mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 04:52:54 +02:00
20a3d2184f
Summary: Local values are constants, global addresses, and stack addresses that can't be folded into the instruction that uses them. For example, when storing the address of a global variable into memory, we need to materialize that address into a register. FastISel doesn't want to materialize any given local value more than once, so it generates all local value materialization code at EmitStartPt, which always dominates the current insertion point. This allows it to maintain a map of local value registers, and it knows that the local value area will always dominate the current insertion point. The downside is that local value instructions are always emitted without a source location. This is done to prevent jumpy line tables, but it means that the local value area will be considered part of the previous statement. Consider this C code: call1(); // line 1 ++global; // line 2 ++global; // line 3 call2(&global, &local); // line 4 Today we end up with assembly and line tables like this: .loc 1 1 callq call1 leaq global(%rip), %rdi leaq local(%rsp), %rsi .loc 1 2 addq $1, global(%rip) .loc 1 3 addq $1, global(%rip) .loc 1 4 callq call2 The LEA instructions in the local value area have no source location and are treated as being on line 1. Stepping through the code in a debugger and correlating it with the assembly won't make much sense, because these materializations are only required for line 4. This is actually problematic for the VS debugger "set next statement" feature, which effectively assumes that there are no registers live across statement boundaries. By sinking the local value code into the statement and fixing up the source location, we can make that feature work. This was filed as https://bugs.llvm.org/show_bug.cgi?id=35975 and https://crbug.com/793819. This change is obviously not enough to make this feature work reliably in all cases, but I felt that it was worth doing anyway because it usually generates smaller, more comprehensible -O0 code. I measured a 0.12% regression in code generation time with LLC on the sqlite3 amalgamation, so I think this is worth doing. There are some special cases worth calling out in the commit message: 1. local values materialized for phis 2. local values used by no-op casts 3. dead local value code Local values can be materialized for phis, and this does not show up as a vreg use in MachineRegisterInfo. In this case, if there are no other uses, this patch sinks the value to the first terminator, EH label, or the end of the BB if nothing else exists. Local values may also be used by no-op casts, which adds the register to the RegFixups table. Without reversing the RegFixups map direction, we don't have enough information to sink these instructions. Lastly, if the local value register has no other uses, we can delete it. This comes up when fastisel tries two instruction selection approaches and the first materializes the value but fails and the second succeeds without using the local value. Reviewers: aprantl, dblaikie, qcolombet, MatzeB, vsk, echristo Subscribers: dotdash, chandlerc, hans, sdardis, amccarth, javed.absar, zturner, llvm-commits, hiraditya Differential Revision: https://reviews.llvm.org/D43093 llvm-svn: 327581
119 lines
4.9 KiB
LLVM
119 lines
4.9 KiB
LLVM
; RUN: llc -mtriple=arm64-apple-darwin -enable-misched=0 -mcpu=cyclone < %s | FileCheck %s
|
|
; RUN: llc -mtriple=arm64-apple-darwin -enable-misched=0 -mcpu=cyclone -fast-isel < %s | FileCheck %s --check-prefix=FAST
|
|
; RUN: llc -mtriple=arm64-apple-darwin -enable-misched=0 -mcpu=cyclone -filetype=obj -o %t %s
|
|
; RUN: llvm-objdump -triple arm64-apple-darwin -d %t | FileCheck %s --check-prefix CHECK-ENCODING
|
|
|
|
; CHECK-ENCODING-NOT: <unknown>
|
|
; CHECK-ENCODING: mov x16, #281470681743360
|
|
; CHECK-ENCODING: movk x16, #57005, lsl #16
|
|
; CHECK-ENCODING: movk x16, #48879
|
|
|
|
; One argument will be passed in register, the other will be pushed on the stack.
|
|
; Return value in x0.
|
|
define void @jscall_patchpoint_codegen(i64 %p1, i64 %p2, i64 %p3, i64 %p4) {
|
|
entry:
|
|
; CHECK-LABEL: jscall_patchpoint_codegen:
|
|
; CHECK: str x{{.+}}, [sp]
|
|
; CHECK-NEXT: mov x0, x{{.+}}
|
|
; CHECK: Ltmp
|
|
; CHECK-NEXT: mov x16, #281470681743360
|
|
; CHECK: movk x16, #57005, lsl #16
|
|
; CHECK: movk x16, #48879
|
|
; CHECK-NEXT: blr x16
|
|
; FAST-LABEL: jscall_patchpoint_codegen:
|
|
; FAST: str x{{.+}}, [sp]
|
|
; FAST: Ltmp
|
|
; FAST-NEXT: mov x16, #281470681743360
|
|
; FAST-NEXT: movk x16, #57005, lsl #16
|
|
; FAST-NEXT: movk x16, #48879
|
|
; FAST-NEXT: blr x16
|
|
%resolveCall2 = inttoptr i64 281474417671919 to i8*
|
|
%result = tail call webkit_jscc i64 (i64, i32, i8*, i32, ...) @llvm.experimental.patchpoint.i64(i64 5, i32 20, i8* %resolveCall2, i32 2, i64 %p4, i64 %p2)
|
|
%resolveCall3 = inttoptr i64 244837814038255 to i8*
|
|
tail call webkit_jscc void (i64, i32, i8*, i32, ...) @llvm.experimental.patchpoint.void(i64 6, i32 20, i8* %resolveCall3, i32 2, i64 %p4, i64 %result)
|
|
ret void
|
|
}
|
|
|
|
; Test if the arguments are properly aligned and that we don't store undef arguments.
