forked from OSchip/llvm-project
UpdateTestChecks: arm64-eabi handlind
Summary: Was looking into supporting `(srl (shl x, c1), c2)` with c1 != c2 in dagcombiner, this test changes, but makes `update_llc_test_checks.py` unhappy Reviewers: RKSimon Reviewed By: RKSimon Subscribers: javed.absar, kristof.beyls, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62097 llvm-svn: 361100
This commit is contained in:
Roman Lebedev
parent
f40c18b628
commit
822b9c971b
|
|
@ -1,16 +1,29 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
||||
; RUN: opt -codegenprepare -mtriple=arm64-apple=ios -S -o - %s | FileCheck --check-prefix=OPT %s
|
||||
; RUN: llc < %s -mtriple=arm64-eabi | FileCheck %s
|
||||
; RUN: llc < %s -mtriple=arm64-eabi | FileCheck --check-prefix=LLC %s
|
||||
|
||||
%struct.X = type { i8, i8, [2 x i8] }
|
||||
%struct.Y = type { i32, i8 }
|
||||
%struct.Z = type { i8, i8, [2 x i8], i16 }
|
||||
%struct.A = type { i64, i8 }
|
||||
|
||||
define void @foo(%struct.X* nocapture %x, %struct.Y* nocapture %y) nounwind optsize ssp {
|
||||
; CHECK-LABEL: foo:
|
||||
; CHECK: ubfx
|
||||
; CHECK-NOT: and
|
||||
; CHECK: ret
|
||||
|
||||
; LLC-LABEL: foo:
|
||||
; LLC: // %bb.0:
|
||||
; LLC-NEXT: ldr w8, [x0]
|
||||
; LLC-NEXT: ubfx w8, w8, #3, #1
|
||||
; LLC-NEXT: strb w8, [x1, #4]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @foo(
|
||||
; OPT-NEXT: [[TMP:%.*]] = bitcast %struct.X* [[X:%.*]] to i32*
|
||||
; OPT-NEXT: [[TMP1:%.*]] = load i32, i32* [[TMP]], align 4
|
||||
; OPT-NEXT: [[B:%.*]] = getelementptr inbounds [[STRUCT_Y:%.*]], %struct.Y* [[Y:%.*]], i64 0, i32 1
|
||||
; OPT-NEXT: [[BF_CLEAR:%.*]] = lshr i32 [[TMP1]], 3
|
||||
; OPT-NEXT: [[BF_CLEAR_LOBIT:%.*]] = and i32 [[BF_CLEAR]], 1
|
||||
; OPT-NEXT: [[FROMBOOL:%.*]] = trunc i32 [[BF_CLEAR_LOBIT]] to i8
|
||||
; OPT-NEXT: store i8 [[FROMBOOL]], i8* [[B]], align 1
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
%tmp = bitcast %struct.X* %x to i32*
|
||||
%tmp1 = load i32, i32* %tmp, align 4
|
||||
%b = getelementptr inbounds %struct.Y, %struct.Y* %y, i64 0, i32 1
|
||||
|
|
@ -22,8 +35,16 @@ define void @foo(%struct.X* nocapture %x, %struct.Y* nocapture %y) nounwind opts
|
|||
}
|
||||
|
||||
define i32 @baz(i64 %cav1.coerce) nounwind {
|
||||
; CHECK-LABEL: baz:
|
||||
; CHECK: sbfx w0, w0, #0, #4
|
||||
; LLC-LABEL: baz:
|
||||
; LLC: // %bb.0:
|
||||
; LLC-NEXT: sbfx w0, w0, #0, #4
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @baz(
|
||||
; OPT-NEXT: [[TMP:%.*]] = trunc i64 [[CAV1_COERCE:%.*]] to i32
|
||||
; OPT-NEXT: [[TMP1:%.*]] = shl i32 [[TMP]], 28
|
||||
; OPT-NEXT: [[BF_VAL_SEXT:%.*]] = ashr exact i32 [[TMP1]], 28
|
||||
; OPT-NEXT: ret i32 [[BF_VAL_SEXT]]
|
||||
;
|
||||
%tmp = trunc i64 %cav1.coerce to i32
|
||||
%tmp1 = shl i32 %tmp, 28
|
||||
%bf.val.sext = ashr exact i32 %tmp1, 28
|
||||
|
|
@ -31,8 +52,16 @@ define i32 @baz(i64 %cav1.coerce) nounwind {
|
|||
}
|
||||
|
||||
define i32 @bar(i64 %cav1.coerce) nounwind {
|
||||
; CHECK-LABEL: bar:
|
||||
; CHECK: sbfx w0, w0, #4, #6
|
||||
; LLC-LABEL: bar:
|
||||
; LLC: // %bb.0:
|
||||
; LLC-NEXT: sbfx w0, w0, #4, #6
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @bar(
|
||||
; OPT-NEXT: [[TMP:%.*]] = trunc i64 [[CAV1_COERCE:%.*]] to i32
|
||||
; OPT-NEXT: [[CAV1_SROA_0_1_INSERT:%.*]] = shl i32 [[TMP]], 22
|
||||
; OPT-NEXT: [[TMP1:%.*]] = ashr i32 [[CAV1_SROA_0_1_INSERT]], 26
|
||||
; OPT-NEXT: ret i32 [[TMP1]]
|
||||
;
|
||||
%tmp = trunc i64 %cav1.coerce to i32
|
||||
%cav1.sroa.0.1.insert = shl i32 %tmp, 22
|
||||
%tmp1 = ashr i32 %cav1.sroa.0.1.insert, 26
|
||||
|
|
@ -40,11 +69,21 @@ define i32 @bar(i64 %cav1.coerce) nounwind {
|
|||
}
|
||||
|
||||
define void @fct1(%struct.Z* nocapture %x, %struct.A* nocapture %y) nounwind optsize ssp {
|
||||
; CHECK-LABEL: fct1:
|
||||
; CHECK: ubfx x{{[0-9]+}}, x{{[0-9]+}}
|
||||
; CHECK-NOT: and
|
||||
; CHECK: ret
|
||||
|
||||
; LLC-LABEL: fct1:
|
||||
; LLC: // %bb.0:
|
||||
; LLC-NEXT: ldr x8, [x0]
|
||||
; LLC-NEXT: ubfx x8, x8, #3, #1
|
||||
; LLC-NEXT: str x8, [x1]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct1(
|
||||
; OPT-NEXT: [[TMP:%.*]] = bitcast %struct.Z* [[X:%.*]] to i64*
|
||||
; OPT-NEXT: [[TMP1:%.*]] = load i64, i64* [[TMP]], align 4
|
||||
; OPT-NEXT: [[B1:%.*]] = bitcast %struct.A* [[Y:%.*]] to i64*
|
||||
; OPT-NEXT: [[BF_CLEAR:%.*]] = lshr i64 [[TMP1]], 3
|
||||
; OPT-NEXT: [[BF_CLEAR_LOBIT:%.*]] = and i64 [[BF_CLEAR]], 1
|
||||
; OPT-NEXT: store i64 [[BF_CLEAR_LOBIT]], i64* [[B1]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
%tmp = bitcast %struct.Z* %x to i64*
|
||||
%tmp1 = load i64, i64* %tmp, align 4
|
||||
%b = getelementptr inbounds %struct.A, %struct.A* %y, i64 0, i32 0
|
||||
|
|
@ -55,28 +94,53 @@ define void @fct1(%struct.Z* nocapture %x, %struct.A* nocapture %y) nounwind opt
|
|||
}
|
||||
|
||||
define i64 @fct2(i64 %cav1.coerce) nounwind {
|
||||
; CHECK-LABEL: fct2:
|
||||
; CHECK: sbfx x0, x0, #0, #36
|
||||
; LLC-LABEL: fct2:
|
||||
; LLC: // %bb.0:
|
||||
; LLC-NEXT: sbfx x0, x0, #0, #36
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct2(
|
||||
; OPT-NEXT: [[TMP:%.*]] = shl i64 [[CAV1_COERCE:%.*]], 28
|
||||
; OPT-NEXT: [[BF_VAL_SEXT:%.*]] = ashr exact i64 [[TMP]], 28
|
||||
; OPT-NEXT: ret i64 [[BF_VAL_SEXT]]
|
||||
;
|
||||
