prefixes=CHECK,CHECK-STRICT +// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -O0 -disable-O0-optnone -frounding-math -fexperimental-strict-floating-point -DPOLYMORPHIC -emit-llvm -o - %s | opt -S -passes='mem2reg,sroa,early-cse<>' | FileCheck %s --check-prefixes=CHECK,CHECK-STRICT // REQUIRES: aarch64-registered-target || arm-registered-target #include <arm_mve.h> -// CHECK-LABEL: @test_vcmpeqq_f16( -// CHECK-NEXT: entry: -// CHECK-NEXT: [[TMP0:%.*]] = fcmp oeq <8 x half> [[A:%.*]], [[B:%.*]] -// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]) -// CHECK-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 -// CHECK-NEXT: ret i16 [[TMP2]] +// CHECK-NOSTRICT-LABEL: @test_vcmpeqq_f16( +// CHECK-NOSTRICT-NEXT: entry: +// CHECK-NOSTRICT-NEXT: [[TMP0:%.*]] = fcmp oeq <8 x half> [[A:%.*]], [[B:%.*]] +// CHECK-NOSTRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]) +// CHECK-NOSTRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-NOSTRICT-NEXT: ret i16 [[TMP2]] +// +// CHECK-STRICT-LABEL: @test_vcmpeqq_f16( +// CHECK-STRICT-NEXT: entry: +// CHECK-STRICT-NEXT: [[TMP0:%.*]] = call <8 x i1> @llvm.arm.mve.cmp.eq.v8i1.v8f16(<8 x half> [[A:%.*]], <8 x half> [[B:%.*]]) #[[ATTR2:[0-9]+]] +// CHECK-STRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-STRICT-NEXT: ret i16 [[TMP2]] // mve_pred16_t test_vcmpeqq_f16(float16x8_t a, float16x8_t b) { @@ -22,12 +31,19 @@ mve_pred16_t test_vcmpeqq_f16(float16x8_t a, float16x8_t b) #endif /* POLYMORPHIC */ } -// CHECK-LABEL: @test_vcmpeqq_f32( -// CHECK-NEXT: entry: -// CHECK-NEXT: [[TMP0:%.*]] = fcmp oeq <4 x float> [[A:%.*]], [[B:%.*]] -// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1> [[TMP0]]) -// CHECK-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 -// CHECK-NEXT: ret i16 [[TMP2]] +// CHECK-NOSTRICT-LABEL: @test_vcmpeqq_f32( +// CHECK-NOSTRICT-NEXT: entry: +// CHECK-NOSTRICT-NEXT: [[TMP0:%.*]] = fcmp oeq <4 x float> [[A:%.*]], [[B:%.*]] +// CHECK-NOSTRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1> [[TMP0]]) +// CHECK-NOSTRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-NOSTRICT-NEXT: ret i16 [[TMP2]] +// +// CHECK-STRICT-LABEL: @test_vcmpeqq_f32( +// CHECK-STRICT-NEXT: entry: +// CHECK-STRICT-NEXT: [[TMP0:%.*]] = call <4 x i1> @llvm.arm.mve.cmp.eq.v4i1.v4f32(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1> [[TMP0]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-STRICT-NEXT: ret i16 [[TMP2]] // mve_pred16_t test_vcmpeqq_f32(float32x4_t a, float32x4_t b) { @@ -38,12 +54,19 @@ mve_pred16_t test_vcmpeqq_f32(float32x4_t a, float32x4_t b) #endif /* POLYMORPHIC */ } -// CHECK-LABEL: @test_vcmpeqq_s8( -// CHECK-NEXT: entry: -// CHECK-NEXT: [[TMP0:%.*]] = icmp eq <16 x i8> [[A:%.*]], [[B:%.*]] -// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v16i1(<16 x i1> [[TMP0]]) -// CHECK-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 -// CHECK-NEXT: ret i16 [[TMP2]] +// CHECK-NOSTRICT-LABEL: @test_vcmpeqq_s8( +// CHECK-NOSTRICT-NEXT: entry: +// CHECK-NOSTRICT-NEXT: [[TMP0:%.*]] = icmp eq <16 x i8> [[A:%.