caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[RISCV][AArch64] Add vscale_range attribute to tests per architecture minimums

Browse Source 
Spent a bunch of time tracing down an odd issue "in SCEV" which turned out
to be the fact that SCEV doesn't have access to TTI.  As a result, the only
way for it to get range facts on vscales (to avoid collapsing ranges of
element counts and type sizes to trivial ranges on multiplies) is to look
at the vscale_range attribute.  Since vscale_range is set by clang by
default, manually setting it in the tests shouldn't interfere with the
test intent.
This commit is contained in:
Philip Reames
2024-02-22 07:54:51 -08:00
committed by Philip Reames
parent 695a9d84dc
commit 9eb5f94f9b
2 changed files with 41 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

90
llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll
View File

@@ -1,7 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
; RUN: opt -S < %s -passes=loop-vectorize -mtriple aarch64-linux-gnu -mattr=+sve 2>&1 | FileCheck %s
define void @clamped_tc_8(ptr nocapture %dst, i32 %n, i64 %val){
define void @clamped_tc_8(ptr nocapture %dst, i32 %n, i64 %val) vscale_range(1,16) {
; CHECK-LABEL: define void @clamped_tc_8(
; CHECK-SAME: ptr nocapture [[DST:%.*]], i32 [[N:%.*]], i64 [[VAL:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: entry:
@@ -18,20 +18,15 @@ define void @clamped_tc_8(ptr nocapture %dst, i32 %n, i64 %val){
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[DST]], i64 [[N_VEC]]
; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 8
; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP8:%.*]] = mul i64 [[TMP7]], 8
; CHECK-NEXT: [[TMP9:%.*]] = sub i64 8, [[TMP8]]
; CHECK-NEXT: [[TMP10:%.*]] = icmp ugt i64 8, [[TMP8]]
; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i64 [[TMP9]], i64 0
; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 0, i64 8)
; CHECK-NEXT: [[TMP12:%.*]] = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
; CHECK-NEXT: [[TMP13:%.*]] = add <vscale x 8 x i64> [[TMP12]], zeroinitializer
; CHECK-NEXT: [[TMP14:%.*]] = mul <vscale x 8 x i64> [[TMP13]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 1, i64 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP14]]
; CHECK-NEXT: [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP16:%.*]] = mul i64 [[TMP15]], 8
; CHECK-NEXT: [[TMP17:%.*]] = mul i64 1, [[TMP16]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP17]], i64 0
; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
; CHECK-NEXT: [[TMP8:%.*]] = add <vscale x 8 x i64> [[TMP7]], zeroinitializer
; CHECK-NEXT: [[TMP9:%.*]] = mul <vscale x 8 x i64> [[TMP8]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 1, i64 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP9]]
; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP11:%.*]] = mul i64 [[TMP10]], 8
; CHECK-NEXT: [[TMP12:%.*]] = mul i64 1, [[TMP11]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP12]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x i64> [[DOTSPLATINSERT]], <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[VAL]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 8 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
@@ -40,17 +35,17 @@ define void @clamped_tc_8(ptr nocapture %dst, i32 %n, i64 %val){
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 8 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <vscale x 8 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP18:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[DST]], i64 [[TMP18]]
; CHECK-NEXT: [[TMP19:%.*]] = shl nuw nsw <vscale x 8 x i64> [[VEC_IND]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 3, i64 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP20:%.*]] = lshr <vscale x 8 x i64> [[BROADCAST_SPLAT]], [[TMP19]]
; CHECK-NEXT: [[TMP21:%.*]] = trunc <vscale x 8 x i64> [[TMP20]] to <vscale x 8 x i8>
; CHECK-NEXT: [[TMP22:%.*]] = getelementptr i8, ptr [[NEXT_GEP]], i32 0
; CHECK-NEXT: call void @llvm.masked.store.nxv8i8.p0(<vscale x 8 x i8> [[TMP21]], ptr [[TMP22]], i32 1, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[TMP13:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[DST]], i64 [[TMP13]]
; CHECK-NEXT: [[TMP14:%.*]] = shl nuw nsw <vscale x 8 x i64> [[VEC_IND]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 3, i64 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP15:%.*]] = lshr <vscale x 8 x i64> [[BROADCAST_SPLAT]], [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = trunc <vscale x 8 x i64> [[TMP15]] to <vscale x 8 x i8>
; CHECK-NEXT: [[TMP17:%.*]] = getelementptr i8, ptr [[NEXT_GEP]], i32 0
; CHECK-NEXT: call void @llvm.masked.store.nxv8i8.p0(<vscale x 8 x i8> [[TMP16]], ptr [[TMP17]], i32 1, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX]], i64 [[TMP11]])
; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX_NEXT]], i64 8)
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 8 x i64> [[VEC_IND]], [[DOTSPLAT]]
; CHECK-NEXT: [[TMP23:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP18:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
@@ -61,8 +56,8 @@ define void @clamped_tc_8(ptr nocapture %dst, i32 %n, i64 %val){
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[P_OUT_TAIL_09:%.*]] = phi ptr [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[INCDEC_PTR:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[TMP24:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
; CHECK-NEXT: [[SHR3:%.*]] = lshr i64 [[VAL]], [[TMP24]]