%tmp = shl i64 %cav1.coerce, 28
|
||||
%bf.val.sext = ashr exact i64 %tmp, 28
|
||||
ret i64 %bf.val.sext
|
||||
}
|
||||
|
||||
define i64 @fct3(i64 %cav1.coerce) nounwind {
|
||||
; CHECK-LABEL: fct3:
|
||||
; CHECK: sbfx x0, x0, #4, #38
|
||||
; LLC-LABEL: fct3:
|
||||
; LLC: // %bb.0:
|
||||
; LLC-NEXT: sbfx x0, x0, #4, #38
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct3(
|
||||
; OPT-NEXT: [[CAV1_SROA_0_1_INSERT:%.*]] = shl i64 [[CAV1_COERCE:%.*]], 22
|
||||
; OPT-NEXT: [[TMP1:%.*]] = ashr i64 [[CAV1_SROA_0_1_INSERT]], 26
|
||||
; OPT-NEXT: ret i64 [[TMP1]]
|
||||
;
|
||||
%cav1.sroa.0.1.insert = shl i64 %cav1.coerce, 22
|
||||
%tmp1 = ashr i64 %cav1.sroa.0.1.insert, 26
|
||||
ret i64 %tmp1
|
||||
}
|
||||
|
||||
define void @fct4(i64* nocapture %y, i64 %x) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct4:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr x8, [x0]
|
||||
; LLC-NEXT: bfxil x8, x1, #16, #24
|
||||
; LLC-NEXT: str x8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct4(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i64, i64* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i64 [[TMP0]], -16777216
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i64 [[X:%.*]], 16
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i64 [[SHR]], 16777215
|
||||
; OPT-NEXT: [[OR:%.*]] = or i64 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: store i64 [[OR]], i64* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct4:
|
||||
; CHECK: ldr [[REG1:x[0-9]+]],
|
||||
; CHECK-NEXT: bfxil [[REG1]], x1, #16, #24
|
||||
; CHECK-NEXT: str [[REG1]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i64, i64* %y, align 8
|
||||
%and = and i64 %0, -16777216
|
||||
%shr = lshr i64 %x, 16
|
||||
|
|
@ -87,12 +151,23 @@ entry:
|
|||
}
|
||||
|
||||
define void @fct5(i32* nocapture %y, i32 %x) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct5:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr w8, [x0]
|
||||
; LLC-NEXT: bfxil w8, w1, #16, #3
|
||||
; LLC-NEXT: str w8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct5(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i32, i32* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i32 [[TMP0]], -8
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i32 [[X:%.*]], 16
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i32 [[SHR]], 7
|
||||
; OPT-NEXT: [[OR:%.*]] = or i32 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: store i32 [[OR]], i32* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct5:
|
||||
; CHECK: ldr [[REG1:w[0-9]+]],
|
||||
; CHECK-NEXT: bfxil [[REG1]], w1, #16, #3
|
||||
; CHECK-NEXT: str [[REG1]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i32, i32* %y, align 8
|
||||
%and = and i32 %0, -8
|
||||
%shr = lshr i32 %x, 16
|
||||
|
|
@ -104,14 +179,26 @@ entry:
|
|||
|
||||
; Check if we can still catch bfm instruction when we drop some low bits
|
||||
define void @fct6(i32* nocapture %y, i32 %x) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct6:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr w8, [x0]
|
||||
; LLC-NEXT: bfxil w8, w1, #16, #3
|
||||
; LLC-NEXT: lsr w8, w8, #2
|
||||
; LLC-NEXT: str w8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct6(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i32, i32* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i32 [[TMP0]], -8
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i32 [[X:%.*]], 16
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i32 [[SHR]], 7
|
||||
; OPT-NEXT: [[OR:%.*]] = or i32 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: [[SHR1:%.*]] = lshr i32 [[OR]], 2
|
||||
; OPT-NEXT: store i32 [[SHR1]], i32* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct6:
|
||||
; CHECK: ldr [[REG1:w[0-9]+]],
|
||||
; CHECK-NEXT: bfxil [[REG1]], w1, #16, #3
|
||||
; lsr is an alias of ubfm
|
||||
; CHECK-NEXT: lsr [[REG2:w[0-9]+]], [[REG1]], #2
|
||||
; CHECK-NEXT: str [[REG2]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i32, i32* %y, align 8
|
||||
%and = and i32 %0, -8
|
||||
%shr = lshr i32 %x, 16
|
||||
|
|
@ -125,14 +212,26 @@ entry:
|
|||
|
||||
; Check if we can still catch bfm instruction when we drop some high bits
|
||||
define void @fct7(i32* nocapture %y, i32 %x) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct7:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr w8, [x0]
|
||||
; LLC-NEXT: bfxil w8, w1, #16, #3
|
||||
; LLC-NEXT: lsl w8, w8, #2
|
||||
; LLC-NEXT: str w8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct7(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i32, i32* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i32 [[TMP0]], -8
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i32 [[X:%.*]], 16
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i32 [[SHR]], 7
|
||||
; OPT-NEXT: [[OR:%.*]] = or i32 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: [[SHL:%.*]] = shl i32 [[OR]], 2
|
||||
; OPT-NEXT: store i32 [[SHL]], i32* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct7:
|
||||
; CHECK: ldr [[REG1:w[0-9]+]],
|
||||
; CHECK-NEXT: bfxil [[REG1]], w1, #16, #3
|
||||
; lsl is an alias of ubfm
|
||||
; CHECK-NEXT: lsl [[REG2:w[0-9]+]], [[REG1]], #2
|
||||
; CHECK-NEXT: str [[REG2]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i32, i32* %y, align 8