*]], [[B:%.*]] +// CHECK-NOSTRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v16i1(<16 x i1> [[TMP0]]) +// CHECK-NOSTRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-NOSTRICT-NEXT: ret i16 [[TMP2]] +// +// CHECK-STRICT-LABEL: @test_vcmpeqq_s8( +// CHECK-STRICT-NEXT: entry: +// CHECK-STRICT-NEXT: [[TMP0:%.*]] = icmp eq <16 x i8> [[A:%.*]], [[B:%.*]] +// CHECK-STRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v16i1(<16 x i1> [[TMP0]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-STRICT-NEXT: ret i16 [[TMP2]] // mve_pred16_t test_vcmpeqq_s8(int8x16_t a, int8x16_t b) { @@ -54,12 +77,19 @@ mve_pred16_t test_vcmpeqq_s8(int8x16_t a, int8x16_t b) #endif /* POLYMORPHIC */ } -// CHECK-LABEL: @test_vcmpeqq_s16( -// CHECK-NEXT: entry: -// CHECK-NEXT: [[TMP0:%.*]] = icmp eq <8 x i16> [[A:%.*]], [[B:%.*]] -// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]) -// CHECK-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 -// CHECK-NEXT: ret i16 [[TMP2]] +// CHECK-NOSTRICT-LABEL: @test_vcmpeqq_s16( +// CHECK-NOSTRICT-NEXT: entry: +// CHECK-NOSTRICT-NEXT: [[TMP0:%.*]] = icmp eq <8 x i16> [[A:%.*]], [[B:%.*]] +// CHECK-NOSTRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]) +// CHECK-NOSTRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-NOSTRICT-NEXT: ret i16 [[TMP2]] +// +// CHECK-STRICT-LABEL: @test_vcmpeqq_s16( +// CHECK-STRICT-NEXT: entry: +// CHECK-STRICT-NEXT: [[TMP0:%.*]] = icmp eq <8 x i16> [[A:%.*]], [[B:%.*]] +// CHECK-STRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-STRICT-NEXT: ret i16 [[TMP2]] // mve_pred16_t test_vcmpeqq_s16(int16x8_t a, int16x8_t b) { @@ -70,12 +100,19 @@ mve_pred16_t test_vcmpeqq_s16(int16x8_t a, int16x8_t b) #endif /* POLYMORPHIC */ } -// CHECK-LABEL: @test_vcmpeqq_s32( -// CHECK-NEXT: entry: -// CHECK-NEXT: [[TMP0:%.*]] = icmp eq <4 x i32> [[A:%.*]], [[B:%.*]] -// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1> [[TMP0]]) -// CHECK-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 -// CHECK-NEXT: ret i16 [[TMP2]] +// CHECK-NOSTRICT-LABEL: @test_vcmpeqq_s32( +// CHECK-NOSTRICT-NEXT: entry: +// CHECK-NOSTRICT-NEXT: [[TMP0:%.*]] = icmp eq <4 x i32> [[A:%.*]], [[B:%.*]] +// CHECK-NOSTRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1> [[TMP0]]) +// CHECK-NOSTRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-NOSTRICT-NEXT: ret i16 [[TMP2]] +// +// CHECK-STRICT-LABEL: @test_vcmpeqq_s32( +// CHECK-STRICT-NEXT: entry: +// CHECK-STRICT-NEXT: [[TMP0:%.*]] = icmp eq <4 x i32> [[A:%.*]], [[B:%.*]] +// CHECK-STRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1> [[TMP0]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-STRICT-NEXT: ret i16 [[TMP2]] // mve_pred16_t test_vcmpeqq_s32(int32x4_t a, int32x4_t b) { @@ -86,12 +123,19 @@ mve_pred16_t test_vcmpeqq_s32(int32x4_t a, int32x4_t b) #endif /* POLYMORPHIC */ } -// CHECK-LABEL: @test_vcmpeqq_u8( -// CHECK-NEXT: entry: -// CHECK-NEXT: [[TMP0:%.*]] = icmp eq <16 x i8> [[A:%.*]], [[B:%.