[AArch64] Optimize floating point materialization
This patch changes isFPImmLegal to return if the value can be enconded
as the immediate operand of a logical instruction besides checking if
for immediate field for fmov.
This optimizes some floating point materization, inclusive values
used on isinf lowering.
Reviewed By: rengolin, efriedma, evandro
Differential Revision: https://reviews.llvm.org/D57044
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@352866 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Target/AArch64/AArch64FastISel.cpp b/lib/Target/AArch64/AArch64FastISel.cpp
index a63ef54..8b033ee 100644
--- a/lib/Target/AArch64/AArch64FastISel.cpp
+++ b/lib/Target/AArch64/AArch64FastISel.cpp
@@ -405,10 +405,9 @@
bool Is64Bit = (VT == MVT::f64);
// This checks to see if we can use FMOV instructions to materialize
// a constant, otherwise we have to materialize via the constant pool.
- if (TLI.isFPImmLegal(Val, VT)) {
- int Imm =
- Is64Bit ? AArch64_AM::getFP64Imm(Val) : AArch64_AM::getFP32Imm(Val);
- assert((Imm != -1) && "Cannot encode floating-point constant.");
+ int Imm =
+ Is64Bit ? AArch64_AM::getFP64Imm(Val) : AArch64_AM::getFP32Imm(Val);
+ if (Imm != -1) {
unsigned Opc = Is64Bit ? AArch64::FMOVDi : AArch64::FMOVSi;
return fastEmitInst_i(Opc, TLI.getRegClassFor(VT), Imm);
}
diff --git a/lib/Target/AArch64/AArch64ISelLowering.cpp b/lib/Target/AArch64/AArch64ISelLowering.cpp
index 03a3dac..7198cdc 100644
--- a/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -5424,34 +5424,30 @@
}
bool AArch64TargetLowering::isFPImmLegal(const APFloat &Imm, EVT VT) const {
- // We can materialize #0.0 as fmov $Rd, XZR for 64-bit and 32-bit cases.
- // FIXME: We should be able to handle f128 as well with a clever lowering.
- if (Imm.isPosZero() && (VT == MVT::f64 || VT == MVT::f32 ||
- (VT == MVT::f16 && Subtarget->hasFullFP16()))) {
- LLVM_DEBUG(dbgs() << "Legal " << VT.getEVTString() << " imm value: 0\n");
- return true;
- }
-
bool IsLegal = false;
- SmallString<128> ImmStrVal;
- Imm.toString(ImmStrVal);
-
+ // We can materialize #0.0 as fmov $Rd, XZR for 64-bit, 32-bit cases, and
+ // 16-bit case when target has full fp16 support.
+ // FIXME: We should be able to handle f128 as well with a clever lowering.
+ const APInt ImmInt = Imm.bitcastToAPInt();
if (VT == MVT::f64)
- IsLegal = AArch64_AM::getFP64Imm(Imm) != -1;
+ IsLegal = AArch64_AM::getFP64Imm(ImmInt) != -1 || Imm.isPosZero();
else if (VT == MVT::f32)
- IsLegal = AArch64_AM::getFP32Imm(Imm) != -1;
+ IsLegal = AArch64_AM::getFP32Imm(ImmInt) != -1 || Imm.isPosZero();
else if (VT == MVT::f16 && Subtarget->hasFullFP16())
- IsLegal = AArch64_AM::getFP16Imm(Imm) != -1;
+ IsLegal = AArch64_AM::getFP16Imm(ImmInt) != -1 || Imm.isPosZero();
+ // TODO: fmov h0, w0 is also legal, however on't have an isel pattern to
+ // generate that fmov.
- if (IsLegal) {
- LLVM_DEBUG(dbgs() << "Legal " << VT.getEVTString()
- << " imm value: " << ImmStrVal << "\n");
- return true;
- }
+ // If we can not materialize in immediate field for fmov, check if the
+ // value can be encoded as the immediate operand of a logical instruction.
+ // The immediate value will be created with either MOVZ, MOVN, or ORR.