|
||||
%and = and i32 %0, -8
|
||||
%shr = lshr i32 %x, 16
|
||||
|
|
@ -147,14 +246,26 @@ entry:
|
|||
; Check if we can still catch bfm instruction when we drop some low bits
|
||||
; (i64 version)
|
||||
define void @fct8(i64* nocapture %y, i64 %x) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct8:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr x8, [x0]
|
||||
; LLC-NEXT: bfxil x8, x1, #16, #3
|
||||
; LLC-NEXT: lsr x8, x8, #2
|
||||
; LLC-NEXT: str x8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct8(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i64, i64* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i64 [[TMP0]], -8
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i64 [[X:%.*]], 16
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i64 [[SHR]], 7
|
||||
; OPT-NEXT: [[OR:%.*]] = or i64 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: [[SHR1:%.*]] = lshr i64 [[OR]], 2
|
||||
; OPT-NEXT: store i64 [[SHR1]], i64* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct8:
|
||||
; CHECK: ldr [[REG1:x[0-9]+]],
|
||||
; CHECK-NEXT: bfxil [[REG1]], x1, #16, #3
|
||||
; lsr is an alias of ubfm
|
||||
; CHECK-NEXT: lsr [[REG2:x[0-9]+]], [[REG1]], #2
|
||||
; CHECK-NEXT: str [[REG2]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i64, i64* %y, align 8
|
||||
%and = and i64 %0, -8
|
||||
%shr = lshr i64 %x, 16
|
||||
|
|
@ -169,14 +280,26 @@ entry:
|
|||
; Check if we can still catch bfm instruction when we drop some high bits
|
||||
; (i64 version)
|
||||
define void @fct9(i64* nocapture %y, i64 %x) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct9:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr x8, [x0]
|
||||
; LLC-NEXT: bfxil x8, x1, #16, #3
|
||||
; LLC-NEXT: lsl x8, x8, #2
|
||||
; LLC-NEXT: str x8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct9(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i64, i64* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i64 [[TMP0]], -8
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i64 [[X:%.*]], 16
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i64 [[SHR]], 7
|
||||
; OPT-NEXT: [[OR:%.*]] = or i64 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: [[SHL:%.*]] = shl i64 [[OR]], 2
|
||||
; OPT-NEXT: store i64 [[SHL]], i64* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct9:
|
||||
; CHECK: ldr [[REG1:x[0-9]+]],
|
||||
; CHECK-NEXT: bfxil [[REG1]], x1, #16, #3
|
||||
; lsr is an alias of ubfm
|
||||
; CHECK-NEXT: lsl [[REG2:x[0-9]+]], [[REG1]], #2
|
||||
; CHECK-NEXT: str [[REG2]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i64, i64* %y, align 8
|
||||
%and = and i64 %0, -8
|
||||
%shr = lshr i64 %x, 16
|
||||
|
|
@ -190,14 +313,25 @@ entry:
|
|||
; Check if we can catch bfm instruction when lsb is 0 (i.e., no lshr)
|
||||
; (i32 version)
|
||||
define void @fct10(i32* nocapture %y, i32 %x) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct10:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr w8, [x0]
|
||||
; LLC-NEXT: bfxil w8, w1, #0, #3
|
||||
; LLC-NEXT: lsl w8, w8, #2
|
||||
; LLC-NEXT: str w8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct10(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i32, i32* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i32 [[TMP0]], -8
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i32 [[X:%.*]], 7
|
||||
; OPT-NEXT: [[OR:%.*]] = or i32 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: [[SHL:%.*]] = shl i32 [[OR]], 2
|
||||
; OPT-NEXT: store i32 [[SHL]], i32* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct10:
|
||||
; CHECK: ldr [[REG1:w[0-9]+]],
|
||||
; CHECK-NEXT: bfxil [[REG1]], w1, #0, #3
|
||||
; lsl is an alias of ubfm
|
||||
; CHECK-NEXT: lsl [[REG2:w[0-9]+]], [[REG1]], #2
|
||||
; CHECK-NEXT: str [[REG2]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i32, i32* %y, align 8
|
||||
%and = and i32 %0, -8
|
||||
%and1 = and i32 %x, 7
|
||||
|
|
@ -210,14 +344,25 @@ entry:
|
|||
; Check if we can catch bfm instruction when lsb is 0 (i.e., no lshr)
|
||||
; (i64 version)
|
||||
define void @fct11(i64* nocapture %y, i64 %x) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct11:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr x8, [x0]
|
||||
; LLC-NEXT: bfxil x8, x1, #0, #3
|
||||
; LLC-NEXT: lsl x8, x8, #2
|
||||
; LLC-NEXT: str x8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct11(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i64, i64* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i64 [[TMP0]], -8
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i64 [[X:%.*]], 7
|
||||
; OPT-NEXT: [[OR:%.*]] = or i64 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: [[SHL:%.*]] = shl i64 [[OR]], 2
|
||||
; OPT-NEXT: store i64 [[SHL]], i64* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct11:
|
||||
; CHECK: ldr [[REG1:x[0-9]+]],
|
||||
; CHECK-NEXT: bfxil [[REG1]], x1, #0, #3
|
||||
; lsl is an alias of ubfm
|
||||
; CHECK-NEXT: lsl [[REG2:x[0-9]+]], [[REG1]], #2
|
||||
; CHECK-NEXT: str [[REG2]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i64, i64* %y, align 8
|
||||
%and = and i64 %0, -8
|
||||
%and1 = and i64 %x, 7
|
||||
|
|
@ -228,9 +373,15 @@ entry:
|
|||
}
|
||||
|
||||
define zeroext i1 @fct12bis(i32 %tmp2) unnamed_addr nounwind ssp align 2 {
