Eliot Miranda uploaded a new version of VMMaker to project VM Maker:
http://source.squeak.org/VMMaker/VMMaker.oscog-eem.2284.mcz

==================== Summary ====================

Name: VMMaker.oscog-eem.2284
Author: eem
Time: 28 November 2017, 12:33:18.151794 pm
UUID: 9a2dfc11-2654-41d3-a83f-9a98cbc9ce2a
Ancestors: VMMaker.oscog-nice.2283

BitBltSimulation>>copyLoop:
Strength reduce the loop split for combinationRule = 3 so that less tests are done in the inner loop and so trhat when combinstionRule = 3 mergeFn is never used.  Use an explicit type declaration for unskew instead of trickier relying on type inference.  Eliminate bogus use of #== for numeric comparison.

=============== Diff against VMMaker.oscog-nice.2283 ===============

Item was changed:
  ----- Method: BitBltSimulation>>copyLoop (in category 'inner loop') -----
  copyLoop
  	| prevWord thisWord skewWord halftoneWord mergeWord hInc y unskew skewMask notSkewMask mergeFnwith destWord |
  	"This version of the inner loop assumes noSource = false."
  	<inline: false>
  	<var: #mergeFnwith declareC: 'unsigned int (*mergeFnwith)(unsigned int, unsigned int)'>
  	<var: #prevWord type: #'unsigned int'>
  	<var: #thisWord type: #'unsigned int'>
  	<var: #skewWord type: #'unsigned int'>
  	<var: #halftoneWord type: #'unsigned int'>
  	<var: #mergeWord type: #'unsigned int'>
  	<var: #destWord type: #'unsigned int'>
  	<var: #skewMask type: #'unsigned int'>
  	<var: #notSkewMask type: #'unsigned int'>
+ 	<var: #unskew type: #int> "unskew is a bitShift and MUST remain signed, while skewMask is unsigned."
  	mergeFnwith := self cCoerce: (opTable at: combinationRule+1) to: 'unsigned int (*)(unsigned int, unsigned int)'.
  	mergeFnwith.  "null ref for compiler"
  
  	hInc := hDir*4.  "Byte delta"
  	"degenerate skew fixed for Sparc. 10/20/96 ikp"
+ 	skew = -32
+ 		ifTrue: [skew := unskew := skewMask := 0]
- 	skew == -32
- 		ifTrue:
- 			["Beware: separate skewMask initialization to avoid bad type inference.
- 			Indeed, unskew is a bitShift and MUST remain signed, while skewMask is unsigned"
- 			skew := unskew := 0.
- 			skewMask := 0]
  		ifFalse: [skew < 0
  			ifTrue:
  				[unskew := skew+32.
  				skewMask := AllOnes << (0-skew)]
  			ifFalse:
  				[skew = 0
  					ifTrue:
  						[unskew := 0.
  						skewMask := AllOnes]
  					ifFalse:
  						[unskew := skew-32.
  						skewMask := AllOnes >> skew]]].
  	notSkewMask := skewMask bitInvert32.
  	noHalftone
  		ifTrue: [halftoneWord := AllOnes.  halftoneHeight := 0]
  		ifFalse: [halftoneWord := self halftoneAt: 0].
  
  	y := dy.
+ 	"here is the vertical loop, in two versions, one for the combinationRule = 3 copy mode, one for the general case."
+ combinationRule = 3
+   ifTrue:
+ 	[1 to: bbH do: "here is the vertical loop for combinationRule = 3 copy mode; no need to call merge"
- 	1 to: bbH do: "here is the vertical loop"
  		[ :i |
  		halftoneHeight > 1 ifTrue:  "Otherwise, its always the same"
  			[halftoneWord := self halftoneAt: y.
  			y := y + vDir].
  		preload ifTrue:
  			["load the 64-bit shifter"
  			prevWord := self srcLongAt: sourceIndex.
  			self incSrcIndex: hInc]
  			ifFalse:
  			[prevWord := 0].
  
  	"Note: the horizontal loop has been expanded into three parts for speed:"
  
  			"This first section requires masking of the destination store..."
  			destMask := mask1.
  			thisWord := self srcLongAt: sourceIndex.  "pick up next word"
  			self incSrcIndex: hInc.
  			skewWord := ((prevWord bitAnd: notSkewMask) bitShift: unskew)
  							bitOr:  "32-bit rotate"
  						((thisWord bitAnd: skewMask) bitShift: skew).
  			prevWord := thisWord.
  			destWord := self dstLongAt: destIndex.
+ 			destWord := (destMask bitAnd: (skewWord bitAnd: halftoneWord)) bitOr:
- 			mergeWord := self mergeFn: (skewWord bitAnd: halftoneWord) with: destWord.
- 			destWord := (destMask bitAnd: mergeWord) bitOr:
  							(destWord bitAnd: destMask bitInvert32).
  			self dstLongAt: destIndex put: destWord.
  			self incDestIndex: hInc.
  