+ if (!IsLegal && (VT == MVT::f64 || VT == MVT::f32))
+ IsLegal = AArch64_AM::isAnyMOVWMovAlias(ImmInt.getZExtValue(),
+ VT.getSizeInBits());
- LLVM_DEBUG(dbgs() << "Illegal " << VT.getEVTString()
- << " imm value: " << ImmStrVal << "\n");
- return false;
+ LLVM_DEBUG(dbgs() << (IsLegal ? "Legal " : "Illegal ") << VT.getEVTString()
+ << " imm value: "; Imm.dump(););
+ return IsLegal;
}
//===----------------------------------------------------------------------===//
diff --git a/test/CodeGen/AArch64/fabs.ll b/test/CodeGen/AArch64/fabs.ll
index cd315ab..58f047a 100644
--- a/test/CodeGen/AArch64/fabs.ll
+++ b/test/CodeGen/AArch64/fabs.ll
@@ -22,11 +22,11 @@
define float @still_not_fabs(float %x) #0 {
; CHECK-LABEL: still_not_fabs:
; CHECK: // %bb.0:
-; CHECK-NEXT: adrp x8, .LCPI1_0
-; CHECK-NEXT: ldr s1, [x8, :lo12:.LCPI1_0]
-; CHECK-NEXT: fneg s2, s0
-; CHECK-NEXT: fcmp s0, s1
-; CHECK-NEXT: fcsel s0, s0, s2, ge
+; CHECK-NEXT: orr w8, wzr, #0x80000000
+; CHECK-NEXT: fmov s2, w8
+; CHECK-NEXT: fneg s1, s0
+; CHECK-NEXT: fcmp s0, s2
+; CHECK-NEXT: fcsel s0, s0, s1, ge
; CHECK-NEXT: ret
%cmp = fcmp nnan oge float %x, -0.0
%sub = fsub nnan float -0.0, %x
diff --git a/test/CodeGen/AArch64/fadd-combines.ll b/test/CodeGen/AArch64/fadd-combines.ll
index 7332101..a204684 100644
--- a/test/CodeGen/AArch64/fadd-combines.ll
+++ b/test/CodeGen/AArch64/fadd-combines.ll
@@ -132,13 +132,13 @@
define float @fadd_const_multiuse_fmf(float %x) {
; CHECK-LABEL: fadd_const_multiuse_fmf:
; CHECK: // %bb.0:
-; CHECK-NEXT: adrp x8, .LCPI10_0
-; CHECK-NEXT: adrp x9, .LCPI10_1
-; CHECK-NEXT: ldr s1, [x8, :lo12:.LCPI10_0]
-; CHECK-NEXT: ldr s2, [x9, :lo12:.LCPI10_1]
-; CHECK-NEXT: fadd s1, s0, s1
-; CHECK-NEXT: fadd s0, s0, s2
-; CHECK-NEXT: fadd s0, s1, s0
+; CHECK-DAG: mov [[W59:w[0-9]+]], #1114374144
+; CHECK-DAG: mov [[W42:w[0-9]+]], #1109917696
+; CHECK-DAG: fmov [[FP59:s[0-9]+]], [[W59]]
+; CHECK-DAG: fmov [[FP42:s[0-9]+]], [[W42]]
+; CHECK-NEXT: fadd [[TMP1:s[0-9]+]], s0, [[FP42]]
+; CHECK-NEXT: fadd [[TMP2:s[0-9]+]], s0, [[FP59]]
+; CHECK-NEXT: fadd s0, [[TMP1]], [[TMP2]]
; CHECK-NEXT: ret
%a1 = fadd float %x, 42.0
%a2 = fadd nsz reassoc float %a1, 17.0
@@ -153,13 +153,13 @@
define float @fadd_const_multiuse_attr(float %x) #0 {
; CHECK-LABEL: fadd_const_multiuse_attr:
; CHECK: // %bb.0:
-; CHECK-NEXT: adrp x9, .LCPI11_1
-; CHECK-NEXT: adrp x8, .LCPI11_0
-; CHECK-NEXT: ldr s1, [x9, :lo12:.LCPI11_1]
-; CHECK-NEXT: ldr s2, [x8, :lo12:.LCPI11_0]