|
||||
; CHECK-LABEL: fct12bis:
|
||||
; CHECK-NOT: and
|
||||
; CHECK: ubfx w0, w0, #11, #1
|
||||
; LLC-LABEL: fct12bis:
|
||||
; LLC: // %bb.0:
|
||||
; LLC-NEXT: ubfx w0, w0, #11, #1
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct12bis(
|
||||
; OPT-NEXT: [[AND_I_I:%.*]] = and i32 [[TMP2:%.*]], 2048
|
||||
; OPT-NEXT: [[TOBOOL_I_I:%.*]] = icmp ne i32 [[AND_I_I]], 0
|
||||
; OPT-NEXT: ret i1 [[TOBOOL_I_I]]
|
||||
;
|
||||
%and.i.i = and i32 %tmp2, 2048
|
||||
%tobool.i.i = icmp ne i32 %and.i.i, 0
|
||||
ret i1 %tobool.i.i
|
||||
|
|
@ -239,14 +390,27 @@ define zeroext i1 @fct12bis(i32 %tmp2) unnamed_addr nounwind ssp align 2 {
|
|||
; Check if we can still catch bfm instruction when we drop some high bits
|
||||
; and some low bits
|
||||
define void @fct12(i32* nocapture %y, i32 %x) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct12:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr w8, [x0]
|
||||
; LLC-NEXT: bfxil w8, w1, #16, #3
|
||||
; LLC-NEXT: ubfx w8, w8, #2, #28
|
||||
; LLC-NEXT: str w8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct12(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i32, i32* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i32 [[TMP0]], -8
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i32 [[X:%.*]], 16
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i32 [[SHR]], 7
|
||||
; OPT-NEXT: [[OR:%.*]] = or i32 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: [[SHL:%.*]] = shl i32 [[OR]], 2
|
||||
; OPT-NEXT: [[SHR2:%.*]] = lshr i32 [[SHL]], 4
|
||||
; OPT-NEXT: store i32 [[SHR2]], i32* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct12:
|
||||
; CHECK: ldr [[REG1:w[0-9]+]],
|
||||
; CHECK-NEXT: bfxil [[REG1]], w1, #16, #3
|
||||
; lsr is an alias of ubfm
|
||||
; CHECK-NEXT: ubfx [[REG2:w[0-9]+]], [[REG1]], #2, #28
|
||||
; CHECK-NEXT: str [[REG2]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i32, i32* %y, align 8
|
||||
%and = and i32 %0, -8
|
||||
%shr = lshr i32 %x, 16
|
||||
|
|
@ -262,14 +426,27 @@ entry:
|
|||
; and some low bits
|
||||
; (i64 version)
|
||||
define void @fct13(i64* nocapture %y, i64 %x) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct13:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr x8, [x0]
|
||||
; LLC-NEXT: bfxil x8, x1, #16, #3
|
||||
; LLC-NEXT: ubfx x8, x8, #2, #60
|
||||
; LLC-NEXT: str x8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct13(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i64, i64* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i64 [[TMP0]], -8
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i64 [[X:%.*]], 16
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i64 [[SHR]], 7
|
||||
; OPT-NEXT: [[OR:%.*]] = or i64 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: [[SHL:%.*]] = shl i64 [[OR]], 2
|
||||
; OPT-NEXT: [[SHR2:%.*]] = lshr i64 [[SHL]], 4
|
||||
; OPT-NEXT: store i64 [[SHR2]], i64* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct13:
|
||||
; CHECK: ldr [[REG1:x[0-9]+]],
|
||||
; CHECK-NEXT: bfxil [[REG1]], x1, #16, #3
|
||||
; lsr is an alias of ubfm
|
||||
; CHECK-NEXT: ubfx [[REG2:x[0-9]+]], [[REG1]], #2, #60
|
||||
; CHECK-NEXT: str [[REG2]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i64, i64* %y, align 8
|
||||
%and = and i64 %0, -8
|
||||
%shr = lshr i64 %x, 16
|
||||
|
|
@ -285,17 +462,34 @@ entry:
|
|||
; Check if we can still catch bfm instruction when we drop some high bits
|
||||
; and some low bits
|
||||
define void @fct14(i32* nocapture %y, i32 %x, i32 %x1) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct14:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr w8, [x0]
|
||||
; LLC-NEXT: bfxil w8, w1, #16, #8
|
||||
; LLC-NEXT: lsr w8, w8, #4
|
||||
; LLC-NEXT: bfxil w8, w2, #5, #3
|
||||
; LLC-NEXT: lsl w8, w8, #2
|
||||
; LLC-NEXT: str w8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct14(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i32, i32* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i32 [[TMP0]], -256
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i32 [[X:%.*]], 16
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i32 [[SHR]], 255
|
||||
; OPT-NEXT: [[OR:%.*]] = or i32 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: [[SHL:%.*]] = lshr i32 [[OR]], 4
|
||||
; OPT-NEXT: [[AND2:%.*]] = and i32 [[SHL]], -8
|
||||
; OPT-NEXT: [[SHR1:%.*]] = lshr i32 [[X1:%.*]], 5
|
||||
; OPT-NEXT: [[AND3:%.*]] = and i32 [[SHR1]], 7
|
||||
; OPT-NEXT: [[OR1:%.*]] = or i32 [[AND2]], [[AND3]]
|
||||
; OPT-NEXT: [[SHL1:%.*]] = shl i32 [[OR1]], 2
|
||||
; OPT-NEXT: store i32 [[SHL1]], i32* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct14:
|
||||
; CHECK: ldr [[REG1:w[0-9]+]],
|
||||
; CHECK-NEXT: bfxil [[REG1]], w1, #16, #8
|
||||
; lsr is an alias of ubfm
|
||||
; CHECK-NEXT: lsr [[REG2:w[0-9]+]], [[REG1]], #4
|
||||
; CHECK-NEXT: bfxil [[REG2]], w2, #5, #3
|
||||
; lsl is an alias of ubfm
|
||||
; CHECK-NEXT: lsl [[REG3:w[0-9]+]], [[REG2]], #2
|
||||
; CHECK-NEXT: str [[REG3]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i32, i32* %y, align 8
|
||||
%and = and i32 %0, -256
|
||||
%shr = lshr i32 %x, 16
|
||||
|
|
@ -315,17 +509,34 @@ entry:
|
|||
; and some low bits
|
||||
; (i64 version)
|
||||
