[llvm] db653ff - [LoopVectorize] auto-generate complete test checks; NFC
Sanjay Patel via llvm-commits
llvm-commits at lists.llvm.org
Fri May 29 10:14:16 PDT 2020
Author: Sanjay Patel
Date: 2020-05-29T13:14:08-04:00
New Revision: db653ff6b777f9133793c21c48a46912bc1a77df
URL: https://github.com/llvm/llvm-project/commit/db653ff6b777f9133793c21c48a46912bc1a77df
DIFF: https://github.com/llvm/llvm-project/commit/db653ff6b777f9133793c21c48a46912bc1a77df.diff
LOG: [LoopVectorize] auto-generate complete test checks; NFC
Added:
Modified:
llvm/test/Transforms/LoopVectorize/X86/reduction-fastmath.ll
Removed:
################################################################################
diff --git a/llvm/test/Transforms/LoopVectorize/X86/reduction-fastmath.ll b/llvm/test/Transforms/LoopVectorize/X86/reduction-fastmath.ll
index 1146e31ec258..9063c5116cca 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/reduction-fastmath.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/reduction-fastmath.ll
@@ -1,10 +1,32 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -loop-vectorize < %s | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
define float @reduction_sum_float_ieee(i32 %n, float* %array) {
-; CHECK-LABEL: define float @reduction_sum_float_ieee(
+; CHECK-LABEL: @reduction_sum_float_ieee(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[ENTRY_COND:%.*]] = icmp ne i32 0, 4096
+; CHECK-NEXT: br i1 [[ENTRY_COND]], label [[LOOP_PREHEADER:%.*]], label [[LOOP_EXIT:%.*]]
+; CHECK: loop.preheader:
+; CHECK-NEXT: br label [[LOOP:%.*]]
+; CHECK: loop:
+; CHECK-NEXT: [[IDX:%.*]] = phi i32 [ [[IDX_INC:%.*]], [[LOOP]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT: [[SUM:%.*]] = phi float [ [[SUM_INC:%.*]], [[LOOP]] ], [ 0.000000e+00, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT: [[ADDRESS:%.*]] = getelementptr float, float* [[ARRAY:%.*]], i32 [[IDX]]
+; CHECK-NEXT: [[VALUE:%.*]] = load float, float* [[ADDRESS]], align 4
+; CHECK-NEXT: [[SUM_INC]] = fadd float [[SUM]], [[VALUE]]
+; CHECK-NEXT: [[IDX_INC]] = add i32 [[IDX]], 1
+; CHECK-NEXT: [[BE_COND:%.*]] = icmp ne i32 [[IDX_INC]], 4096
+; CHECK-NEXT: br i1 [[BE_COND]], label [[LOOP]], label [[LOOP_EXIT_LOOPEXIT:%.*]]
+; CHECK: loop.exit.loopexit:
+; CHECK-NEXT: [[SUM_INC_LCSSA:%.*]] = phi float [ [[SUM_INC]], [[LOOP]] ]
+; CHECK-NEXT: br label [[LOOP_EXIT]]
+; CHECK: loop.exit:
+; CHECK-NEXT: [[SUM_LCSSA:%.*]] = phi float [ 0.000000e+00, [[ENTRY:%.*]] ], [ [[SUM_INC_LCSSA]], [[LOOP_EXIT_LOOPEXIT]] ]
+; CHECK-NEXT: ret float [[SUM_LCSSA]]
+;
entry:
%entry.cond = icmp ne i32 0, 4096
br i1 %entry.cond, label %loop, label %loop.exit
@@ -21,18 +43,66 @@ loop:
loop.exit:
%sum.lcssa = phi float [ %sum.inc, %loop ], [ 0.000000e+00, %entry ]
-; CHECK-NOT: %wide.load = load <4 x float>, <4 x float>*
-; CHECK: ret float %sum.lcssa
ret float %sum.lcssa
}
define float @reduction_sum_float_fastmath(i32 %n, float* %array) {
-; CHECK-LABEL: define float @reduction_sum_float_fastmath(
-; CHECK: fadd fast <4 x float>
-; CHECK: fadd fast <4 x float>
-; CHECK: fadd fast <4 x float>
-; CHECK: fadd fast <4 x float>
-; CHECK: fadd fast <4 x float>
+; CHECK-LABEL: @reduction_sum_float_fastmath(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[ENTRY_COND:%.*]] = icmp ne i32 0, 4096