-; CHECK-NEXT: fadd s1, s0, s1
-; CHECK-NEXT: fadd s1, s2, s1
-; CHECK-NEXT: fadd s0, s0, s1
+; CHECK-DAG: mov [[W59:w[0-9]+]], #1114374144
+; CHECK-DAG: mov [[W17:w[0-9]+]], #1109917696
+; CHECK-NEXT: fmov [[FP59:s[0-9]+]], [[W59]]
+; CHECK-NEXT: fmov [[FP17:s[0-9]+]], [[W17]]
+; CHECK-NEXT: fadd [[TMP1:s[0-9]+]], s0, [[FP59]]
+; CHECK-NEXT: fadd [[TMP2:s[0-9]+]], [[FP17]], [[TMP1]]
+; CHECK-NEXT: fadd s0, s0, [[TMP2]]
; CHECK-NEXT: ret
%a1 = fadd float %x, 42.0
%a2 = fadd float %a1, 17.0
diff --git a/test/CodeGen/AArch64/fpimm.ll b/test/CodeGen/AArch64/fpimm.ll
index de15bc0..a09d5d0 100644
--- a/test/CodeGen/AArch64/fpimm.ll
+++ b/test/CodeGen/AArch64/fpimm.ll
@@ -18,8 +18,10 @@
%newval2 = fadd float %val, 128.0
store volatile float %newval2, float* @varf32
-; CHECK-DAG: ldr {{s[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.LCPI0_0
-; TINY-DAG: ldr {{s[0-9]+}}, .LCPI0_0
+; CHECK-DAG: mov [[W128:w[0-9]+]], #1124073472
+; CHECK-DAG: fmov {{s[0-9]+}}, [[W128]]
+; TINY-DAG: mov [[W128:w[0-9]+]], #1124073472
+; TINY-DAG: fmov {{s[0-9]+}}, [[W128]]
; CHECK: ret
; TINY: ret
@@ -38,8 +40,10 @@
%newval2 = fadd double %val, 128.0
store volatile double %newval2, double* @varf64
-; CHECK-DAG: ldr {{d[0-9]+}}, [{{x[0-9]+}}, {{#?}}:lo12:.LCPI1_0
-; TINY-DAG: ldr {{d[0-9]+}}, .LCPI1_0
+; CHECK-DAG: mov [[X128:x[0-9]+]], #4638707616191610880
+; CHECK-DAG: fmov {{d[0-9]+}}, [[X128]]
+; TINY-DAG: mov [[X128:x[0-9]+]], #4638707616191610880
+; TINY-DAG: fmov {{d[0-9]+}}, [[X128]]
; CHECK: ret
; TINY: ret
diff --git a/test/CodeGen/AArch64/isinf.ll b/test/CodeGen/AArch64/isinf.ll
new file mode 100644
index 0000000..e4607d0
--- /dev/null
+++ b/test/CodeGen/AArch64/isinf.ll
@@ -0,0 +1,62 @@
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mattr=+neon,+fullfp16 < %s -o -| FileCheck %s
+
+declare half @llvm.fabs.f16(half)
+declare float @llvm.fabs.f32(float)
+declare double @llvm.fabs.f64(double)
+declare fp128 @llvm.fabs.f128(fp128)
+
+; INFINITY requires loading the constant for _Float16
+define i32 @replace_isinf_call_f16(half %x) {
+; CHECK-LABEL: replace_isinf_call_f16:
+; CHECK: adrp [[ADDR:x[0-9]+]], [[CSTLABEL:.LCP.*]]
+; CHECK: ldr [[INFINITY:h[0-9]+]], {{[[]}}[[ADDR]], :lo12:[[CSTLABEL]]{{[]]}}
+; CHECK-NEXT: fabs [[ABS:h[0-9]+]], h0
+; CHECK-NEXT: fcmp [[ABS]], [[INFINITY]]
+; CHECK-NEXT: cset w0, eq
+ %abs = tail call half @llvm.fabs.f16(half %x)
+ %cmpinf = fcmp oeq half %abs, 0xH7C00
+ %ret = zext i1 %cmpinf to i32
+ ret i32 %ret
+}