define void @fct15(i64* nocapture %y, i64 %x, i64 %x1) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct15:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr x8, [x0]
|
||||
; LLC-NEXT: bfxil x8, x1, #16, #8
|
||||
; LLC-NEXT: lsr x8, x8, #4
|
||||
; LLC-NEXT: bfxil x8, x2, #5, #3
|
||||
; LLC-NEXT: lsl x8, x8, #2
|
||||
; LLC-NEXT: str x8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct15(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i64, i64* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i64 [[TMP0]], -256
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i64 [[X:%.*]], 16
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i64 [[SHR]], 255
|
||||
; OPT-NEXT: [[OR:%.*]] = or i64 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: [[SHL:%.*]] = lshr i64 [[OR]], 4
|
||||
; OPT-NEXT: [[AND2:%.*]] = and i64 [[SHL]], -8
|
||||
; OPT-NEXT: [[SHR1:%.*]] = lshr i64 [[X1:%.*]], 5
|
||||
; OPT-NEXT: [[AND3:%.*]] = and i64 [[SHR1]], 7
|
||||
; OPT-NEXT: [[OR1:%.*]] = or i64 [[AND2]], [[AND3]]
|
||||
; OPT-NEXT: [[SHL1:%.*]] = shl i64 [[OR1]], 2
|
||||
; OPT-NEXT: store i64 [[SHL1]], i64* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct15:
|
||||
; CHECK: ldr [[REG1:x[0-9]+]],
|
||||
; CHECK-NEXT: bfxil [[REG1]], x1, #16, #8
|
||||
; lsr is an alias of ubfm
|
||||
; CHECK-NEXT: lsr [[REG2:x[0-9]+]], [[REG1]], #4
|
||||
; CHECK-NEXT: bfxil [[REG2]], x2, #5, #3
|
||||
; lsl is an alias of ubfm
|
||||
; CHECK-NEXT: lsl [[REG3:x[0-9]+]], [[REG2]], #2
|
||||
; CHECK-NEXT: str [[REG3]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i64, i64* %y, align 8
|
||||
%and = and i64 %0, -256
|
||||
%shr = lshr i64 %x, 16
|
||||
|
|
@ -344,19 +555,32 @@ entry:
|
|||
; Check if we can still catch bfm instruction when we drop some high bits
|
||||
; and some low bits and a masking operation has to be kept
|
||||
define void @fct16(i32* nocapture %y, i32 %x) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct16:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr w8, [x0]
|
||||
; LLC-NEXT: mov w9, #33120
|
||||
; LLC-NEXT: movk w9, #26, lsl #16
|
||||
; LLC-NEXT: and w8, w8, w9
|
||||
; LLC-NEXT: bfxil w8, w1, #16, #3
|
||||
; LLC-NEXT: ubfx w8, w8, #2, #28
|
||||
; LLC-NEXT: str w8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct16(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i32, i32* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i32 [[TMP0]], 1737056
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i32 [[X:%.*]], 16
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i32 [[SHR]], 7
|
||||
; OPT-NEXT: [[OR:%.*]] = or i32 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: [[SHL:%.*]] = shl i32 [[OR]], 2
|
||||
; OPT-NEXT: [[SHR2:%.*]] = lshr i32 [[SHL]], 4
|
||||
; OPT-NEXT: store i32 [[SHR2]], i32* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct16:
|
||||
; CHECK: ldr [[REG1:w[0-9]+]],
|
||||
; Create the constant
|
||||
; CHECK: mov [[REGCST:w[0-9]+]], #33120
|
||||
; CHECK: movk [[REGCST]], #26, lsl #16
|
||||
; Do the masking
|
||||
; CHECK: and [[REG2:w[0-9]+]], [[REG1]], [[REGCST]]
|
||||
; CHECK-NEXT: bfxil [[REG2]], w1, #16, #3
|
||||
; lsr is an alias of ubfm
|
||||
; CHECK-NEXT: ubfx [[REG3:w[0-9]+]], [[REG2]], #2, #28
|
||||
; CHECK-NEXT: str [[REG3]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i32, i32* %y, align 8
|
||||
%and = and i32 %0, 1737056
|
||||
%shr = lshr i32 %x, 16
|
||||
|
|
@ -373,19 +597,32 @@ entry:
|
|||
; and some low bits and a masking operation has to be kept
|
||||
; (i64 version)
|
||||
define void @fct17(i64* nocapture %y, i64 %x) nounwind optsize inlinehint ssp {
|
||||
; LLC-LABEL: fct17:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: ldr x8, [x0]
|
||||
; LLC-NEXT: mov w9, #33120
|
||||
; LLC-NEXT: movk w9, #26, lsl #16
|
||||
; LLC-NEXT: and x8, x8, x9
|
||||
; LLC-NEXT: bfxil x8, x1, #16, #3
|
||||
; LLC-NEXT: ubfx x8, x8, #2, #60
|
||||
; LLC-NEXT: str x8, [x0]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct17(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i64, i64* [[Y:%.*]], align 8
|
||||
; OPT-NEXT: [[AND:%.*]] = and i64 [[TMP0]], 1737056
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i64 [[X:%.*]], 16
|
||||
; OPT-NEXT: [[AND1:%.*]] = and i64 [[SHR]], 7
|
||||
; OPT-NEXT: [[OR:%.*]] = or i64 [[AND]], [[AND1]]
|
||||
; OPT-NEXT: [[SHL:%.*]] = shl i64 [[OR]], 2
|
||||
; OPT-NEXT: [[SHR2:%.*]] = lshr i64 [[SHL]], 4
|
||||
; OPT-NEXT: store i64 [[SHR2]], i64* [[Y]], align 8
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
; CHECK-LABEL: fct17:
|
||||
; CHECK: ldr [[REG1:x[0-9]+]],
|
||||
; Create the constant
|
||||
; CHECK: mov w[[REGCST:[0-9]+]], #33120
|
||||
; CHECK: movk w[[REGCST]], #26, lsl #16
|
||||
; Do the masking
|
||||
; CHECK: and [[REG2:x[0-9]+]], [[REG1]], x[[REGCST]]
|
||||
; CHECK-NEXT: bfxil [[REG2]], x1, #16, #3
|
||||
; lsr is an alias of ubfm
|
||||
; CHECK-NEXT: ubfx [[REG3:x[0-9]+]], [[REG2]], #2, #60
|
||||
; CHECK-NEXT: str [[REG3]],
|
||||
; CHECK-NEXT: ret
|
||||
%0 = load i64, i64* %y, align 8
|
||||
%and = and i64 %0, 1737056
|
||||
%shr = lshr i64 %x, 16
|
||||
|
|
@ -398,8 +635,17 @@ entry:
|
|||
}
|
||||
|
||||
define i64 @fct18(i32 %xor72) nounwind ssp {
|
||||
; CHECK-LABEL: fct18:
|
||||
; CHECK: ubfx x0, x0, #9, #8
|
||||
; LLC-LABEL: fct18:
|
||||
; LLC: // %bb.0:
|
