Allow packing constructor fields

This is another step for fixing #13825 and is based on D38 by Simon
Marlow.

The change allows storing multiple constructor fields within the same
word. This currently applies only to `Float`s, e.g.,
```
data Foo = Foo {-# UNPACK #-} !Float {-# UNPACK #-} !Float
```
on 64-bit arch, will now store both fields within the same constructor
word. For `WordX/IntX` we'll need to introduce new primop types.

Main changes:

- We now use sizes in bytes when we compute the offsets for
  constructor fields in `StgCmmLayout` and introduce padding if
  necessary (word-sized fields are still word-aligned)

- `ByteCodeGen` had to be updated to correctly construct the data
  types. This required some new bytecode instructions to allow pushing
  things that are not full words onto the stack (and updating
  `Interpreter.c`). Note that we only use the packed stuff when
  constructing data types (i.e., for `PACK`), in all other cases the
  behavior should not change.

- `RtClosureInspect` was changed to handle the new layout when
  extracting subterms. This seems to be used by things like `:print`.
  I've also added a test for this.

- I deviated slightly from Simon's approach and use `PrimRep` instead
  of `ArgRep` for computing the size of fields.  This seemed more
  natural and in the future we'll probably want to introduce new
  primitive types (e.g., `Int8#`) and `PrimRep` seems like a better
  place to do that (where we already have `Int64Rep` for example).
  `ArgRep` on the other hand seems to be more focused on calling
  functions.