+
+; Check if INFINITY for float is materialized
+define i32 @replace_isinf_call_f32(float %x) {
+; CHECK-LABEL: replace_isinf_call_f32:
+; CHECK: orr [[INFSCALARREG:w[0-9]+]], wzr, #0x7f800000
+; CHECK-NEXT: fabs [[ABS:s[0-9]+]], s0
+; CHECK-NEXT: fmov [[INFREG:s[0-9]+]], [[INFSCALARREG]]
+; CHECK-NEXT: fcmp [[ABS]], [[INFREG]]
+; CHECK-NEXT: cset w0, eq
+ %abs = tail call float @llvm.fabs.f32(float %x)
+ %cmpinf = fcmp oeq float %abs, 0x7FF0000000000000
+ %ret = zext i1 %cmpinf to i32
+ ret i32 %ret
+}
+
+; Check if INFINITY for double is materialized
+define i32 @replace_isinf_call_f64(double %x) {
+; CHECK-LABEL: replace_isinf_call_f64:
+; CHECK: orr [[INFSCALARREG:x[0-9]+]], xzr, #0x7ff0000000000000
+; CHECK-NEXT: fabs [[ABS:d[0-9]+]], d0
+; CHECK-NEXT: fmov [[INFREG:d[0-9]+]], [[INFSCALARREG]]
+; CHECK-NEXT: fcmp [[ABS]], [[INFREG]]
+; CHECK-NEXT: cset w0, eq
+ %abs = tail call double @llvm.fabs.f64(double %x)
+ %cmpinf = fcmp oeq double %abs, 0x7FF0000000000000
+ %ret = zext i1 %cmpinf to i32
+ ret i32 %ret
+}
+
+; For long double it still requires loading the constant.
+define i32 @replace_isinf_call_f128(fp128 %x) {
+; CHECK-LABEL: replace_isinf_call_f128:
+; CHECK: adrp [[ADDR:x[0-9]+]], [[CSTLABEL:.LCP.*]]
+; CHECK: ldr q1, {{[[]}}[[ADDR]], :lo12:[[CSTLABEL]]{{[]]}}
+; CHECK: bl __eqtf2
+; CHECK: cmp w0, #0
+; CHECK: cset w0, eq
+ %abs = tail call fp128 @llvm.fabs.f128(fp128 %x)
+ %cmpinf = fcmp oeq fp128 %abs, 0xL00000000000000007FFF000000000000
+ %ret = zext i1 %cmpinf to i32
+ ret i32 %ret
+}
diff --git a/test/CodeGen/AArch64/known-never-nan.ll b/test/CodeGen/AArch64/known-never-nan.ll
index 1ffbb9b..ef9fa5f 100644
--- a/test/CodeGen/AArch64/known-never-nan.ll
+++ b/test/CodeGen/AArch64/known-never-nan.ll
@@ -28,13 +28,13 @@
define float @not_fmaxnm_maybe_nan(i32 %i1, i32 %i2) #0 {
; CHECK-LABEL: not_fmaxnm_maybe_nan:
; CHECK: // %bb.0:
-; CHECK-NEXT: adrp x8, .LCPI1_0
-; CHECK-NEXT: ldr s0, [x8, :lo12:.LCPI1_0]
-; CHECK-NEXT: ucvtf s1, w0
-; CHECK-NEXT: ucvtf s2, w1
-; CHECK-NEXT: fmov s3, #17.00000000
-; CHECK-NEXT: fmul s0, s1, s0
-; CHECK-NEXT: fadd s1, s2, s3
+; CHECK-NEXT: orr w8, wzr, #0xff800000
+; CHECK-NEXT: ucvtf s0, w0
+; CHECK-NEXT: ucvtf s1, w1
+; CHECK-NEXT: fmov s2, #17.00000000
+; CHECK-NEXT: fmov s3, w8
+; CHECK-NEXT: fmul s0, s0, s3
+; CHECK-NEXT: fadd s1, s1, s2
; CHECK-NEXT: fcmp s0, s1
; CHECK-NEXT: fcsel s0, s0, s1, pl
; CHECK-NEXT: ret
diff --git a/test/CodeGen/AArch64/literal_pools_float.ll b/test/CodeGen/AArch64/literal_pools_float.ll
