Revert "Reland "make SkJumper stages normal Skia code""

This reverts commit 78cb579f33943421afc8423a39867fcfd69fed44.

Reason for revert: lowp should be controlled by defined(JUMPER_IS_SCALAR), not defined(__clang__).  So close.

Original change's description:
> Reland "make SkJumper stages normal Skia code"
> 
> This is a reland of 22e536e3a1a09405d1c0e6f071717a726d86e8d4
> 
> Now with fixed #include paths in SkRasterPipeline_opts.h,
> and -ffp-contract=fast for the :hsw target to minimize
> diffs on non-Windows Clang AVX2/AVX-512 bots.
> 
> Original change's description:
> > make SkJumper stages normal Skia code
> >
> > Enough clients are using Clang now that we can say, use Clang to build
> > if you want these software pipeline stages to go fast.
> >
> > This lets us drop the offline build aspect of SkJumper stages, instead
> > building as part of Skia using the SkOpts framework.
> >
> > I think everything should work, except I've (temporarily) removed
> > AVX-512 support.  I will put this back in a follow up.
> >
> > I have had to drop Windows down to __vectorcall and our narrower
> > stage calling convention that keeps the d-registers on the stack.
> > I tried forcing sysv_abi, but that crashed Clang.  :/
> >
> > Added a TODO to up the same narrower stage calling convention
> > for lowp stages... we just *don't* today, for no good reason.
> >
> > Change-Id: Iaaa792ffe4deab3508d2dc5d0008c163c24b3383
> > Reviewed-on: https://skia-review.googlesource.com/110641
> > Commit-Queue: Mike Klein <mtklein@chromium.org>
> > Reviewed-by: Herb Derby <herb@google.com>
> > Reviewed-by: Florin Malita <fmalita@chromium.org>
> 
> Change-Id: I44f2c03d33958e3807747e40904b6351957dd448
> Reviewed-on: https://skia-review.googlesource.com/112742
> Reviewed-by: Mike Klein <mtklein@chromium.org>

TBR=mtklein@chromium.org,herb@google.com,fmalita@chromium.org

Change-Id: Ie64da98f5187d44e03c0ce05d7cb189d4a6e6663
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Reviewed-on: https://skia-review.googlesource.com/112743
Reviewed-by: Mike Klein <mtklein@google.com>
Commit-Queue: Mike Klein <mtklein@google.com>

1 files changed, 29 insertions, 6 deletions

diff --git a/src/jumper/SkJumper.h b/src/jumper/SkJumper.h
index d4c4698048..e7bf9b2403 100644
--- a/src/jumper/SkJumper.h
+++ b/src/jumper/SkJumper.h
@@ -11,11 +11,34 @@
 #include <stddef.h>
 #include <stdint.h>
 
-// This file contains definitions shared by SkJumper.cpp/SkJumper_stages.cpp
-// and the rest of Skia.  It is important to keep the interface to SkJumper
-// limited and simple to avoid serious ODR violation pitfalls, especially when
-// using Microsoft's <math.h> and similar headers with inline-but-not-static
-// function definitions.
+// This file contains definitions shared by SkJumper.cpp (compiled normally as part of Skia)
+// and SkJumper_stages.cpp (compiled into Skia _and_ offline into SkJumper_generated.h).
+// Keep it simple!
+
+// Externally facing functions (start_pipeline) are called a little specially on Windows.
+#if defined(JUMPER_IS_OFFLINE) && defined(WIN) && defined(__x86_64__)
+    #define MAYBE_MSABI __attribute__((ms_abi))                   // Use MS' ABI, not System V.
+#elif defined(JUMPER_IS_OFFLINE) && defined(WIN) && defined(__i386__)
+    #define MAYBE_MSABI __attribute__((force_align_arg_pointer))  // Re-align stack 4 -> 16 bytes.
+#else
+    #define MAYBE_MSABI
+#endif
+
+// Any custom ABI to use for all non-externally-facing stage functions.
+#if defined(__ARM_NEON) && defined(__arm__)
+    // This lets us pass vectors more efficiently on 32-bit ARM.
+    #define ABI __attribute__((pcs("aapcs-vfp")))
+#else
+    #define ABI
+#endif
+
+// On ARM we expect that you're using Clang if you want SkJumper to be fast.
+// If you are, the baseline float stages will use NEON, and lowp stages will
+// also be available. (If somehow you're building for ARM not using Clang,
+// you'll get scalar baseline stages and no lowp support.)
+#if defined(__clang__) && defined(__ARM_NEON)
+    #define JUMPER_HAS_NEON_LOWP
+#endif
 
 static const int SkJumper_kMaxStride = 16;
 
@@ -53,7 +76,7 @@ struct SkJumper_DecalTileCtx {
 };
 
 struct SkJumper_CallbackCtx {
-    void (*fn)(SkJumper_CallbackCtx* self, int active_pixels/*<= SkJumper_kMaxStride*/);
+    MAYBE_MSABI void (*fn)(SkJumper_CallbackCtx* self, int active_pixels/*<= SkJumper_kMaxStride*/);
 
     // When called, fn() will have our active pixels available in rgba.
     // When fn() returns, the pipeline will read back those active pixels from read_from.