Signed-off-by: Michal Terepeta <michal.terepeta@gmail.com>

Test Plan: ./validate

Reviewers: bgamari, simonmar, austin, hvr, goldfire, erikd

Reviewed By: bgamari

Subscribers: maoe, rwbarton, thomie

GHC Trac Issues: #13825

Differential Revision: https://phabricator.haskell.org/D3809

2 files changed, 68 insertions, 52 deletions

diff --git a/includes/rts/Bytecodes.h b/includes/rts/Bytecodes.h
index 6ca74bf36e..e5d55f694f 100644
--- a/includes/rts/Bytecodes.h
+++ b/includes/rts/Bytecodes.h
@@ -27,58 +27,70 @@
 #define bci_PUSH_L    			2
 #define bci_PUSH_LL   			3
 #define bci_PUSH_LLL  			4
-#define bci_PUSH_G    			5
-#define bci_PUSH_ALTS  			6
-#define bci_PUSH_ALTS_P			7
-#define bci_PUSH_ALTS_N			8 
-#define bci_PUSH_ALTS_F			9 
-#define bci_PUSH_ALTS_D			10
-#define bci_PUSH_ALTS_L			11
-#define bci_PUSH_ALTS_V			12
-#define bci_PUSH_UBX  			13
-#define bci_PUSH_APPLY_N		14
-#define bci_PUSH_APPLY_F		15
-#define bci_PUSH_APPLY_D		16
-#define bci_PUSH_APPLY_L		17
-#define bci_PUSH_APPLY_V		18
-#define bci_PUSH_APPLY_P		19
-#define bci_PUSH_APPLY_PP		20
-#define bci_PUSH_APPLY_PPP		21
-#define bci_PUSH_APPLY_PPPP		22
-#define bci_PUSH_APPLY_PPPPP		23
-#define bci_PUSH_APPLY_PPPPPP		24
-/* #define bci_PUSH_APPLY_PPPPPPP		25 */
-#define bci_SLIDE     			26
-#define bci_ALLOC_AP   			27
-#define bci_ALLOC_AP_NOUPD		28
-#define bci_ALLOC_PAP  			29
-#define bci_MKAP      			30
-#define bci_MKPAP      			31
-#define bci_UNPACK    			32
-#define bci_PACK      			33
-#define bci_TESTLT_I   			34
-#define bci_TESTEQ_I  			35
-#define bci_TESTLT_F  			36
-#define bci_TESTEQ_F  			37
-#define bci_TESTLT_D  			38
-#define bci_TESTEQ_D  			39
-#define bci_TESTLT_P  			40
-#define bci_TESTEQ_P  			41
-#define bci_CASEFAIL  			42
-#define bci_JMP       			43
-#define bci_CCALL     			44
-#define bci_SWIZZLE   			45
-#define bci_ENTER     			46
-#define bci_RETURN    			47
-#define bci_RETURN_P 			48
-#define bci_RETURN_N 			49
-#define bci_RETURN_F 			50
-#define bci_RETURN_D 			51
-#define bci_RETURN_L 			52
-#define bci_RETURN_V 			53
-#define bci_BRK_FUN			54
-#define bci_TESTLT_W   			55
-#define bci_TESTEQ_W  			56
+#define bci_PUSH8                       5
+#define bci_PUSH16                      6
+#define bci_PUSH32                      7
+#define bci_PUSH8_W                     8
+#define bci_PUSH16_W                    9
+#define bci_PUSH32_W                    10
+#define bci_PUSH_G    			11
+#define bci_PUSH_ALTS  			12
+#define bci_PUSH_ALTS_P			13
+#define bci_PUSH_ALTS_N			14
+#define bci_PUSH_ALTS_F			15
+#define bci_PUSH_ALTS_D			16
+#define bci_PUSH_ALTS_L			17
+#define bci_PUSH_ALTS_V			18
+#define bci_PUSH_PAD8                   19
+#define bci_PUSH_PAD16                  20
+#define bci_PUSH_PAD32                  21
+#define bci_PUSH_UBX8                   22
+#define bci_PUSH_UBX16                  23
+#define bci_PUSH_UBX32                  24
+#define bci_PUSH_UBX  			25
+#define bci_PUSH_APPLY_N		26
+#define bci_PUSH_APPLY_F		27
+#define bci_PUSH_APPLY_D		28
+#define bci_PUSH_APPLY_L		29
+#define bci_PUSH_APPLY_V		30
+#define bci_PUSH_APPLY_P		31
+#define bci_PUSH_APPLY_PP		32
+#define bci_PUSH_APPLY_PPP		33
+#define bci_PUSH_APPLY_PPPP		34
+#define bci_PUSH_APPLY_PPPPP		35
+#define bci_PUSH_APPLY_PPPPPP		36
+/* #define bci_PUSH_APPLY_PPPPPPP		37 */
+#define bci_SLIDE     			38
+#define bci_ALLOC_AP   			39
+#define bci_ALLOC_AP_NOUPD		40
+#define bci_ALLOC_PAP  			41
+#define bci_MKAP      			42
+#define bci_MKPAP      			43
+#define bci_UNPACK    			44
+#define bci_PACK      			45
+#define bci_TESTLT_I   			46
+#define bci_TESTEQ_I  			47
+#define bci_TESTLT_F  			48
+#define bci_TESTEQ_F  			49
+#define bci_TESTLT_D  			50
+#define bci_TESTEQ_D  			51
+#define bci_TESTLT_P  			52
+#define bci_TESTEQ_P  			53
+#define bci_CASEFAIL  			54
+#define bci_JMP       			55
+#define bci_CCALL     			56
+#define bci_SWIZZLE   			57
+#define bci_ENTER     			58
+#define bci_RETURN    			59
+#define bci_RETURN_P 			60
+#define bci_RETURN_N 			61
+#define bci_RETURN_F 			62
+#define bci_RETURN_D 			63
+#define bci_RETURN_L 			64
+#define bci_RETURN_V 			65
+#define bci_BRK_FUN			66
+#define bci_TESTLT_W   			67
+#define bci_TESTEQ_W  			68
 /* If you need to go past 255 then you will run into the flags */
 
 /* If you need to go below 0x0100 then you will run into the instructions */
diff --git a/includes/stg/Types.h b/includes/stg/Types.h
index af6a51791c..91ad446993 100644
--- a/includes/stg/Types.h
+++ b/includes/stg/Types.h
@@ -68,6 +68,8 @@ typedef uint8_t                  StgWord8;
 #define STG_INT8_MAX             INT8_MAX
 #define STG_WORD8_MAX            UINT8_MAX
 
+#define FMT_Word8                PRIu8
+
 typedef int16_t                  StgInt16;
 typedef uint16_t                 StgWord16;
 
@@ -75,6 +77,8 @@ typedef uint16_t                 StgWord16;
 #define STG_INT16_MAX            INT16_MAX
 #define STG_WORD16_MAX           UINT16_MAX
 
+#define FMT_Word16               PRIu16
+
 typedef int32_t                  StgInt32;
 typedef uint32_t                 StgWord32;