CmmEntry :: !Label -> CmmTickScope -> CmmNode C O

CmmComment :: FastString -> CmmNode O O

CmmTick :: !CmmTickish -> CmmNode O O

CmmUnwind :: [(GlobalReg, Maybe CmmExpr)] -> CmmNode O O

CmmAssign :: !CmmReg -> !CmmExpr -> CmmNode O O

CmmStore :: !CmmExpr -> !CmmExpr -> CmmNode O O

CmmUnsafeForeignCall :: ForeignTarget -> [CmmFormal] -> [CmmActual] -> CmmNode O O

CmmBranch :: !Label -> CmmNode O C

CmmCondBranch

CmmSwitch :: CmmExpr -> SwitchTargets -> CmmNode O C

CmmCall

CmmForeignCall

NativeDirectCall

top-level Haskell functions use NativeDirectCall, which maps arguments to registers starting with R2, according to how many registers are available on the platform. This convention ignores R1, because for a top-level function call the function closure is implicit, and doesn't need to be passed.

NativeNodeCall

non-top-level Haskell functions, which pass the address of the function closure in R1 (regardless of whether R1 is a real register or not), and the rest of the arguments in registers or on the stack.

NativeReturn

a native return. The convention for returns depends on how many values are returned: for just one value returned, the appropriate register is used (R1, F1, etc.). regardless of whether it is a real register or not. For multiple values returned, they are mapped to registers or the stack.

Slow

Slow entry points: all args pushed on the stack

GC

Entry to the garbage collector: uses the node reg! (TODO: I don't think we need this --SDM)

ForeignConvention CCallConv [ForeignHint] [ForeignHint] CmmReturnInfo

ForeignTarget CmmExpr ForeignConvention

PrimTarget CallishMachOp

CmmMayReturn

CmmNeverReturns

GlobalScope

The global scope is the "root" of the scope graph. Every scope is a sub-scope of the global scope. It doesn't make sense to add ticks to this scope. On the other hand, this means that setting this scope on a block means no ticks apply to it.

SubScope !Unique CmmTickScope

Constructs a new sub-scope to an existing scope. This allows us to translate Core-style scoping rules (see tickishScoped) into the Cmm world. Suppose the following code:

tick1 case ... of A -> tick2 ... B -> tick3 ...

We want the top-level tick annotation to apply to blocks generated for the A and B alternatives. We can achieve that by generating tick1 into a block with scope a, while the code for alternatives A and B gets generated into sub-scopes a/b and a/c respectively.

CombinedScope CmmTickScope CmmTickScope

A combined scope scopes over everything that the two given scopes cover. It is therefore a sub-scope of either scope. This is required for optimisations. Consider common block elimination:

A -> tick2 case ... of C -> [common] B -> tick3 case ... of D -> [common]

We will generate code for the C and D alternatives, and figure out afterwards that it's actually common code. Scoping rules dictate that the resulting common block needs to be covered by both tick2 and tick3, therefore we need to construct a scope that is a child to *both* scope. Now we can do that - if we assign the scopes ac and bd to the common-ed up blocks, the new block could have a combined tick scope ac+bd, which both tick2 and tick3 apply to.