index 3c70634..1a67394 100644
--- a/test/CodeGen/AArch64/literal_pools_float.ll
+++ b/test/CodeGen/AArch64/literal_pools_float.ll
@@ -13,18 +13,16 @@
%floatval = load float, float* @varfloat
%newfloat = fadd float %floatval, 128.0
-; CHECK: adrp x[[LITBASE:[0-9]+]], [[CURLIT:.LCPI[0-9]+_[0-9]+]]
-; CHECK: ldr [[LIT128:s[0-9]+]], [x[[LITBASE]], {{#?}}:lo12:[[CURLIT]]]
+; CHECK: mov [[W128:w[0-9]+]], #1124073472
+; CHECK: fmov [[LIT128:s[0-9]+]], [[W128]]
; CHECK-NOFP-NOT: ldr {{s[0-9]+}},
-; CHECK-TINY: ldr [[LIT128:s[0-9]+]], [[CURLIT:.LCPI[0-9]+_[0-9]+]]
+; CHECK-TINY: mov [[W128:w[0-9]+]], #1124073472
+; CHECK-TINE: fmov [[LIT128:s[0-9]+]], [[W128]]
; CHECK-NOFP-TINY-NOT: ldr {{s[0-9]+}},
-; CHECK-LARGE: movz x[[LITADDR:[0-9]+]], #:abs_g0_nc:[[CURLIT:.LCPI[0-9]+_[0-9]+]]
-; CHECK-LARGE: movk x[[LITADDR]], #:abs_g1_nc:[[CURLIT]]
-; CHECK-LARGE: movk x[[LITADDR]], #:abs_g2_nc:[[CURLIT]]
-; CHECK-LARGE: movk x[[LITADDR]], #:abs_g3:[[CURLIT]]
-; CHECK-LARGE: ldr {{s[0-9]+}}, [x[[LITADDR]]]
+; CHECK-LARGE: mov [[W128:w[0-9]+]], #1124073472
+; CHECK-LARGE: fmov [[LIT128:s[0-9]+]], [[W128]]
; CHECK-LARGE: fadd
; CHECK-NOFP-LARGE-NOT: ldr {{s[0-9]+}},
; CHECK-NOFP-LARGE-NOT: fadd
diff --git a/test/CodeGen/AArch64/win_cst_pool.ll b/test/CodeGen/AArch64/win_cst_pool.ll
index 5bcc919..f26e7aa 100644
--- a/test/CodeGen/AArch64/win_cst_pool.ll
+++ b/test/CodeGen/AArch64/win_cst_pool.ll
@@ -2,22 +2,22 @@
; RUN: llc < %s -mtriple=aarch64-win32-gnu | FileCheck -check-prefix=MINGW %s
define double @double() {
- ret double 0x0000000000800000
+ ret double 0x0000000000800001
}
-; CHECK: .globl __real@0000000000800000
-; CHECK-NEXT: .section .rdata,"dr",discard,__real@0000000000800000
+; CHECK: .globl __real@0000000000800001
+; CHECK-NEXT: .section .rdata,"dr",discard,__real@0000000000800001
; CHECK-NEXT: .p2align 3
-; CHECK-NEXT: __real@0000000000800000:
-; CHECK-NEXT: .xword 8388608
+; CHECK-NEXT: __real@0000000000800001:
+; CHECK-NEXT: .xword 8388609
; CHECK: double:
-; CHECK: adrp x8, __real@0000000000800000
-; CHECK-NEXT: ldr d0, [x8, __real@0000000000800000]
+; CHECK: adrp x8, __real@0000000000800001
+; CHECK-NEXT: ldr d0, [x8, __real@0000000000800001]
; CHECK-NEXT: ret
; MINGW: .section .rdata,"dr"
; MINGW-NEXT: .p2align 3
; MINGW-NEXT: [[LABEL:\.LC.*]]:
-; MINGW-NEXT: .xword 8388608
+; MINGW-NEXT: .xword 8388609
; MINGW: double:
; MINGW: adrp x8, [[LABEL]]
; MINGW-NEXT: ldr d0, [x8, [[LABEL]]]