|
|
define i64 @jscall_patchpoint_codegen2(i64 %callee) {
|
|
entry:
|
|
; CHECK-LABEL: jscall_patchpoint_codegen2:
|
|
; CHECK: orr w[[REG:[0-9]+]], wzr, #0x6
|
|
; CHECK-NEXT: str x[[REG]], [sp, #24]
|
|
; CHECK-NEXT: orr w[[REG:[0-9]+]], wzr, #0x4
|
|
; CHECK-NEXT: str w[[REG]], [sp, #16]
|
|
; CHECK-NEXT: orr w[[REG:[0-9]+]], wzr, #0x2
|
|
; CHECK-NEXT: str x[[REG]], [sp]
|
|
; CHECK: Ltmp
|
|
; CHECK-NEXT: mov x16, #281470681743360
|
|
; CHECK-NEXT: movk x16, #57005, lsl #16
|
|
; CHECK-NEXT: movk x16, #48879
|
|
; CHECK-NEXT: blr x16
|
|
; FAST-LABEL: jscall_patchpoint_codegen2:
|
|
; FAST: orr [[REG1:x[0-9]+]], xzr, #0x2
|
|
; FAST-NEXT: str [[REG1]], [sp]
|
|
; FAST-NEXT: orr [[REG2:w[0-9]+]], wzr, #0x4
|
|
; FAST-NEXT: str [[REG2]], [sp, #16]
|
|
; FAST-NEXT: orr [[REG3:x[0-9]+]], xzr, #0x6
|
|
; FAST-NEXT: str [[REG3]], [sp, #24]
|
|
; FAST: Ltmp
|
|
; FAST-NEXT: mov x16, #281470681743360
|
|
; FAST-NEXT: movk x16, #57005, lsl #16
|
|
; FAST-NEXT: movk x16, #48879
|
|
; FAST-NEXT: blr x16
|
|
%call = inttoptr i64 281474417671919 to i8*
|
|
%result = call webkit_jscc i64 (i64, i32, i8*, i32, ...) @llvm.experimental.patchpoint.i64(i64 7, i32 20, i8* %call, i32 6, i64 %callee, i64 2, i64 undef, i32 4, i32 undef, i64 6)
|
|
ret i64 %result
|
|
}
|
|
|
|
; Test if the arguments are properly aligned and that we don't store undef arguments.
|
|
define i64 @jscall_patchpoint_codegen3(i64 %callee) {
|
|
entry:
|
|
; CHECK-LABEL: jscall_patchpoint_codegen3:
|
|
; CHECK: mov w[[REG:[0-9]+]], #10
|
|
; CHECK-NEXT: str x[[REG]], [sp, #48]
|
|
; CHECK-NEXT: orr w[[REG:[0-9]+]], wzr, #0x8
|
|
; CHECK-NEXT: str w[[REG]], [sp, #36]
|
|
; CHECK-NEXT: orr w[[REG:[0-9]+]], wzr, #0x6
|
|
; CHECK-NEXT: str x[[REG]], [sp, #24]
|
|
; CHECK-NEXT: orr w[[REG:[0-9]+]], wzr, #0x4
|
|
; CHECK-NEXT: str w[[REG]], [sp, #16]
|
|
; CHECK-NEXT: orr w[[REG:[0-9]+]], wzr, #0x2
|
|
; CHECK-NEXT: str x[[REG]], [sp]
|
|
; CHECK: Ltmp
|
|
; CHECK-NEXT: mov x16, #281470681743360
|
|
; CHECK-NEXT: movk x16, #57005, lsl #16
|
|
; CHECK-NEXT: movk x16, #48879
|
|
; CHECK-NEXT: blr x16
|
|
; FAST-LABEL: jscall_patchpoint_codegen3:
|
|
; FAST: orr [[REG1:x[0-9]+]], xzr, #0x2
|
|
; FAST-NEXT: str [[REG1]], [sp]
|
|
; FAST-NEXT: orr [[REG2:w[0-9]+]], wzr, #0x4
|
|
; FAST-NEXT: str [[REG2]], [sp, #16]
|
|
; FAST-NEXT: orr [[REG3:x[0-9]+]], xzr, #0x6
|
|
; FAST-NEXT: str [[REG3]], [sp, #24]
|
|
; FAST-NEXT: orr [[REG4:w[0-9]+]], wzr, #0x8
|
|
; FAST-NEXT: str [[REG4]], [sp, #36]
|
|
; FAST-NEXT: mov [[REG5:x[0-9]+]], #10
|
|
; FAST-NEXT: str [[REG5]], [sp, #48]
|
|
; FAST: Ltmp
|
|
; FAST-NEXT: mov x16, #281470681743360
|
|
; FAST-NEXT: movk x16, #57005, lsl #16
|
|
; FAST-NEXT: movk x16, #48879
|
|
; FAST-NEXT: blr x16
|
|
%call = inttoptr i64 281474417671919 to i8*
|
|
%result = call webkit_jscc i64 (i64, i32, i8*, i32, ...) @llvm.experimental.patchpoint.i64(i64 7, i32 20, i8* %call, i32 10, i64 %callee, i64 2, i64 undef, i32 4, i32 undef, i64 6, i32 undef, i32 8, i32 undef, i64 10)
|
|
ret i64 %result
|
|
}
|
|
|
|
; CHECK-LABEL: test_i16:
|
|
; CHECK: ldrh [[BREG:w[0-9]+]], [sp]
|
|
; CHECK: add {{w[0-9]+}}, w0, [[BREG]]
|
|
define webkit_jscc zeroext i16 @test_i16(i16 zeroext %a, i16 zeroext %b) {
|
|
%sum = add i16 %a, %b
|
|
ret i16 %sum
|
|
}
|
|
|
|
declare void @llvm.experimental.patchpoint.void(i64, i32, i8*, i32, ...)
|
|
declare i64 @llvm.experimental.patchpoint.i64(i64, i32, i8*, i32, ...)
|