||||
; LLC-NEXT: // kill: def $w0 killed $w0 def $x0
|
||||
; LLC-NEXT: ubfx x0, x0, #9, #8
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct18(
|
||||
; OPT-NEXT: [[SHR81:%.*]] = lshr i32 [[XOR72:%.*]], 9
|
||||
; OPT-NEXT: [[CONV82:%.*]] = zext i32 [[SHR81]] to i64
|
||||
; OPT-NEXT: [[RESULT:%.*]] = and i64 [[CONV82]], 255
|
||||
; OPT-NEXT: ret i64 [[RESULT]]
|
||||
;
|
||||
%shr81 = lshr i32 %xor72, 9
|
||||
%conv82 = zext i32 %shr81 to i64
|
||||
%result = and i64 %conv82, 255
|
||||
|
|
@ -411,7 +657,78 @@ define i64 @fct18(i32 %xor72) nounwind ssp {
|
|||
|
||||
; Function Attrs: nounwind readonly ssp
|
||||
define i32 @fct19(i64 %arg1) nounwind readonly ssp {
|
||||
; CHECK-LABEL: fct19:
|
||||
; LLC-LABEL: fct19:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: lsr x8, x0, #48
|
||||
; LLC-NEXT: cbz x8, .LBB22_2
|
||||
; LLC-NEXT: // %bb.1: // %if.then
|
||||
; LLC-NEXT: adrp x9, first_ones
|
||||
; LLC-NEXT: add x9, x9, :lo12:first_ones
|
||||
; LLC-NEXT: ldrb w0, [x9, x8]
|
||||
; LLC-NEXT: ret
|
||||
; LLC-NEXT: .LBB22_2: // %if.end
|
||||
; LLC-NEXT: ubfx x8, x0, #32, #16
|
||||
; LLC-NEXT: cbz w8, .LBB22_4
|
||||
; LLC-NEXT: // %bb.3: // %if.then7
|
||||
; LLC-NEXT: adrp x9, first_ones
|
||||
; LLC-NEXT: add x9, x9, :lo12:first_ones
|
||||
; LLC-NEXT: ldrb w8, [x9, x8]
|
||||
; LLC-NEXT: add w0, w8, #16 // =16
|
||||
; LLC-NEXT: ret
|
||||
; LLC-NEXT: .LBB22_4: // %if.end13
|
||||
; LLC-NEXT: ubfx x8, x0, #16, #16
|
||||
; LLC-NEXT: cbz w8, .LBB22_6
|
||||
; LLC-NEXT: // %bb.5: // %if.then17
|
||||
; LLC-NEXT: adrp x9, first_ones
|
||||
; LLC-NEXT: add x9, x9, :lo12:first_ones
|
||||
; LLC-NEXT: ldrb w8, [x9, x8]
|
||||
; LLC-NEXT: add w0, w8, #32 // =32
|
||||
; LLC-NEXT: ret
|
||||
; LLC-NEXT: .LBB22_6:
|
||||
; LLC-NEXT: mov w0, #64
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct19(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[X_SROA_1_0_EXTRACT_SHIFT:%.*]] = lshr i64 [[ARG1:%.*]], 16
|
||||
; OPT-NEXT: [[X_SROA_1_0_EXTRACT_TRUNC:%.*]] = trunc i64 [[X_SROA_1_0_EXTRACT_SHIFT]] to i16
|
||||
; OPT-NEXT: [[X_SROA_5_0_EXTRACT_SHIFT:%.*]] = lshr i64 [[ARG1]], 48
|
||||
; OPT-NEXT: [[TOBOOL:%.*]] = icmp eq i64 [[X_SROA_5_0_EXTRACT_SHIFT]], 0
|
||||
; OPT-NEXT: br i1 [[TOBOOL]], label [[IF_END:%.*]], label [[IF_THEN:%.*]]
|
||||
; OPT: if.then:
|
||||
; OPT-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds [65536 x i8], [65536 x i8]* @first_ones, i64 0, i64 [[X_SROA_5_0_EXTRACT_SHIFT]]
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i8, i8* [[ARRAYIDX3]], align 1
|
||||
; OPT-NEXT: [[CONV:%.*]] = zext i8 [[TMP0]] to i32
|
||||
; OPT-NEXT: br label [[RETURN:%.*]]
|
||||
; OPT: if.end:
|
||||
; OPT-NEXT: [[TMP1:%.*]] = lshr i64 [[ARG1]], 32
|
||||
; OPT-NEXT: [[X_SROA_3_0_EXTRACT_TRUNC:%.*]] = trunc i64 [[TMP1]] to i16
|
||||
; OPT-NEXT: [[TOBOOL6:%.*]] = icmp eq i16 [[X_SROA_3_0_EXTRACT_TRUNC]], 0
|
||||
; OPT-NEXT: br i1 [[TOBOOL6]], label [[IF_END13:%.*]], label [[IF_THEN7:%.*]]
|
||||
; OPT: if.then7:
|
||||
; OPT-NEXT: [[TMP2:%.*]] = lshr i64 [[ARG1]], 32
|
||||
; OPT-NEXT: [[IDXPROM10:%.*]] = and i64 [[TMP2]], 65535
|
||||
; OPT-NEXT: [[ARRAYIDX11:%.*]] = getelementptr inbounds [65536 x i8], [65536 x i8]* @first_ones, i64 0, i64 [[IDXPROM10]]
|
||||
; OPT-NEXT: [[TMP3:%.*]] = load i8, i8* [[ARRAYIDX11]], align 1
|
||||
; OPT-NEXT: [[CONV12:%.*]] = zext i8 [[TMP3]] to i32
|
||||
; OPT-NEXT: [[ADD:%.*]] = add nsw i32 [[CONV12]], 16
|
||||
; OPT-NEXT: br label [[RETURN]]
|
||||
; OPT: if.end13:
|
||||
; OPT-NEXT: [[TMP4:%.*]] = lshr i64 [[ARG1]], 16
|
||||
; OPT-NEXT: [[TMP5:%.*]] = trunc i64 [[TMP4]] to i16
|
||||
; OPT-NEXT: [[TOBOOL16:%.*]] = icmp eq i16 [[TMP5]], 0
|
||||
; OPT-NEXT: br i1 [[TOBOOL16]], label [[RETURN]], label [[IF_THEN17:%.*]]
|
||||
; OPT: if.then17:
|
||||
; OPT-NEXT: [[TMP6:%.*]] = lshr i64 [[ARG1]], 16
|
||||
; OPT-NEXT: [[IDXPROM20:%.*]] = and i64 [[TMP6]], 65535
|
||||
; OPT-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds [65536 x i8], [65536 x i8]* @first_ones, i64 0, i64 [[IDXPROM20]]
|
||||
; OPT-NEXT: [[TMP7:%.*]] = load i8, i8* [[ARRAYIDX21]], align 1
|
||||
; OPT-NEXT: [[CONV22:%.*]] = zext i8 [[TMP7]] to i32
|
||||
; OPT-NEXT: [[ADD23:%.*]] = add nsw i32 [[CONV22]], 32
|
||||
; OPT-NEXT: br label [[RETURN]]
|
||||
; OPT: return:
|
||||
; OPT-NEXT: [[RETVAL_0:%.*]] = phi i32 [ [[CONV]], [[IF_THEN]] ], [ [[ADD]], [[IF_THEN7]] ], [ [[ADD23]], [[IF_THEN17]] ], [ 64, [[IF_END13]] ]
|
||||
; OPT-NEXT: ret i32 [[RETVAL_0]]
|
||||
;
|
||||
entry:
|
||||
%x.sroa.1.0.extract.shift = lshr i64 %arg1, 16
|
||||
%x.sroa.1.0.extract.trunc = trunc i64 %x.sroa.1.0.extract.shift to i16
|
||||
|
|
@ -426,22 +743,14 @@ if.then: ; preds = %entry
|
|||
%conv = zext i8 %0 to i32
|
||||
br label %return
|
||||
|
||||
; OPT-LABEL: if.end
|
||||
if.end: ; preds = %entry
|
||||
; OPT: lshr
|
||||
; CHECK: ubfx [[REG1:x[0-9]+]], [[REG2:x[0-9]+]], #32, #16
|
||||
%x.sroa.3.0.extract.trunc = trunc i64 %x.sroa.3.0.extract.shift to i16
|
||||
%tobool6 = icmp eq i16 %x.sroa.3.0.extract.trunc, 0
|
||||
; CHECK: cbz
|
||||
br i1 %tobool6, label %if.end13, label %if.then7
|
||||
|
||||
; OPT-LABEL: if.then7
|
||||
if.then7: ; preds = %if.end
|
||||
; OPT: lshr
|
||||
; "and" should be combined to "ubfm" while "ubfm" should be removed by cse.