  		"This central horizontal loop requires no store masking"
  		destMask := AllOnes.
+ 		(skew = 0) & (halftoneWord = AllOnes)
- combinationRule = 3
- ifTrue: [(skew = 0) & (halftoneWord = AllOnes)
  		ifTrue: 
  		["Very special inner loop for STORE mode with no skew -- just move words"
  		hDir = -1
  		ifTrue: ["Woeful patch: revert to older code for hDir = -1"
  				2 to: nWords-1 do: 
  					[ :word |
  					thisWord := self srcLongAt: sourceIndex.
  					self incSrcIndex: hInc.
  					self dstLongAt: destIndex put: thisWord.
  					self incDestIndex: hInc]]
  		ifFalse: [2 to: nWords-1 do: 
  					[ :word |  "Note loop starts with prevWord loaded (due to preload)"
  					self dstLongAt: destIndex put: prevWord.
  					self incDestIndex: hInc.
  					prevWord := self srcLongAt: sourceIndex.
  					self incSrcIndex: hInc]]]
  		ifFalse:
  		["Special inner loop for STORE mode -- no need to call merge"
  		2 to: nWords-1 do: 
  			[ :word |
  			thisWord := self srcLongAt: sourceIndex.
  			self incSrcIndex: hInc.
  			skewWord := ((prevWord bitAnd: notSkewMask) bitShift: unskew)
  							bitOr:  "32-bit rotate"
  						((thisWord bitAnd: skewMask) bitShift: skew).
  			prevWord := thisWord.
  			self dstLongAt: destIndex put: (skewWord bitAnd: halftoneWord).
+ 			self incDestIndex: hInc]].
+ 
+ 		"This last section, if used, requires masking of the destination store..."
+ 		nWords > 1 ifTrue:
+ 			[destMask := mask2.
+ 			thisWord := self srcLongAt: sourceIndex.  "pick up next word"
+ 			self incSrcIndex: hInc.
+ 			skewWord := ((prevWord bitAnd: notSkewMask) bitShift: unskew)
+ 							bitOr:  "32-bit rotate"
+ 						((thisWord bitAnd: skewMask) bitShift: skew).
+ 			destWord := self dstLongAt: destIndex.
+ 			destWord := (destMask bitAnd: (skewWord bitAnd: halftoneWord)) bitOr:
+ 							(destWord bitAnd: destMask bitInvert32).
+ 			self dstLongAt: destIndex put: destWord.
+ 			self incDestIndex: hInc].
+ 
+ 	self incSrcIndex: sourceDelta.
+ 	self incDestIndex: destDelta]]
+   ifFalse:
+ 	[1 to: bbH do: "here is the vertical loop for the general case (combinationRule ~= 3)"
+ 		[ :i |
+ 		halftoneHeight > 1 ifTrue:  "Otherwise, its always the same"
+ 			[halftoneWord := self halftoneAt: y.
+ 			y := y + vDir].
+ 		preload ifTrue:
+ 			["load the 64-bit shifter"
+ 			prevWord := self srcLongAt: sourceIndex.
+ 			self incSrcIndex: hInc]
+ 			ifFalse:
+ 			[prevWord := 0].
+ 
+ 	"Note: the horizontal loop has been expanded into three parts for speed:"
+ 
+ 			"This first section requires masking of the destination store..."
+ 			destMask := mask1.
+ 			thisWord := self srcLongAt: sourceIndex.  "pick up next word"
+ 			self incSrcIndex: hInc.
+ 			skewWord := ((prevWord bitAnd: notSkewMask) bitShift: unskew)
+ 							bitOr:  "32-bit rotate"
+ 						((thisWord bitAnd: skewMask) bitShift: skew).
+ 			prevWord := thisWord.
+ 			destWord := self dstLongAt: destIndex.
+ 			mergeWord := self mergeFn: (skewWord bitAnd: halftoneWord) with: destWord.
+ 			destWord := (destMask bitAnd: mergeWord) bitOr:
+ 							(destWord bitAnd: destMask bitInvert32).
+ 			self dstLongAt: destIndex put: destWord.
+ 			self incDestIndex: hInc.
+ 
+ 		"This central horizontal loop requires no store masking"
+ 		destMask := AllOnes.
+ 		2 to: nWords-1 do: "Normal inner loop does merge:"
- 			self incDestIndex: hInc]]
- ] ifFalse: [2 to: nWords-1 do: "Normal inner loop does merge:"
  			[ :word |
  			thisWord := self srcLongAt: sourceIndex.  "pick up next word"
  			self incSrcIndex: hInc.
  			skewWord := ((prevWord bitAnd: notSkewMask) bitShift: unskew)
  							bitOr:  "32-bit rotate"
  						((thisWord bitAnd: skewMask) bitShift: skew).
  			prevWord := thisWord.
  			mergeWord := self mergeFn: (skewWord bitAnd: halftoneWord)
  							with: (self dstLongAt: destIndex).
  			self dstLongAt: destIndex put: mergeWord.
+ 			self incDestIndex: hInc].
- 			self incDestIndex: hInc]
- ].
  
  		"This last section, if used, requires masking of the destination store..."
  		nWords > 1 ifTrue:
  			[destMask := mask2.
  			thisWord := self srcLongAt: sourceIndex.  "pick up next word"
  			self incSrcIndex: hInc.
  			skewWord := ((prevWord bitAnd: notSkewMask) bitShift: unskew)
  							bitOr:  "32-bit rotate"
  						((thisWord bitAnd: skewMask) bitShift: skew).
  			destWord := self dstLongAt: destIndex.
  			mergeWord := self mergeFn: (skewWord bitAnd: halftoneWord) with: destWord.
  			destWord := (destMask bitAnd: mergeWord) bitOr:
  							(destWord bitAnd: destMask bitInvert32).
  			self dstLongAt: destIndex put: destWord.
  			self incDestIndex: hInc].
  
  	self incSrcIndex: sourceDelta.
+ 	self incDestIndex: destDelta]]!
- 	self incDestIndex: destDelta]!