+; CHECK-NEXT: br i1 [[ENTRY_COND]], label [[LOOP_PREHEADER:%.*]], label [[LOOP_EXIT:%.*]]
+; CHECK: loop.preheader:
+; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK: vector.ph:
+; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
+; CHECK: vector.body:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x float> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP8:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <4 x float> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP9:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
+; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[INDEX]], 4
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr float, float* [[ARRAY:%.*]], i32 [[TMP0]]
+; CHECK-NEXT: [[TMP3:%.*]] = getelementptr float, float* [[ARRAY]], i32 [[TMP1]]
+; CHECK-NEXT: [[TMP4:%.*]] = getelementptr float, float* [[TMP2]], i32 0
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast float* [[TMP4]] to <4 x float>*
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, <4 x float>* [[TMP5]], align 4
+; CHECK-NEXT: [[TMP6:%.*]] = getelementptr float, float* [[TMP2]], i32 4
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast float* [[TMP6]] to <4 x float>*
+; CHECK-NEXT: [[WIDE_LOAD2:%.*]] = load <4 x float>, <4 x float>* [[TMP7]], align 4
+; CHECK-NEXT: [[TMP8]] = fadd fast <4 x float> [[VEC_PHI]], [[WIDE_LOAD]]
+; CHECK-NEXT: [[TMP9]] = fadd fast <4 x float> [[VEC_PHI1]], [[WIDE_LOAD2]]
+; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 8
+; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i32 [[INDEX_NEXT]], 4096
+; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
+; CHECK: middle.block:
+; CHECK-NEXT: [[BIN_RDX:%.*]] = fadd fast <4 x float> [[TMP9]], [[TMP8]]
+; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x float> [[BIN_RDX]], <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
+; CHECK-NEXT: [[BIN_RDX3:%.*]] = fadd fast <4 x float> [[BIN_RDX]], [[RDX_SHUF]]
+; CHECK-NEXT: [[RDX_SHUF4:%.*]] = shufflevector <4 x float> [[BIN_RDX3]], <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT: [[BIN_RDX5:%.*]] = fadd fast <4 x float> [[BIN_RDX3]], [[RDX_SHUF4]]
+; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x float> [[BIN_RDX5]], i32 0
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 4096, 4096
+; CHECK-NEXT: br i1 [[CMP_N]], label [[LOOP_EXIT_LOOPEXIT:%.*]], label [[SCALAR_PH]]
+; CHECK: scalar.ph:
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 4096, [[MIDDLE_BLOCK]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi float [ 0.000000e+00, [[LOOP_PREHEADER]] ], [ [[TMP11]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: br label [[LOOP:%.*]]
+; CHECK: loop:
+; CHECK-NEXT: [[IDX:%.*]] = phi i32 [ [[IDX_INC:%.*]], [[LOOP]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT: [[SUM:%.*]] = phi float [ [[SUM_INC:%.*]], [[LOOP]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
+; CHECK-NEXT: [[ADDRESS:%.*]] = getelementptr float, float* [[ARRAY]], i32 [[IDX]]
+; CHECK-NEXT: [[VALUE:%.*]] = load float, float* [[ADDRESS]], align 4
+; CHECK-NEXT: [[SUM_INC]] = fadd fast float [[SUM]], [[VALUE]]
+; CHECK-NEXT: [[IDX_INC]] = add i32 [[IDX]], 1
+; CHECK-NEXT: [[BE_COND:%.*]] = icmp ne i32 [[IDX_INC]], 4096