|
||||
; So neither of them should be in the assemble code.
|
||||
; CHECK-NOT: and
|
||||
; CHECK-NOT: ubfm
|
||||
; "and" should be combined to "ubfm" while "ubfm" should be removed by cse.
|
||||
; So neither of them should be in the assemble code.
|
||||
%idxprom10 = and i64 %x.sroa.3.0.extract.shift, 65535
|
||||
%arrayidx11 = getelementptr inbounds [65536 x i8], [65536 x i8]* @first_ones, i64 0, i64 %idxprom10
|
||||
%1 = load i8, i8* %arrayidx11, align 1
|
||||
|
|
@ -449,22 +758,13 @@ if.then7: ; preds = %if.end
|
|||
%add = add nsw i32 %conv12, 16
|
||||
br label %return
|
||||
|
||||
; OPT-LABEL: if.end13
|
||||
if.end13: ; preds = %if.end
|
||||
; OPT: lshr
|
||||
; OPT: trunc
|
||||
; CHECK: ubfx [[REG3:x[0-9]+]], [[REG4:x[0-9]+]], #16, #16
|
||||
%tobool16 = icmp eq i16 %x.sroa.1.0.extract.trunc, 0
|
||||
; CHECK: cbz
|
||||
br i1 %tobool16, label %return, label %if.then17
|
||||
|
||||
; OPT-LABEL: if.then17
|
||||
if.then17: ; preds = %if.end13
|
||||
; OPT: lshr
|
||||
; "and" should be combined to "ubfm" while "ubfm" should be removed by cse.
|
||||
; So neither of them should be in the assemble code.
|
||||
; CHECK-NOT: and
|
||||
; CHECK-NOT: ubfm
|
||||
; "and" should be combined to "ubfm" while "ubfm" should be removed by cse.
|
||||
; So neither of them should be in the assemble code.
|
||||
%idxprom20 = and i64 %x.sroa.1.0.extract.shift, 65535
|
||||
%arrayidx21 = getelementptr inbounds [65536 x i8], [65536 x i8]* @first_ones, i64 0, i64 %idxprom20
|
||||
%2 = load i8, i8* %arrayidx21, align 1
|
||||
|
|
@ -473,39 +773,75 @@ if.then17: ; preds = %if.end13
|
|||
br label %return
|
||||
|
||||
return: ; preds = %if.end13, %if.then17, %if.then7, %if.then
|
||||
; CHECK: ret
|
||||
%retval.0 = phi i32 [ %conv, %if.then ], [ %add, %if.then7 ], [ %add23, %if.then17 ], [ 64, %if.end13 ]
|
||||
ret i32 %retval.0
|
||||
}
|
||||
|
||||
; Make sure we do not assert if the immediate in and is bigger than i64.
|
||||
; PR19503.
|
||||
; OPT-LABEL: @fct20
|
||||
; OPT: lshr
|
||||
; OPT-NOT: lshr
|
||||
; OPT: ret
|
||||
; CHECK-LABEL: fct20:
|
||||
; CHECK: ret
|
||||
define i80 @fct20(i128 %a, i128 %b) {
|
||||
; LLC-LABEL: fct20:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: mov x12, #11776
|
||||
; LLC-NEXT: movk x12, #25856, lsl #16
|
||||
; LLC-NEXT: movk x12, #11077, lsl #32
|
||||
; LLC-NEXT: extr x8, x1, x0, #18
|
||||
; LLC-NEXT: lsr x9, x1, #18
|
||||
; LLC-NEXT: orr x10, x2, x3
|
||||
; LLC-NEXT: mov w11, #26220
|
||||
; LLC-NEXT: movk x12, #45, lsl #48
|
||||
; LLC-NEXT: and x11, x9, x11
|
||||
; LLC-NEXT: and x12, x8, x12
|
||||
; LLC-NEXT: cmp x10, #0 // =0
|
||||
; LLC-NEXT: csel x0, x12, x8, eq
|
||||
; LLC-NEXT: csel x1, x11, x9, eq
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct20(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i128 [[A:%.*]], 18
|
||||
; OPT-NEXT: [[CONV:%.*]] = trunc i128 [[SHR]] to i80
|
||||
; OPT-NEXT: [[TOBOOL:%.*]] = icmp eq i128 [[B:%.*]], 0
|
||||
; OPT-NEXT: br i1 [[TOBOOL]], label [[THEN:%.*]], label [[END:%.*]]
|
||||
; OPT: then:
|
||||
; OPT-NEXT: [[AND:%.*]] = and i128 [[SHR]], 483673642326615442599424
|
||||
; OPT-NEXT: [[CONV2:%.*]] = trunc i128 [[AND]] to i80
|
||||
; OPT-NEXT: br label [[END]]
|
||||
; OPT: end:
|
||||
; OPT-NEXT: [[CONV3:%.*]] = phi i80 [ [[CONV]], [[ENTRY:%.*]] ], [ [[CONV2]], [[THEN]] ]
|
||||
; OPT-NEXT: ret i80 [[CONV3]]
|
||||
;
|
||||
entry:
|
||||
%shr = lshr i128 %a, 18
|
||||
%conv = trunc i128 %shr to i80
|
||||
%tobool = icmp eq i128 %b, 0
|
||||
br i1 %tobool, label %then, label %end
|
||||
then:
|
||||
then:
|
||||
%and = and i128 %shr, 483673642326615442599424
|
||||
%conv2 = trunc i128 %and to i80
|
||||
br label %end
|
||||
end:
|
||||
%conv3 = phi i80 [%conv, %entry], [%conv2, %then]
|
||||
%conv3 = phi i80 [%conv, %entry], [%conv2, %then]
|
||||
ret i80 %conv3
|
||||
}
|
||||
|
||||
; Check if we can still catch UBFX when "AND" is used by SHL.