*]] -// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v16i1(<16 x i1> [[TMP0]]) -// CHECK-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 -// CHECK-NEXT: ret i16 [[TMP2]] +// CHECK-NOSTRICT-LABEL: @test_vcmpeqq_u8( +// CHECK-NOSTRICT-NEXT: entry: +// CHECK-NOSTRICT-NEXT: [[TMP0:%.*]] = icmp eq <16 x i8> [[A:%.*]], [[B:%.*]] +// CHECK-NOSTRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v16i1(<16 x i1> [[TMP0]]) +// CHECK-NOSTRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-NOSTRICT-NEXT: ret i16 [[TMP2]] +// +// CHECK-STRICT-LABEL: @test_vcmpeqq_u8( +// CHECK-STRICT-NEXT: entry: +// CHECK-STRICT-NEXT: [[TMP0:%.*]] = icmp eq <16 x i8> [[A:%.*]], [[B:%.*]] +// CHECK-STRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v16i1(<16 x i1> [[TMP0]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-STRICT-NEXT: ret i16 [[TMP2]] // mve_pred16_t test_vcmpeqq_u8(uint8x16_t a, uint8x16_t b) { @@ -102,12 +146,19 @@ mve_pred16_t test_vcmpeqq_u8(uint8x16_t a, uint8x16_t b) #endif /* POLYMORPHIC */ } -// CHECK-LABEL: @test_vcmpeqq_u16( -// CHECK-NEXT: entry: -// CHECK-NEXT: [[TMP0:%.*]] = icmp eq <8 x i16> [[A:%.*]], [[B:%.*]] -// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]) -// CHECK-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 -// CHECK-NEXT: ret i16 [[TMP2]] +// CHECK-NOSTRICT-LABEL: @test_vcmpeqq_u16( +// CHECK-NOSTRICT-NEXT: entry: +// CHECK-NOSTRICT-NEXT: [[TMP0:%.*]] = icmp eq <8 x i16> [[A:%.*]], [[B:%.*]] +// CHECK-NOSTRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]) +// CHECK-NOSTRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-NOSTRICT-NEXT: ret i16 [[TMP2]] +// +// CHECK-STRICT-LABEL: @test_vcmpeqq_u16( +// CHECK-STRICT-NEXT: entry: +// CHECK-STRICT-NEXT: [[TMP0:%.*]] = icmp eq <8 x i16> [[A:%.*]], [[B:%.*]] +// CHECK-STRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-STRICT-NEXT: ret i16 [[TMP2]] // mve_pred16_t test_vcmpeqq_u16(uint16x8_t a, uint16x8_t b) { @@ -118,12 +169,19 @@ mve_pred16_t test_vcmpeqq_u16(uint16x8_t a, uint16x8_t b) #endif /* POLYMORPHIC */ } -// CHECK-LABEL: @test_vcmpeqq_u32( -// CHECK-NEXT: entry: -// CHECK-NEXT: [[TMP0:%.*]] = icmp eq <4 x i32> [[A:%.*]], [[B:%.*]] -// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1> [[TMP0]]) -// CHECK-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 -// CHECK-NEXT: ret i16 [[TMP2]] +// CHECK-NOSTRICT-LABEL: @test_vcmpeqq_u32( +// CHECK-NOSTRICT-NEXT: entry: +// CHECK-NOSTRICT-NEXT: [[TMP0:%.*]] = icmp eq <4 x i32> [[A:%.*]], [[B:%.*]] +// CHECK-NOSTRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1> [[TMP0]]) +// CHECK-NOSTRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-NOSTRICT-NEXT: ret i16 [[TMP2]] +// +// CHECK-STRICT-LABEL: @test_vcmpeqq_u32( +// CHECK-STRICT-NEXT: entry: +// CHECK-STRICT-NEXT: [[TMP0:%.*]] = icmp eq <4 x i32> [[A:%.*]], [[B:%.*]] +// CHECK-STRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1> [[TMP0]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-STRICT-NEXT: ret i16 [[TMP2]] // mve_pred16_t test_vcmpeqq_u32(uint32x4_t a, uint32x4_t b) { @@ -134,14 +192,23 @@ mve_pred16_t test_vcmpeqq_u32(uint32x4_t a, uint32x4_t b) #endif /* POLYMORPHIC */ } -// CHECK-LABEL: @test_vcmpeqq_n_f16( -// CHECK-NEXT: entry: -// CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <8 x half> poison, half [[B:%.