+; CHECK-NEXT: br i1 [[BE_COND]], label [[LOOP]], label [[LOOP_EXIT_LOOPEXIT]], !llvm.loop !2
+; CHECK: loop.exit.loopexit:
+; CHECK-NEXT: [[SUM_INC_LCSSA:%.*]] = phi float [ [[SUM_INC]], [[LOOP]] ], [ [[TMP11]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: br label [[LOOP_EXIT]]
+; CHECK: loop.exit:
+; CHECK-NEXT: [[SUM_LCSSA:%.*]] = phi float [ 0.000000e+00, [[ENTRY:%.*]] ], [ [[SUM_INC_LCSSA]], [[LOOP_EXIT_LOOPEXIT]] ]
+; CHECK-NEXT: ret float [[SUM_LCSSA]]
+;
entry:
%entry.cond = icmp ne i32 0, 4096
br i1 %entry.cond, label %loop, label %loop.exit
@@ -49,19 +119,66 @@ loop:
loop.exit:
%sum.lcssa = phi float [ %sum.inc, %loop ], [ 0.000000e+00, %entry ]
-; CHECK: ret float %sum.lcssa
ret float %sum.lcssa
}
define float @reduction_sum_float_only_reassoc(i32 %n, float* %array) {
-; CHECK-LABEL: define float @reduction_sum_float_only_reassoc(
-; CHECK-NOT: fadd fast
-; CHECK: fadd reassoc <4 x float>
-; CHECK: fadd reassoc <4 x float>
-; CHECK: fadd reassoc <4 x float>
-; CHECK: fadd reassoc <4 x float>
-; CHECK: fadd reassoc <4 x float>
-
+; CHECK-LABEL: @reduction_sum_float_only_reassoc(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[ENTRY_COND:%.*]] = icmp ne i32 0, 4096
+; CHECK-NEXT: br i1 [[ENTRY_COND]], label [[LOOP_PREHEADER:%.*]], label [[LOOP_EXIT:%.*]]
+; CHECK: loop.preheader:
+; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK: vector.ph:
+; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
+; CHECK: vector.body:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x float> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP8:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <4 x float> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP9:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
+; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[INDEX]], 4
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr float, float* [[ARRAY:%.*]], i32 [[TMP0]]
+; CHECK-NEXT: [[TMP3:%.*]] = getelementptr float, float* [[ARRAY]], i32 [[TMP1]]
+; CHECK-NEXT: [[TMP4:%.*]] = getelementptr float, float* [[TMP2]], i32 0
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast float* [[TMP4]] to <4 x float>*
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, <4 x float>* [[TMP5]], align 4
+; CHECK-NEXT: [[TMP6:%.*]] = getelementptr float, float* [[TMP2]], i32 4
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast float* [[TMP6]] to <4 x float>*
+; CHECK-NEXT: [[WIDE_LOAD2:%.*]] = load <4 x float>, <4 x float>* [[TMP7]], align 4
+; CHECK-NEXT: [[TMP8]] = fadd reassoc <4 x float> [[VEC_PHI]], [[WIDE_LOAD]]
+; CHECK-NEXT: [[TMP9]] = fadd reassoc <4 x float> [[VEC_PHI1]], [[WIDE_LOAD2]]
+; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 8
+; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i32 [[INDEX_NEXT]], 4096
+; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !4
+; CHECK: middle.block:
+; CHECK-NEXT: [[BIN_RDX:%.*]] = fadd reassoc <4 x float> [[TMP9]], [[TMP8]]
+; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x float> [[BIN_RDX]], <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
+; CHECK-NEXT: [[BIN_RDX3:%.*]] = fadd reassoc <4 x float> [[BIN_RDX]], [[RDX_SHUF]]
+; CHECK-NEXT: [[RDX_SHUF4:%.*]] = shufflevector <4 x float> [[BIN_RDX3]], <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT: [[BIN_RDX5:%.*]] = fadd reassoc <4 x float> [[BIN_RDX3]], [[RDX_SHUF4]]
+; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x float> [[BIN_RDX5]], i32 0
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 4096, 4096
+; CHECK-NEXT: br i1 [[CMP_N]], label [[LOOP_EXIT_LOOPEXIT:%.*]], label [[SCALAR_PH]]
+; CHECK: scalar.ph:
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 4096, [[MIDDLE_BLOCK]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi float [ 0.000000e+00, [[LOOP_PREHEADER]] ], [ [[TMP11]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: br label [[LOOP:%.*]]
+; CHECK: loop:
+; CHECK-NEXT: [[IDX:%.*]] = phi i32 [ [[IDX_INC:%.*]], [[LOOP]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT: [[SUM:%.*]] = phi float [ [[SUM_INC:%.*]], [[LOOP]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
+; CHECK-NEXT: [[ADDRESS:%.*]] = getelementptr float, float* [[ARRAY]], i32 [[IDX]]
+; CHECK-NEXT: [[VALUE:%.*]] = load float, float* [[ADDRESS]], align 4
+; CHECK-NEXT: [[SUM_INC]] = fadd reassoc float [[SUM]], [[VALUE]]
+; CHECK-NEXT: [[IDX_INC]] = add i32 [[IDX]], 1
+; CHECK-NEXT: [[BE_COND:%.*]] = icmp ne i32 [[IDX_INC]], 4096
+; CHECK-NEXT: br i1 [[BE_COND]], label [[LOOP]], label [[LOOP_EXIT_LOOPEXIT]], !llvm.loop !5
+; CHECK: loop.exit.loopexit:
+; CHECK-NEXT: [[SUM_INC_LCSSA:%.*]] = phi float [ [[SUM_INC]], [[LOOP]] ], [ [[TMP11]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: br label [[LOOP_EXIT]]
+; CHECK: loop.exit:
+; CHECK-NEXT: [[SUM_LCSSA:%.*]] = phi float [ 0.000000e+00, [[ENTRY:%.*]] ], [ [[SUM_INC_LCSSA]], [[LOOP_EXIT_LOOPEXIT]] ]
+; CHECK-NEXT: ret float [[SUM_LCSSA]]
+;
entry:
%entry.cond = icmp ne i32 0, 4096
br i1 %entry.cond, label %loop, label %loop.exit
@@ -78,19 +195,66 @@ loop:
loop.exit:
%sum.lcssa = phi float [ %sum.inc, %loop ], [ 0.000000e+00, %entry ]
-; CHECK: ret float %sum.lcssa
ret float %sum.lcssa
}
define float @reduction_sum_float_only_reassoc_and_contract(i32 %n, float* %array) {
-; CHECK-LABEL: define float @reduction_sum_float_only_reassoc_and_contract(
-; CHECK-NOT: fadd fast
-; CHECK: fadd reassoc contract <4 x float>
-; CHECK: fadd reassoc contract <4 x float>
-; CHECK: fadd reassoc contract <4 x float>
-; CHECK: fadd reassoc contract <4 x float>
-; CHECK: fadd reassoc contract <4 x float>
-
+; CHECK-LABEL: @reduction_sum_float_only_reassoc_and_contract(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[ENTRY_COND:%.*]] = icmp ne i32 0, 4096
+; CHECK-NEXT: br i1 [[ENTRY_COND]], label [[LOOP_PREHEADER:%.*]], label [[LOOP_EXIT:%.*]]
+; CHECK: loop.preheader:
+; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK: vector.ph:
+; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
+; CHECK: vector.body:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x float> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP8:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <4 x float> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP9:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
+; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[INDEX]], 4
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr float, float* [[ARRAY:%.*]], i32 [[TMP0]]
+; CHECK-NEXT: [[TMP3:%.*]] = getelementptr float, float* [[ARRAY]], i32 [[TMP1]]