; CHECK-NEXT: [[TMP19:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
; CHECK-NEXT: [[SHR3:%.*]] = lshr i64 [[VAL]], [[TMP19]]
; CHECK-NEXT: [[CONV4:%.*]] = trunc i64 [[SHR3]] to i8
; CHECK-NEXT: store i8 [[CONV4]], ptr [[P_OUT_TAIL_09]], align 1
; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, ptr [[P_OUT_TAIL_09]], i64 1
@@ -91,7 +86,7 @@ for.cond.cleanup: ; preds = %for.body
ret void
}
define void @clamped_tc_max_8(ptr nocapture %dst, i32 %n, i64 %val){
define void @clamped_tc_max_8(ptr nocapture %dst, i32 %n, i64 %val) vscale_range(1,16) {
; CHECK-LABEL: define void @clamped_tc_max_8(
; CHECK-SAME: ptr nocapture [[DST:%.*]], i32 [[N:%.*]], i64 [[VAL:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
@@ -115,20 +110,15 @@ define void @clamped_tc_max_8(ptr nocapture %dst, i32 %n, i64 %val){
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[DST]], i64 [[N_VEC]]
; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 8
; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP8:%.*]] = mul i64 [[TMP7]], 8
; CHECK-NEXT: [[TMP9:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[TMP8]]
; CHECK-NEXT: [[TMP10:%.*]] = icmp ugt i64 [[WIDE_TRIP_COUNT]], [[TMP8]]
; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i64 [[TMP9]], i64 0
; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 0, i64 [[WIDE_TRIP_COUNT]])
; CHECK-NEXT: [[TMP12:%.*]] = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
; CHECK-NEXT: [[TMP13:%.*]] = add <vscale x 8 x i64> [[TMP12]], zeroinitializer
; CHECK-NEXT: [[TMP14:%.*]] = mul <vscale x 8 x i64> [[TMP13]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 1, i64 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP14]]
; CHECK-NEXT: [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP16:%.*]] = mul i64 [[TMP15]], 8
; CHECK-NEXT: [[TMP17:%.*]] = mul i64 1, [[TMP16]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP17]], i64 0
; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
; CHECK-NEXT: [[TMP8:%.*]] = add <vscale x 8 x i64> [[TMP7]], zeroinitializer
; CHECK-NEXT: [[TMP9:%.*]] = mul <vscale x 8 x i64> [[TMP8]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 1, i64 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP9]]
; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP11:%.*]] = mul i64 [[TMP10]], 8
; CHECK-NEXT: [[TMP12:%.*]] = mul i64 1, [[TMP11]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP12]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x i64> [[DOTSPLATINSERT]], <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[VAL]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 8 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
@@ -137,17 +127,17 @@ define void @clamped_tc_max_8(ptr nocapture %dst, i32 %n, i64 %val){
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 8 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <vscale x 8 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP18:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[DST]], i64 [[TMP18]]
; CHECK-NEXT: [[TMP19:%.*]] = shl nuw nsw <vscale x 8 x i64> [[VEC_IND]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 3, i64 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP20:%.*]] = lshr <vscale x 8 x i64> [[BROADCAST_SPLAT]], [[TMP19]]
; CHECK-NEXT: [[TMP21:%.*]] = trunc <vscale x 8 x i64> [[TMP20]] to <vscale x 8 x i8>
; CHECK-NEXT: [[TMP22:%.*]] = getelementptr i8, ptr [[NEXT_GEP]], i32 0
; CHECK-NEXT: call void @llvm.masked.store.nxv8i8.p0(<vscale x 8 x i8> [[TMP21]], ptr [[TMP22]], i32 1, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[TMP13:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[DST]], i64 [[TMP13]]
; CHECK-NEXT: [[TMP14:%.*]] = shl nuw nsw <vscale x 8 x i64> [[VEC_IND]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 3, i64 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP15:%.*]] = lshr <vscale x 8 x i64> [[BROADCAST_SPLAT]], [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = trunc <vscale x 8 x i64> [[TMP15]] to <vscale x 8 x i8>
; CHECK-NEXT: [[TMP17:%.*]] = getelementptr i8, ptr [[NEXT_GEP]], i32 0
; CHECK-NEXT: call void @llvm.masked.store.nxv8i8.p0(<vscale x 8 x i8> [[TMP16]], ptr [[TMP17]], i32 1, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX]], i64 [[TMP11]])
; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX_NEXT]], i64 [[WIDE_TRIP_COUNT]])
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 8 x i64> [[VEC_IND]], [[DOTSPLAT]]
; CHECK-NEXT: [[TMP23:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP18:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
@@ -158,8 +148,8 @@ define void @clamped_tc_max_8(ptr nocapture %dst, i32 %n, i64 %val){
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[P_OUT_TAIL_09:%.*]] = phi ptr [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[INCDEC_PTR:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[TMP24:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
; CHECK-NEXT: [[SHR3:%.*]] = lshr i64 [[VAL]], [[TMP24]]
; CHECK-NEXT: [[TMP19:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
; CHECK-NEXT: [[SHR3:%.*]] = lshr i64 [[VAL]], [[TMP19]]
; CHECK-NEXT: [[CONV4:%.*]] = trunc i64 [[SHR3]] to i8
; CHECK-NEXT: store i8 [[CONV4]], ptr [[P_OUT_TAIL_09]], align 1
; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, ptr [[P_OUT_TAIL_09]], i64 1

2
llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
View File

@@ -74,4 +74,4 @@ for.end: ; preds = %for.body
ret void
}
attributes #0 = { "target-features"="+v,+d" }
attributes #0 = { "target-features"="+v,+d" vscale_range(2, 1024) }