*]], i64 0 -// CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <8 x half> [[DOTSPLATINSERT]], <8 x half> poison, <8 x i32> zeroinitializer -// CHECK-NEXT: [[TMP0:%.*]] = fcmp oeq <8 x half> [[A:%.*]], [[DOTSPLAT]] -// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]) -// CHECK-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 -// CHECK-NEXT: ret i16 [[TMP2]] +// CHECK-NOSTRICT-LABEL: @test_vcmpeqq_n_f16( +// CHECK-NOSTRICT-NEXT: entry: +// CHECK-NOSTRICT-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <8 x half> poison, half [[B:%.*]], i64 0 +// CHECK-NOSTRICT-NEXT: [[DOTSPLAT:%.*]] = shufflevector <8 x half> [[DOTSPLATINSERT]], <8 x half> poison, <8 x i32> zeroinitializer +// CHECK-NOSTRICT-NEXT: [[TMP0:%.*]] = fcmp oeq <8 x half> [[A:%.*]], [[DOTSPLAT]] +// CHECK-NOSTRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]) +// CHECK-NOSTRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-NOSTRICT-NEXT: ret i16 [[TMP2]] +// +// CHECK-STRICT-LABEL: @test_vcmpeqq_n_f16( +// CHECK-STRICT-NEXT: entry: +// CHECK-STRICT-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <8 x half> poison, half [[B:%.*]], i64 0 +// CHECK-STRICT-NEXT: [[DOTSPLAT:%.*]] = shufflevector <8 x half> [[DOTSPLATINSERT]], <8 x half> poison, <8 x i32> zeroinitializer +// CHECK-STRICT-NEXT: [[TMP0:%.*]] = call <8 x i1> @llvm.arm.mve.cmp.eq.v8i1.v8f16(<8 x half> [[A:%.*]], <8 x half> [[DOTSPLAT]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-STRICT-NEXT: ret i16 [[TMP2]] // mve_pred16_t test_vcmpeqq_n_f16(float16x8_t a, float16_t b) { @@ -152,14 +219,23 @@ mve_pred16_t test_vcmpeqq_n_f16(float16x8_t a, float16_t b) #endif /* POLYMORPHIC */ } -// CHECK-LABEL: @test_vcmpeqq_n_f32( -// CHECK-NEXT: entry: -// CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x float> poison, float [[B:%.*]], i64 0 -// CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT]], <4 x float> poison, <4 x i32> zeroinitializer -// CHECK-NEXT: [[TMP0:%.*]] = fcmp oeq <4 x float> [[A:%.*]], [[DOTSPLAT]] -// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1> [[TMP0]]) -// CHECK-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 -// CHECK-NEXT: ret i16 [[TMP2]] +// CHECK-NOSTRICT-LABEL: @test_vcmpeqq_n_f32( +// CHECK-NOSTRICT-NEXT: entry: +// CHECK-NOSTRICT-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x float> poison, float [[B:%.*]], i64 0 +// CHECK-NOSTRICT-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT]], <4 x float> poison, <4 x i32> zeroinitializer +// CHECK-NOSTRICT-NEXT: [[TMP0:%.*]] = fcmp oeq <4 x float> [[A:%.*]], [[DOTSPLAT]] +// CHECK-NOSTRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1> [[TMP0]]) +// CHECK-NOSTRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-NOSTRICT-NEXT: ret i16 [[TMP2]] +// +// CHECK-STRICT-LABEL: @test_vcmpeqq_n_f32( +// CHECK-STRICT-NEXT: entry: +// CHECK-STRICT-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x float> poison, float [[B:%.