llvm-project/llvm/test/CodeGen/ARM/inlineasm.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

75 lines
2.7 KiB
LLVM
Raw Normal View History

; RUN: llc -mtriple=armv8-eabi -mattr=+neon %s -o - | FileCheck %s
define i32 @test1(i32 %tmp54) {
%tmp56 = tail call i32 asm "uxtb16 $0,$1", "=r,r"( i32 %tmp54 ) ; <i32> [#uses=1]
ret i32 %tmp56
}
define void @test2() {
tail call void asm sideeffect "/* number: ${0:c} */", "i"( i32 1 )
ret void
}
define float @t-constraint-int(i32 %i) {
; CHECK-LABEL: t-constraint-int
; CHECK: vcvt.f32.s32 {{s[0-9]+}}, {{s[0-9]+}}
%ret = call float asm "vcvt.f32.s32 $0, $1\0A", "=t,t"(i32 %i)
ret float %ret
}
[ARM] Allow 64- and 128-bit types with 't' inline asm constraint Summary: In LLVM, 't' selects a floating-point/SIMD register and only supports 32-bit values. This is appropriately documented in the LLVM Language Reference Manual. However, this behaviour diverges from that of GCC, where 't' selects the s0-s31 registers and its qX and dX variants depending on additional operand modifiers (q/P). For example, the following C code: #include <arm_neon.h> float32x4_t a, b, x; asm("vadd.f32 %0, %1, %2" : "=t" (x) : "t" (a), "t" (b)) results in the following assembly if compiled with GCC: vadd.f32 s0, s0, s1 whereas LLVM will show "error: couldn't allocate output register for constraint 't'", since a, b, x are 128-bit variables, not 32-bit. This patch extends the use of 't' to mean that of GCC, thus allowing selection of the lower Q vector regs and their D/S variants. For example, the earlier code will now compile as: vadd.f32 q0, q0, q1 This behaviour still differs from that of GCC but I think it is actually more correct, since LLVM picks up the right register type based on the datatype of x, while GCC would need an extra operand modifier to achieve the same result, as follows: asm("vadd.f32 %q0, %q1, %q2" : "=t" (x) : "t" (a), "t" (b)) Since this is only an extension of functionality, existing code should not be affected by this change. Note that operand modifiers q/P are already supported by LLVM, so this patch should suffice to support inline assembly with constraint 't' originally built for GCC. Reviewers: grosbach, rengolin Reviewed By: rengolin Subscribers: rogfer01, efriedma, olista01, aemerson, javed.absar, eraman, kristof.beyls, llvm-commits Differential Revision: https://reviews.llvm.org/D42962 llvm-svn: 325244
2018-02-15 22:44:22 +08:00
define <2 x i32> @t-constraint-int-vector-64bit(<2 x float> %x) {
entry:
; CHECK-LABEL: t-constraint-int-vector-64bit
; CHECK: vcvt.s32.f32 {{d[0-9]+}}, {{d[0-9]+}}
%0 = tail call <2 x i32> asm "vcvt.s32.f32 $0, $1", "=t,t"(<2 x float> %x)
ret <2 x i32> %0
}
define <4 x i32> @t-constraint-int-vector-128bit(<4 x float> %x) {
entry:
; CHECK-LABEL: t-constraint-int-vector-128bit
; CHECK: vcvt.s32.f32 {{q[0-7]}}, {{q[0-7]}}
%0 = tail call <4 x i32> asm "vcvt.s32.f32 $0, $1", "=t,t"(<4 x float> %x)
ret <4 x i32> %0
}
define <2 x float> @t-constraint-float-vector-64bit(<2 x float> %a, <2 x float> %b) {
entry:
; CHECK-LABEL: t-constraint-float-vector-64bit
; CHECK: vadd.f32 d{{[0-9]+}}, d{{[0-9]+}}, d{{[0-9]+}}
%0 = tail call <2 x float> asm "vadd.f32 $0, $1, $2", "=t,t,t"(<2 x float> %a, <2 x float> %b)
ret <2 x float> %0
}
define <4 x float> @t-constraint-float-vector-128bit(<4 x float> %a, <4 x float> %b) {
entry:
; CHECK-LABEL: t-constraint-float-vector-128bit
; CHECK: vadd.f32 q{{[0-7]}}, q{{[0-7]}}, q{{[0-7]}}
%0 = tail call <4 x float> asm "vadd.f32 $0, $1, $2", "=t,t,t"(<4 x float> %a, <4 x float> %b)
ret <4 x float> %0
}
define i32 @even-GPR-constraint() {
entry:
; CHECK-LABEL: even-GPR-constraint
; CHECK: add [[REG:r1*[0, 2, 4, 6, 8]]], [[REG]], #1
; CHECK: add [[REG:r1*[0, 2, 4, 6, 8]]], [[REG]], #2
; CHECK: add [[REG:r1*[0, 2, 4, 6, 8]]], [[REG]], #3
; CHECK: add [[REG:r1*[0, 2, 4, 6, 8]]], [[REG]], #4
%0 = tail call { i32, i32, i32, i32 } asm "add $0, #1\0Aadd $1, #2\0Aadd $2, #3\0Aadd $3, #4\0A", "=^Te,=^Te,=^Te,=^Te,0,1,2,3"(i32 0, i32 0, i32 0, i32 0)
%asmresult = extractvalue { i32, i32, i32, i32 } %0, 0
ret i32 %asmresult
}
define i32 @odd-GPR-constraint() {
entry:
; CHECK-LABEL: odd-GPR-constraint
; CHECK: add [[REG:r1*[1, 3, 5, 7, 9]]], [[REG]], #1
; CHECK: add [[REG:r1*[1, 3, 5, 7, 9]]], [[REG]], #2
; CHECK: add [[REG:r1*[1, 3, 5, 7, 9]]], [[REG]], #3
; CHECK: add [[REG:r1*[1, 3, 5, 7, 9]]], [[REG]], #4
%0 = tail call { i32, i32, i32, i32 } asm "add $0, #1\0Aadd $1, #2\0Aadd $2, #3\0Aadd $3, #4\0A", "=^To,=^To,=^To,=^To,0,1,2,3"(i32 0, i32 0, i32 0, i32 0)
%asmresult = extractvalue { i32, i32, i32, i32 } %0, 0
ret i32 %asmresult
}