|
||||
; CHECK-LABEL: fct21:
|
||||
; CHECK: ubfx
|
||||
@arr = external global [8 x [64 x i64]]
|
||||
define i64 @fct21(i64 %x) {
|
||||
; LLC-LABEL: fct21:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: adrp x9, arr
|
||||
; LLC-NEXT: ubfx x8, x0, #4, #4
|
||||
; LLC-NEXT: add x9, x9, :lo12:arr
|
||||
; LLC-NEXT: ldr x0, [x9, x8, lsl #3]
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @fct21(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[SHR:%.*]] = lshr i64 [[X:%.*]], 4
|
||||
; OPT-NEXT: [[AND:%.*]] = and i64 [[SHR]], 15
|
||||
; OPT-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [8 x [64 x i64]], [8 x [64 x i64]]* @arr, i64 0, i64 0, i64 [[AND]]
|
||||
; OPT-NEXT: [[TMP0:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
|
||||
; OPT-NEXT: ret i64 [[TMP0]]
|
||||
;
|
||||
entry:
|
||||
%shr = lshr i64 %x, 4
|
||||
%and = and i64 %shr, 15
|
||||
|
|
@ -515,18 +851,30 @@ entry:
|
|||
}
|
||||
|
||||
define i16 @test_ignored_rightbits(i32 %dst, i32 %in) {
|
||||
; CHECK-LABEL: test_ignored_rightbits:
|
||||
|
||||
; LLC-LABEL: test_ignored_rightbits:
|
||||
; LLC: // %bb.0:
|
||||
; LLC-NEXT: and w0, w0, #0x7
|
||||
; LLC-NEXT: bfi w0, w1, #3, #4
|
||||
; LLC-NEXT: bfi w0, w0, #8, #7
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @test_ignored_rightbits(
|
||||
; OPT-NEXT: [[POSITIONED_FIELD:%.*]] = shl i32 [[IN:%.*]], 3
|
||||
; OPT-NEXT: [[POSITIONED_MASKED_FIELD:%.*]] = and i32 [[POSITIONED_FIELD]], 120
|
||||
; OPT-NEXT: [[MASKED_DST:%.*]] = and i32 [[DST:%.*]], 7
|
||||
; OPT-NEXT: [[INSERTION:%.*]] = or i32 [[MASKED_DST]], [[POSITIONED_MASKED_FIELD]]
|
||||
; OPT-NEXT: [[SHL16:%.*]] = shl i32 [[INSERTION]], 8
|
||||
; OPT-NEXT: [[OR18:%.*]] = or i32 [[SHL16]], [[INSERTION]]
|
||||
; OPT-NEXT: [[CONV19:%.*]] = trunc i32 [[OR18]] to i16
|
||||
; OPT-NEXT: ret i16 [[CONV19]]
|
||||
;
|
||||
%positioned_field = shl i32 %in, 3
|
||||
%positioned_masked_field = and i32 %positioned_field, 120
|
||||
%masked_dst = and i32 %dst, 7
|
||||
%insertion = or i32 %masked_dst, %positioned_masked_field
|
||||
; CHECK: {{bfm|bfi|bfxil}}
|
||||
|
||||
%shl16 = shl i32 %insertion, 8
|
||||
%or18 = or i32 %shl16, %insertion
|
||||
%conv19 = trunc i32 %or18 to i16
|
||||
; CHECK: bfi {{w[0-9]+}}, {{w[0-9]+}}, #8, #7
|
||||
|
||||
ret i16 %conv19
|
||||
}
|
||||
|
|
@ -534,12 +882,37 @@ define i16 @test_ignored_rightbits(i32 %dst, i32 %in) {
|
|||
; The following test excercises the case where we have a BFI
|
||||
; instruction with the same input in both operands. We need to
|
||||
; track the useful bits through both operands.
|
||||
; CHECK-LABEL: sameOperandBFI
|
||||
; CHECK: lsr
|
||||
; CHECK: and
|
||||
; CHECK: bfi
|
||||
; CHECK: bfi
|
||||
define void @sameOperandBFI(i64 %src, i64 %src2, i16 *%ptr) {
|
||||
; LLC-LABEL: sameOperandBFI:
|
||||
; LLC: // %bb.0: // %entry
|
||||
; LLC-NEXT: cbnz wzr, .LBB26_2
|
||||
; LLC-NEXT: // %bb.1: // %if.else
|
||||
; LLC-NEXT: lsr x8, x0, #47
|
||||
; LLC-NEXT: and w9, w1, #0x3
|
||||
; LLC-NEXT: bfi w9, w8, #2, #2
|
||||
; LLC-NEXT: bfi w9, w9, #4, #4
|
||||
; LLC-NEXT: strh w9, [x2]
|
||||
; LLC-NEXT: .LBB26_2: // %end
|
||||
; LLC-NEXT: ret
|
||||
; OPT-LABEL: @sameOperandBFI(
|
||||
; OPT-NEXT: entry:
|
||||
; OPT-NEXT: [[SHR47:%.*]] = lshr i64 [[SRC:%.*]], 47
|
||||
; OPT-NEXT: [[SRC2_TRUNC:%.*]] = trunc i64 [[SRC2:%.*]] to i32
|
||||
; OPT-NEXT: br i1 undef, label [[END:%.*]], label [[IF_ELSE:%.*]]
|
||||
; OPT: if.else:
|
||||
; OPT-NEXT: [[AND3:%.*]] = and i32 [[SRC2_TRUNC]], 3
|
||||
; OPT-NEXT: [[SHL2:%.*]] = shl nuw nsw i64 [[SHR47]], 2
|
||||
; OPT-NEXT: [[SHL2_TRUNC:%.*]] = trunc i64 [[SHL2]] to i32
|
||||
; OPT-NEXT: [[AND12:%.*]] = and i32 [[SHL2_TRUNC]], 12
|
||||
; OPT-NEXT: [[BFISOURCE:%.*]] = or i32 [[AND3]], [[AND12]]
|
||||
; OPT-NEXT: [[BFIRHS:%.*]] = shl nuw nsw i32 [[BFISOURCE]], 4
|
||||
; OPT-NEXT: [[BFI:%.*]] = or i32 [[BFIRHS]], [[BFISOURCE]]
|
||||
; OPT-NEXT: [[BFITRUNC:%.*]] = trunc i32 [[BFI]] to i16
|
||||
; OPT-NEXT: store i16 [[BFITRUNC]], i16* [[PTR:%.*]], align 4
|
||||
; OPT-NEXT: br label [[END]]
|
||||
; OPT: end:
|
||||
; OPT-NEXT: ret void
|
||||
;
|
||||
entry:
|
||||
%shr47 = lshr i64 %src, 47
|
||||
%src2.trunc = trunc i64 %src2 to i32
|
||||
|
|
|
|||
|
|
@ -206,6 +206,7 @@ def build_function_body_dictionary_for_triple(args, raw_tool_output, triple, pre
|
|||
'i686': (scrub_asm_x86, ASM_FUNCTION_X86_RE),
|
||||
'x86': (scrub_asm_x86, ASM_FUNCTION_X86_RE),
|
||||
'i386': (scrub_asm_x86, ASM_FUNCTION_X86_RE),
|
||||
'arm64-eabi': (scrub_asm_arm_eabi, ASM_FUNCTION_AARCH64_RE),
|
||||
'aarch64': (scrub_asm_arm_eabi, ASM_FUNCTION_AARCH64_RE),
|
||||
'r600': (scrub_asm_amdgpu, ASM_FUNCTION_AMDGPU_RE),
|
||||
'amdgcn': (scrub_asm_amdgpu, ASM_FUNCTION_AMDGPU_RE),
|
||||
|
|
|
|||
Loading…
Reference in New Issue