*]], i64 0 +// CHECK-STRICT-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT]], <4 x float> poison, <4 x i32> zeroinitializer +// CHECK-STRICT-NEXT: [[TMP0:%.*]] = call <4 x i1> @llvm.arm.mve.cmp.eq.v4i1.v4f32(<4 x float> [[A:%.*]], <4 x float> [[DOTSPLAT]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v4i1(<4 x i1> [[TMP0]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-STRICT-NEXT: ret i16 [[TMP2]] // mve_pred16_t test_vcmpeqq_n_f32(float32x4_t a, float32_t b) { @@ -170,14 +246,23 @@ mve_pred16_t test_vcmpeqq_n_f32(float32x4_t a, float32_t b) #endif /* POLYMORPHIC */ } -// CHECK-LABEL: @test_vcmpeqq_n_s8( -// CHECK-NEXT: entry: -// CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <16 x i8> poison, i8 [[B:%.*]], i64 0 -// CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <16 x i8> [[DOTSPLATINSERT]], <16 x i8> poison, <16 x i32> zeroinitializer -// CHECK-NEXT: [[TMP0:%.*]] = icmp eq <16 x i8> [[A:%.*]], [[DOTSPLAT]] -// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v16i1(<16 x i1> [[TMP0]]) -// CHECK-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 -// CHECK-NEXT: ret i16 [[TMP2]] +// CHECK-NOSTRICT-LABEL: @test_vcmpeqq_n_s8( +// CHECK-NOSTRICT-NEXT: entry: +// CHECK-NOSTRICT-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <16 x i8> poison, i8 [[B:%.*]], i64 0 +// CHECK-NOSTRICT-NEXT: [[DOTSPLAT:%.*]] = shufflevector <16 x i8> [[DOTSPLATINSERT]], <16 x i8> poison, <16 x i32> zeroinitializer +// CHECK-NOSTRICT-NEXT: [[TMP0:%.*]] = icmp eq <16 x i8> [[A:%.*]], [[DOTSPLAT]] +// CHECK-NOSTRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v16i1(<16 x i1> [[TMP0]]) +// CHECK-NOSTRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-NOSTRICT-NEXT: ret i16 [[TMP2]] +// +// CHECK-STRICT-LABEL: @test_vcmpeqq_n_s8( +// CHECK-STRICT-NEXT: entry: +// CHECK-STRICT-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <16 x i8> poison, i8 [[B:%.*]], i64 0 +// CHECK-STRICT-NEXT: [[DOTSPLAT:%.*]] = shufflevector <16 x i8> [[DOTSPLATINSERT]], <16 x i8> poison, <16 x i32> zeroinitializer +// CHECK-STRICT-NEXT: [[TMP0:%.*]] = icmp eq <16 x i8> [[A:%.*]], [[DOTSPLAT]] +// CHECK-STRICT-NEXT: [[TMP1:%.*]] = call i32 @llvm.arm.mve.pred.v2i.v16i1(<16 x i1> [[TMP0]]) #[[ATTR2]] +// CHECK-STRICT-NEXT: [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16 +// CHECK-STRICT-NEXT: ret i16 [[TMP2]] // mve_pred16_t test_vcmpeqq_n_s8(int8x16_t a, int8_t b) { @@ -188,14 +273,23 @@ mve_pred16_t test_vcmpeqq_n_s8(int8x16_t a, int8_t b) #endif /* POLYMORPHIC */ } -// CHECK-LABEL: @test_vcmpeqq_n_s16( -// CHECK-NEXT: entry: -// CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <8 x i16> poison, i16 [[B:%.*]], i64 0 -// CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <8 x i16> [[DOTSPLATINSERT]], <8 x i16> poison, <8 x ... [truncated] `````````` </details> https://github.com/llvm/llvm-project/pull/169798 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