+; CHECK-NEXT: [[TMP4:%.*]] = getelementptr float, float* [[TMP2]], i32 0
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast float* [[TMP4]] to <4 x float>*
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, <4 x float>* [[TMP5]], align 4
+; CHECK-NEXT: [[TMP6:%.*]] = getelementptr float, float* [[TMP2]], i32 4
+; CHECK-NEXT: [[TMP7:%.*]] = bitcast float* [[TMP6]] to <4 x float>*
+; CHECK-NEXT: [[WIDE_LOAD2:%.*]] = load <4 x float>, <4 x float>* [[TMP7]], align 4
+; CHECK-NEXT: [[TMP8]] = fadd reassoc contract <4 x float> [[VEC_PHI]], [[WIDE_LOAD]]
+; CHECK-NEXT: [[TMP9]] = fadd reassoc contract <4 x float> [[VEC_PHI1]], [[WIDE_LOAD2]]
+; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 8
+; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i32 [[INDEX_NEXT]], 4096
+; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !6
+; CHECK: middle.block:
+; CHECK-NEXT: [[BIN_RDX:%.*]] = fadd reassoc contract <4 x float> [[TMP9]], [[TMP8]]
+; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x float> [[BIN_RDX]], <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
+; CHECK-NEXT: [[BIN_RDX3:%.*]] = fadd reassoc contract <4 x float> [[BIN_RDX]], [[RDX_SHUF]]
+; CHECK-NEXT: [[RDX_SHUF4:%.*]] = shufflevector <4 x float> [[BIN_RDX3]], <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT: [[BIN_RDX5:%.*]] = fadd reassoc contract <4 x float> [[BIN_RDX3]], [[RDX_SHUF4]]
+; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x float> [[BIN_RDX5]], i32 0
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 4096, 4096
+; CHECK-NEXT: br i1 [[CMP_N]], label [[LOOP_EXIT_LOOPEXIT:%.*]], label [[SCALAR_PH]]
+; CHECK: scalar.ph:
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 4096, [[MIDDLE_BLOCK]] ], [ 0, [[LOOP_PREHEADER]] ]
+; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi float [ 0.000000e+00, [[LOOP_PREHEADER]] ], [ [[TMP11]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: br label [[LOOP:%.*]]
+; CHECK: loop:
+; CHECK-NEXT: [[IDX:%.*]] = phi i32 [ [[IDX_INC:%.*]], [[LOOP]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT: [[SUM:%.*]] = phi float [ [[SUM_INC:%.*]], [[LOOP]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
+; CHECK-NEXT: [[ADDRESS:%.*]] = getelementptr float, float* [[ARRAY]], i32 [[IDX]]
+; CHECK-NEXT: [[VALUE:%.*]] = load float, float* [[ADDRESS]], align 4
+; CHECK-NEXT: [[SUM_INC]] = fadd reassoc contract float [[SUM]], [[VALUE]]
+; CHECK-NEXT: [[IDX_INC]] = add i32 [[IDX]], 1
+; CHECK-NEXT: [[BE_COND:%.*]] = icmp ne i32 [[IDX_INC]], 4096
+; CHECK-NEXT: br i1 [[BE_COND]], label [[LOOP]], label [[LOOP_EXIT_LOOPEXIT]], !llvm.loop !7
+; CHECK: loop.exit.loopexit:
+; CHECK-NEXT: [[SUM_INC_LCSSA:%.*]] = phi float [ [[SUM_INC]], [[LOOP]] ], [ [[TMP11]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: br label [[LOOP_EXIT]]
+; CHECK: loop.exit:
+; CHECK-NEXT: [[SUM_LCSSA:%.*]] = phi float [ 0.000000e+00, [[ENTRY:%.*]] ], [ [[SUM_INC_LCSSA]], [[LOOP_EXIT_LOOPEXIT]] ]
+; CHECK-NEXT: ret float [[SUM_LCSSA]]
+;
entry:
%entry.cond = icmp ne i32 0, 4096
br i1 %entry.cond, label %loop, label %loop.exit
@@ -107,6 +271,5 @@ loop:
loop.exit:
%sum.lcssa = phi float [ %sum.inc, %loop ], [ 0.000000e+00, %entry ]
-; CHECK: ret float %sum.lcssa
ret float %sum.lcssa
}
More information about the llvm-commits
mailing list